Authors: Saeed AlMarri, Mathieu Ravaut, Kristof Juhasz, Gautier Marti, Hamdan Al Ahbabi, Ibrahim Elfadel
Abstract: Large Language Models (LLMs) have attracted significant attention for classification tasks, offering a flexible alternative to trusted classical machine learning models like LightGBM through zero-shot prompting. However, their reliability for structured tabular data remains unclear, particularly in high stakes applications like financial risk assessment. Our study systematically evaluates LLMs and generates their SHAP values on financial classification tasks. Our analysis shows a divergence between LLMs self-explanation of feature impact and their SHAP values, as well as notable differences between LLMs and LightGBM SHAP values. These findings highlight the limitations of LLMs as standalone classifiers for structured financial modeling, but also instill optimism that improved explainability mechanisms coupled with few-shot prompting will make LLMs usable in risk-sensitive domains.
Authors: Alessandro De Palma, Greta Dolcetti, Caterina Urban
Abstract: Verified explanations are a theoretically-principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations. FaVeX accelerates the computation by dynamically combining batch and sequential processing of input features, and by reusing information from previous queries, both when proving invariances with respect to certain input features, and when searching for feature assignments altering the prediction. Furthermore, we present a novel and hierarchical definition of verified explanations, termed verifier-optimal robust explanations, that explicitly factors the incompleteness of network verifiers within the explanation. Our comprehensive experimental evaluation demonstrates the superior scalability of both FaVeX, and of verifier-optimal robust explanations, which together can produce meaningful formal explanation on networks with hundreds of thousands of non-linear activations.
Authors: Colin Doumont, Donney Fan, Natalie Maus, Jacob R. Gardner, Henry Moss, Geoff Pleiss
Abstract: High-dimensional spaces have challenged Bayesian optimization (BO). Existing methods aim to overcome this so-called curse of dimensionality by carefully encoding structural assumptions, from locality to sparsity to smoothness, into the optimization procedure. Surprisingly, we demonstrate that these approaches are outperformed by arguably the simplest method imaginable: Bayesian linear regression. After applying a geometric transformation to avoid boundary-seeking behavior, Gaussian processes with linear kernels match state-of-the-art performance on tasks with 60- to 6,000-dimensional search spaces. Linear models offer numerous advantages over their non-parametric counterparts: they afford closed-form sampling and their computation scales linearly with data, a fact we exploit on molecular optimization tasks with > 20,000 observations. Coupled with empirical analyses, our results suggest the need to depart from past intuitions about BO methods in high-dimensional spaces.
Authors: Mohamed Bouadi, Pratinav Seth, Aditya Tanna, Vinay Kumar Sankarapu
Abstract: Tabular data drive most real-world machine learning applications, yet building general-purpose models for them remains difficult. Mixed numeric and categorical fields, weak feature structure, and limited labeled data make scaling and generalization challenging. To this end, we introduce Orion-Bix, a tabular foundation model that combines biaxial attention with meta-learned in-context reasoning for few-shot tabular learning. Its encoder alternates standard, grouped, hierarchical, and relational attention, fusing their outputs through multi-CLS summarization to capture both local and global dependencies efficiently. A label-aware ICL head adapts on the fly and scales to large label spaces via hierarchical decision routing. Meta-trained on synthetically generated, structurally diverse tables with causal priors, Orion-Bix learns transferable inductive biases across heterogeneous data. Delivered as a scikit-learn compatible foundation model, it outperforms gradient-boosting baselines and remains competitive with state-of-the-art tabular foundation models on public benchmarks, showing that biaxial attention with episodic meta-training enables robust, few-shot-ready tabular learning. The model is publicly available at https://github.com/Lexsi-Labs/Orion-BiX .
Authors: Jose Luis Lima de Jesus Silva, Joao Pedro Gomes, Paulo Roberto de Melo Barros Junior, Vitor Hugo Serravalle Reis Rodrigues, Alexsandro Guerra Cerqueira
Abstract: Interpreting seismic horizons is a critical task for characterizing subsurface structures in hydrocarbon exploration. Recent advances in deep learning, particularly U-Net-based architectures, have significantly improved automated horizon tracking. However, challenges remain in accurately segmenting complex geological features and interpolating horizons from sparse annotations. To address these issues, a hybrid framework is presented that integrates advanced U-Net variants with spatial clustering to enhance horizon continuity and geometric fidelity. The core contribution is the Context Fusion Attention (CFA) U-Net, a novel architecture that fuses spatial and Sobel-derived geometric features within attention gates to improve both precision and surface completeness. The performance of five architectures, the U-Net (Standard and compressed), U-Net++, Attention U-Net, and CFA U-Net, was systematically evaluated across various data sparsity regimes (10-, 20-, and 40-line spacing). This approach outperformed existing baselines, achieving state-of-the-art results on the Mexilhao field (Santos Basin, Brazil) dataset with a validation IoU of 0.881 and MAE of 2.49ms, and excellent surface coverage of 97.6% on the F3 Block of the North Sea dataset under sparse conditions. The framework further refines merged horizon predictions (inline and cross-line) using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to produce geologically plausible surfaces. The results demonstrate the advantages of hybrid methodologies and attention-based architectures enhanced with geometric context, providing a robust and generalizable solution for seismic interpretation in structurally complex and data-scarce environments.
Authors: Julian Brandon, Angus Chadwick, Arthur Pellegrino
Abstract: Many tasks require mapping continuous input data (e.g. images) to discrete task outputs (e.g. class labels). Yet, how neural networks learn to perform such discrete computations on continuous data manifolds remains poorly understood. Here, we show that signatures of such computations emerge in the representational geometry of neural networks as they learn. By analysing the Riemannian pullback metric across layers of a neural network, we find that network computation can be decomposed into two functions: discretising continuous input features and performing logical operations on these discretised variables. Furthermore, we demonstrate how different learning regimes (rich vs. lazy) have contrasting metric and curvature structures, affecting the ability of the networks to generalise to unseen inputs. Overall, our work provides a geometric framework for understanding how neural networks learn to perform discrete computations on continuous manifolds.
Authors: Owen Dugan, Roberto Garcia, Ronny Junkins, Jerry Liu, Dylan Zinsley, Sabri Eyuboglu, Atri Rudra, Chris R\'e
Abstract: The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Recent work has proposed explicit weight constructions to build such fact-storing MLPs, providing an improved understanding of LLM fact storage mechanisms. In this paper, we introduce an MLP construction framework that improves over previous constructions in three areas: it 1) works for all but a measure-zero set of feasible input-output pairs, 2) achieves asymptotically optimal parameter efficiency matching information-theoretic bounds for some embeddings, and 3) maintains usability within Transformers for factual recall. Through our improvements, we 1) discover a metric on value embeddings that characterizes facts-per-parameter scaling for both constructed and gradient-descent-trained MLPs, 2) identify a simple encoder-decoder mechanism that empirically matches gradient-descent MLP facts-per-parameter asymptotics across all the inputs and outputs we test, and 3) uncover a fundamental tradeoff between an MLP's fact-storage capacity and its usability within Transformers. Finally, we demonstrate a proof-of-concept application of fact-storing MLPs: modular fact editing on one-layer Transformers by \textit{replacing entire MLPs at once}.
Authors: Pirzada Suhail, Rehna Afroz, Amit Sethi
Abstract: Deep neural networks often struggle to recognize when an input lies outside their training experience, leading to unreliable and overconfident predictions. Building dependable machine learning systems therefore requires methods that can both estimate predictive \textit{uncertainty} and detect \textit{out-of-distribution (OOD)} samples in a unified manner. In this paper, we propose \textbf{TIE: a Training--Inversion--Exclusion} framework for visually interpretable and uncertainty-guided anomaly detection that jointly addresses these challenges through iterative refinement. TIE extends a standard $n$-class classifier to an $(n+1)$-class model by introducing a garbage class initialized with Gaussian noise to represent outlier inputs. Within each epoch, TIE performs a closed-loop process of \textit{training, inversion, and exclusion}, where highly uncertain inverted samples reconstructed from the just-trained classifier are excluded into the garbage class. Over successive iterations, the inverted samples transition from noisy artifacts into visually coherent class prototypes, providing transparent insight into how the model organizes its learned manifolds. During inference, TIE rejects OOD inputs by either directly mapping them to the garbage class or producing low-confidence, uncertain misclassifications within the in-distribution classes that are easily separable, all without relying on external OOD datasets. A comprehensive threshold-based evaluation using multiple OOD metrics and performance measures such as \textit{AUROC}, \textit{AUPR}, and \textit{FPR@95\%TPR} demonstrates that TIE offers a unified and interpretable framework for robust anomaly detection and calibrated uncertainty estimation (UE) achieving near-perfect OOD detection with \textbf{\(\!\approx\!\) 0 FPR@95\%TPR} when trained on MNIST or FashionMNIST and tested against diverse unseen datasets.
Authors: Yenho Chen, Maxwell A. Xu, James M. Rehg, Christopher J. Rozell
Abstract: The effectiveness of self-supervised learning (SSL) for physiological time series depends on the ability of a pretraining objective to preserve information about the underlying physiological state while filtering out unrelated noise. However, existing strategies are limited due to reliance on heuristic principles or poorly constrained generative tasks. To address this limitation, we propose a pretraining framework that exploits the information structure of a dynamical systems generative model across multiple time-series. This framework reveals our key insight that class identity can be efficiently captured by extracting information about the generative variables related to the system parameters shared across similar time series samples, while noise unique to individual samples should be discarded. Building on this insight, we propose PULSE, a cross-reconstruction-based pretraining objective for physiological time series datasets that explicitly extracts system information while discarding non-transferrable sample-specific ones. We establish theory that provides sufficient conditions for the system information to be recovered, and empirically validate it using a synthetic dynamical systems experiment. Furthermore, we apply our method to diverse real-world datasets, demonstrating that PULSE learns representations that can broadly distinguish semantic classes, increase label efficiency, and improve transfer learning.
Authors: Alessio Borgi, Fabrizio Silvestri, Pietro Li\`o
Abstract: Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-aware inductive bias that handles heterophily and limits oversmoothing. However, common Neural Sheaf Diffusion implementations rely on SVD-based sheaf normalization and dense per-edge restriction maps, which scale with stalk dimension, require frequent Laplacian rebuilds, and yield brittle gradients. To address these limitations, we introduce Polynomial Neural Sheaf Diffusion (PolyNSD), a new sheaf diffusion approach whose propagation operator is a degree-K polynomial in a normalised sheaf Laplacian, evaluated via a stable three-term recurrence on a spectrally rescaled operator. This provides an explicit K-hop receptive field in a single layer (independently of the stalk dimension), with a trainable spectral response obtained as a convex mixture of K+1 orthogonal polynomial basis responses. PolyNSD enforces stability via convex mixtures, spectral rescaling, and residual/gated paths, reaching new state-of-the-art results on both homophilic and heterophilic benchmarks, inverting the Neural Sheaf Diffusion trend by obtaining these results with just diagonal restriction maps, decoupling performance from large stalk dimension, while reducing runtime and memory requirements.
Authors: Scotty Black, Christian Darken
Abstract: In the domain of combat simulations in support of wargaming, the development of intelligent agents has predominantly been characterized by rule-based, scripted methodologies with deep reinforcement learning (RL) approaches only recently being introduced. While scripted agents offer predictability and consistency in controlled environments, they fall short in dynamic, complex scenarios due to their inherent inflexibility. Conversely, RL agents excel in adaptability and learning, offering potential improvements in handling unforeseen situations, but suffer from significant challenges such as black-box decision-making processes and scalability issues in larger simulation environments. This paper introduces a novel hierarchical hybrid artificial intelligence (AI) approach that synergizes the reliability and predictability of scripted agents with the dynamic, adaptive learning capabilities of RL. By structuring the AI system hierarchically, the proposed approach aims to utilize scripted agents for routine, tactical-level decisions and RL agents for higher-level, strategic decision-making, thus addressing the limitations of each method while leveraging their individual strengths. This integration is shown to significantly improve overall performance, providing a robust, adaptable, and effective solution for developing and training intelligent agents in complex simulation environments.
Authors: Henry Onyeka, Emmanuel Samson, Liang Hong, Tariqul Islam, Imtiaz Ahmed, Kamrul Hasan
Abstract: The increasing complexity of IoT edge networks presents significant challenges for anomaly detection, particularly in identifying sophisticated Denial-of-Service (DoS) attacks and zero-day exploits under highly dynamic and imbalanced traffic conditions. This paper proposes SD-CGAN, a Conditional Generative Adversarial Network framework enhanced with Sinkhorn Divergence, tailored for robust anomaly detection in IoT edge environments. The framework incorporates CTGAN-based synthetic data augmentation to address class imbalance and leverages Sinkhorn Divergence as a geometry-aware loss function to improve training stability and reduce mode collapse. The model is evaluated on exploitative attack subsets from the CICDDoS2019 dataset and compared against baseline deep learning and GAN-based approaches. Results show that SD-CGAN achieves superior detection accuracy, precision, recall, and F1-score while maintaining computational efficiency suitable for deployment in edge-enabled IoT environments.
Authors: Y. Sungtaek Ju
Abstract: Kolmogorov-Arnold Networks (KANs) offer a promising alternative to Multi-Layer Perceptron (MLP) by placing learnable univariate functions on network edges, enhancing interpretability. However, standard KANs lack probabilistic outputs, limiting their utility in applications requiring uncertainty quantification. While recent Gaussian Process (GP) extensions to KANs address this, they utilize exact inference methods that scale cubically with data size N, restricting their application to smaller datasets. We introduce the Sparse Variational GP-KAN (SVGP-KAN), an architecture that integrates sparse variational inference with the KAN topology. By employing $M$ inducing points and analytic moment matching, our method reduces computational complexity from $O(N^3)$ to $O(NM^2)$ or linear in sample size, enabling the application of probabilistic KANs to larger scientific datasets. Furthermore, we demonstrate that integrating a permutation-based importance analysis enables the network to function as a framework for structural identification, identifying relevant inputs and classifying functional relationships.
Authors: Mohammad M Maheri, Xavier Cadet, Peter Chin, Hamed Haddadi
Abstract: Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model, offering a practical alternative to full retraining. However, it introduces privacy risks: an adversary with access to pre- and post-unlearning models can exploit their differences for membership inference or data reconstruction. We show these vulnerabilities arise from two factors: large gradient norms of forget-set samples and the close proximity of unlearned parameters to the original model. To demonstrate their severity, we propose unlearning-specific membership inference and reconstruction attacks, showing that several state-of-the-art methods (e.g., NGP, SCRUB) remain vulnerable. To mitigate this leakage, we introduce WARP, a plug-and-play teleportation defense that leverages neural network symmetries to reduce forget-set gradient energy and increase parameter dispersion while preserving predictions. This reparameterization obfuscates the signal of forgotten data, making it harder for attackers to distinguish forgotten samples from non-members or recover them via reconstruction. Across six unlearning algorithms, our approach achieves consistent privacy gains, reducing adversarial advantage (AUC) by up to 64% in black-box and 92% in white-box settings, while maintaining accuracy on retained data. These results highlight teleportation as a general tool for reducing attack success in approximate unlearning.
Authors: Yi Fang, Haoran Xu, Jiaxin Han, Sirui Ding, Yizhi Wang, Yue Wang, Xuan Wang
Abstract: Foundation models have revolutionized various fields such as natural language processing (NLP) and computer vision (CV). While efforts have been made to transfer the success of the foundation models in general AI domains to biology, existing works focus on directly adopting the existing foundation model architectures from general machine learning domains without a systematic design considering the unique physicochemical and structural properties of each biological data modality. This leads to suboptimal performance, as these repurposed architectures struggle to capture the long-range dependencies, sparse information, and complex underlying ``grammars'' inherent to biological data. To address this gap, we introduce BioArc, a novel framework designed to move beyond intuition-driven architecture design towards principled, automated architecture discovery for biological foundation models. Leveraging Neural Architecture Search (NAS), BioArc systematically explores a vast architecture design space, evaluating architectures across multiple biological modalities while rigorously analyzing the interplay between architecture, tokenization, and training strategies. This large-scale analysis identifies novel, high-performance architectures, allowing us to distill a set of empirical design principles to guide future model development. Furthermore, to make the best of this set of discovered principled architectures, we propose and compare several architecture prediction methods that effectively and efficiently predict optimal architectures for new biological tasks. Overall, our work provides a foundational resource and a principled methodology to guide the creation of the next generation of task-specific and foundation models for biology.
Authors: Nguyen Ly, Caroline Tatsuoka, Jai Nagaraj, Jacob Levy, Fernando Palafox, David Fridovich-Keil, Hannah Lu
Abstract: We develop a data-driven framework for learning and correcting non-autonomous vehicle dynamics. Physics-based vehicle models are often simplified for tractability and therefore exhibit inherent model-form uncertainty, motivating the need for data-driven correction. Moreover, non-autonomous dynamics are governed by time-dependent control inputs, which pose challenges in learning predictive models directly from temporal snapshot data. To address these, we reformulate the vehicle dynamics via a local parameterization of the time-dependent inputs, yielding a modified system composed of a sequence of local parametric dynamical systems. We approximate these parametric systems using two complementary approaches. First, we employ the DRIPS (dimension reduction and interpolation in parameter space) methodology to construct efficient linear surrogate models, equipped with lifted observable spaces and manifold-based operator interpolation. This enables data-efficient learning of vehicle models whose dynamics admit accurate linear representations in the lifted spaces. Second, for more strongly nonlinear systems, we employ FML (Flow Map Learning), a deep neural network approach that approximates the parametric evolution map without requiring special treatment of nonlinearities. We further extend FML with a transfer-learning-based model correction procedure, enabling the correction of misspecified prior models using only a sparse set of high-fidelity or experimental measurements, without assuming a prescribed form for the correction term. Through a suite of numerical experiments on unicycle, simplified bicycle, and slip-based bicycle models, we demonstrate that DRIPS offers robust and highly data-efficient learning of non-autonomous vehicle dynamics, while FML provides expressive nonlinear modeling and effective correction of model-form errors under severe data scarcity.
Authors: Yafei Lyu, Hao Zhou, Lu Zhang, Xu Yang, Zhiyong Liu
Abstract: Time series forecasting is central to data analysis and web technologies. The recent success of Large Language Models (LLMs) offers significant potential for this field, especially from the cross-modality aspect. Most methods adopt an LLM-as-Predictor paradigm, using LLM as the forecasting backbone and designing modality alignment mechanisms to enable LLM to understand time series data. However, the semantic information in the two modalities of time series and text differs significantly, making it challenging for LLM to fully understand time series data. To mitigate this challenge, our work follows an LLM-as-Enhancer paradigm to fully utilize the advantage of LLM in text understanding, where LLM is only used to encode text modality to complement time series modality. Based on this paradigm, we propose FiCoTS, an LLM-enhanced fine-to-coarse framework for multimodal time series forecasting. Specifically, the framework facilitates progressive cross-modality interaction by three levels in a fine-to-coarse scheme: First, in the token-level modality alignment module, a dynamic heterogeneous graph is constructed to filter noise and align time series patches with text tokens; Second, in the feature-level modality interaction module, a global cross-attention mechanism is introduced to enable each time series variable to connect with relevant textual contexts; Third, in the decision-level modality fusion module, we design a gated network to adaptively fuse the results of the two modalities for robust predictions. These three modules work synergistically to let the two modalities interact comprehensively across three semantic levels, enabling textual information to effectively support temporal prediction. Extensive experiments on seven real-world benchmarks demonstrate that our model achieves state-of-the-art performance. The codes will be released publicly.
Authors: Gonz\'alez Trigueros Jes\'us Eduardo, Alonso S\'anchez Alejandro, Mu\~noz Rivera Emilio, Pe\~nar\'an Prieto Mariana Jaqueline, Mendoza Gonz\'alez Camila Natalia
Abstract: This study analyzes the impact of heterogeneity ("Variety") in Big Data by comparing classification strategies across structured (Epsilon) and unstructured (Rest-Mex, IMDB) domains. A dual methodology was implemented: evolutionary and Bayesian hyperparameter optimization (Genetic Algorithms, Optuna) in Python for numerical data, and distributed processing in Apache Spark for massive textual corpora. The results reveal a "complexity paradox": in high-dimensional spaces, optimized linear models (SVM, Logistic Regression) outperformed deep architectures and Gradient Boosting. Conversely, in text-based domains, the constraints of distributed fine-tuning led to overfitting in complex models, whereas robust feature engineering -- specifically Transformer-based embeddings (ROBERTa) and Bayesian Target Encoding -- enabled simpler models to generalize effectively. This work provides a unified framework for algorithm selection based on data nature and infrastructure constraints.
Authors: Shenghong He
Abstract: Federated reinforcement learning (FRL) enables distributed learning of optimal policies while preserving local data privacy through gradient sharing.However, FRL faces the risk of data privacy leaks, where attackers exploit shared gradients to reconstruct local training data.Compared to traditional supervised federated learning, successful reconstruction in FRL requires the generated data not only to match the shared gradients but also to align with real transition dynamics of the environment (i.e., aligning with the real data transition distribution).To address this issue, we propose a novel attack method called Regularization Gradient Inversion Attack (RGIA), which enforces prior-knowledge-based regularization on states, rewards, and transition dynamics during the optimization process to ensure that the reconstructed data remain close to the true transition distribution.Theoretically, we prove that the prior-knowledge-based regularization term narrows the solution space from a broad set containing spurious solutions to a constrained subset that satisfies both gradient matching and true transition dynamics.Extensive experiments on control tasks and autonomous driving tasks demonstrate that RGIA can effectively constrain reconstructed data transition distributions and thus successfully reconstruct local private data.
Authors: Haobin Ke, Sen Zhang, Qingqing Ye, Xun Ran, Haibo Hu
Abstract: Signed graphs with positive and negative edges can model complex relationships in social networks. Leveraging on balance theory that deduces edge signs from multi-hop node pairs, signed graph learning can generate node embeddings that preserve both structural and sign information. However, training on sensitive signed graphs raises significant privacy concerns, as model parameters may leak private link information. Existing protection methods with differential privacy (DP) typically rely on edge or gradient perturbation for unsigned graph protection. Yet, they are not well-suited for signed graphs, mainly because edge perturbation tends to cascading errors in edge sign inference under balance theory, while gradient perturbation increases sensitivity due to node interdependence and gradient polarity change caused by sign flips, resulting in larger noise injection. In this paper, motivated by the robustness of adversarial learning to noisy interactions, we present ASGL, a privacy-preserving adversarial signed graph learning method that preserves high utility while achieving node-level DP. We first decompose signed graphs into positive and negative subgraphs based on edge signs, and then design a gradient-perturbed adversarial module to approximate the true signed connectivity distribution. In particular, the gradient perturbation helps mitigate cascading errors, while the subgraph separation facilitates sensitivity reduction. Further, we devise a constrained breadth-first search tree strategy that fuses with balance theory to identify the edge signs between generated node pairs. This strategy also enables gradient decoupling, thereby effectively lowering gradient sensitivity. Extensive experiments on real-world datasets show that ASGL achieves favorable privacy-utility trade-offs across multiple downstream tasks.
Authors: Jungyang Park, Suho Kang, Jaewoo Park, Jaehong Kim, Jaewoo Shin, Seonjoon Park, Youngjae Yu
Abstract: Knowledge Tracing (KT) aims to model student's knowledge state and predict future performance to enable personalized learning in Intelligent Tutoring Systems. However, traditional KT methods face fundamental limitations in explainability, as they rely solely on the response correctness, neglecting the rich information embedded in students' problem-solving processes. To address this gap, we propose Knowledge Tracing Leveraging Problem-Solving Process (KT-PSP), which incorporates students' problem-solving processes to capture the multidimensional aspects of mathematical proficiency. We also introduce KT-PSP-25, a new dataset specifically designed for the KT-PSP. Building on this, we present StatusKT, a KT framework that employs a teacher-student-teacher three-stage LLM pipeline to extract students' MP as intermediate signals. In this pipeline, the teacher LLM first extracts problem-specific proficiency indicators, then a student LLM generates responses based on the student's solution process, and a teacher LLM evaluates these responses to determine mastery of each indicator. The experimental results on KT-PSP-25 demonstrate that StatusKT improves the prediction performance of existing KT methods. Moreover, StatusKT provides interpretable explanations for its predictions by explicitly modeling students' mathematical proficiency.
Authors: Shivani Mruthyunjaya, Anandi Dutta, Kazi Sifatul Islam
Abstract: Power consumption has become a critical aspect of modern life due to the consistent reliance on technological advancements. Reducing power consumption or following power usage predictions can lead to lower monthly costs and improved electrical reliability. The proposal of a holistic framework to establish a foundation for IoT systems with a focus on contextual decision making, proactive adaptation, and scalable structure. A structured process for IoT systems with accuracy and interconnected development would support reducing power consumption and support grid stability. This study presents the feasibility of this proposal through the application of each aspect of the framework. This system would have long term forecasting, short term forecasting, anomaly detection, and consideration of qualitative data with any energy management decisions taken. Performance was evaluated on Power Consumption Time Series data to display the direct application of the framework.
Authors: Haizheng Li, Lei Guo
Abstract: Real-world intelligence systems usually operate by combining offline learning and online adaptation with highly correlated and non-stationary system data or signals, which, however, has rarely been investigated theoretically in the literature. This paper initiates a theoretical investigation on the prediction performance of a two-stage learning framework combining offline and online algorithms for a class of nonlinear stochastic dynamical systems. For the offline-learning phase, we establish an upper bound on the generalization error for approximate nonlinear-least-squares estimation under general datasets with strong correlation and distribution shift, leveraging the Kullback-Leibler divergence to quantify the distributional discrepancies. For the online-adaptation phase, we address, on the basis of the offline-trained model, the possible uncertain parameter drift in real-world target systems by proposing a meta-LMS prediction algorithm. This two-stage framework, integrating offline learning with online adaptation, demonstrates superior prediction performances compared with either purely offline or online methods. Both theoretical guarantees and empirical studies are provided.
Authors: Na Li, Yuchen Jiao, Hangguan Shan, Shefeng Yan
Abstract: The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theoretical studies in this area suffer from at least two of the following obstacles: memory inefficiency, the heavy dependence of sample complexity on the long horizon and the large state space, the high computational complexity, non-Markov policy, non-Nash policy, and high burn-in cost. In this work, we take a step towards settling this problem by designing a model-free self-play algorithm \emph{Memory-Efficient Nash Q-Learning (ME-Nash-QL)} for two-player zero-sum Markov games, which is a specific setting of MARL. ME-Nash-QL is proven to enjoy the following merits. First, it can output an $\varepsilon$-approximate Nash policy with space complexity $O(SABH)$ and sample complexity $\widetilde{O}(H^4SAB/\varepsilon^2)$, where $S$ is the number of states, $\{A, B\}$ is the number of actions for two players, and $H$ is the horizon length. It outperforms existing algorithms in terms of space complexity for tabular cases, and in terms of sample complexity for long horizons, i.e., when $\min\{A, B\}\ll H^2$. Second, ME-Nash-QL achieves the lowest computational complexity $O(T\mathrm{poly}(AB))$ while preserving Markov policies, where $T$ is the number of samples. Third, ME-Nash-QL also achieves the best burn-in cost $O(SAB\,\mathrm{poly}(H))$, whereas previous algorithms have a burn-in cost of at least $O(S^3 AB\,\mathrm{poly}(H))$ to attain the same level of sample complexity with ours.
Authors: Na Li, Zewu Zheng, Wei Ni, Hangguan Shan, Wenjie Zhang, Xinyu Li
Abstract: Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the sim-to-real gap. We focus on robust two-player zero-sum Markov games (TZMGs) in offline settings, specifically on tabular robust TZMGs (RTZMGs). We propose a model-based algorithm (\textit{RTZ-VI-LCB}) for offline RTZMGs, which is optimistic robust value iteration combined with a data-driven Bernstein-style penalty term for robust value estimation. By accounting for distribution shifts in the historical dataset, the proposed algorithm establishes near-optimal sample complexity guarantees under partial coverage and environmental uncertainty. An information-theoretic lower bound is developed to confirm the tightness of our algorithm's sample complexity, which is optimal regarding both state and action spaces. To the best of our knowledge, RTZ-VI-LCB is the first to attain this optimality, sets a new benchmark for offline RTZMGs, and is validated experimentally.
Authors: Na Li, Hangguan Shan, Wei Ni, Wenjie Zhang, Xinyu Li, Yamin Wang
Abstract: A critical challenge for reinforcement learning (RL) is making decisions based on incomplete and noisy observations, especially in perturbed and partially observable Markov decision processes (P$^2$OMDPs). Existing methods fail to mitigate perturbations while addressing partial observability. We propose \textit{Causal State Representation under Asynchronous Diffusion Model (CaDiff)}, a framework that enhances any RL algorithm by uncovering the underlying causal structure of P$^2$OMDPs. This is achieved by incorporating a novel asynchronous diffusion model (ADM) and a new bisimulation metric. ADM enables forward and reverse processes with different numbers of steps, thus interpreting the perturbation of P$^2$OMDP as part of the noise suppressed through diffusion. The bisimulation metric quantifies the similarity between partially observable environments and their causal counterparts. Moreover, we establish the theoretical guarantee of CaDiff by deriving an upper bound for the value function approximation errors between perturbed observations and denoised causal states, reflecting a principled trade-off between approximation errors of reward and transition-model. Experiments on Roboschool tasks show that CaDiff enhances returns by at least 14.18\% compared to baselines. CaDiff is the first framework that approximates causal states using diffusion models with both theoretical rigor and practicality.
Authors: Wenshuo Wang, Yaomin Shen, Yingjie Tan, Yihao Chen
Abstract: Spatiotemporal forecasting often relies on computationally intensive models to capture complex dynamics. Knowledge distillation (KD) has emerged as a key technique for creating lightweight student models, with recent advances like frequency-aware KD successfully preserving spectral properties (i.e., high-frequency details and low-frequency trends). However, these methods are fundamentally constrained by operating on pixel-level signals, leaving them blind to the rich semantic and causal context behind the visual patterns. To overcome this limitation, we introduce S^2-KD, a novel framework that unifies Semantic priors with Spectral representations for distillation. Our approach begins by training a privileged, multimodal teacher model. This teacher leverages textual narratives from a Large Multimodal Model (LMM) to reason about the underlying causes of events, while its architecture simultaneously decouples spectral components in its latent space. The core of our framework is a new distillation objective that transfers this unified semantic-spectral knowledge into a lightweight, vision-only student. Consequently, the student learns to make predictions that are not only spectrally accurate but also semantically coherent, without requiring any textual input or architectural overhead at inference. Extensive experiments on benchmarks like WeatherBench and TaxiBJ+ show that S^2-KD significantly boosts the performance of simple student models, enabling them to outperform state-of-the-art methods, particularly in long-horizon and complex non-stationary scenarios.
Authors: Jianhai Su, Jinzhu Luo, Qi Zhang
Abstract: We take the novel perspective of incorporating offline RL algorithms as subroutines of tabula rasa online RL. This is feasible because an online learning agent can repurpose its historical interactions as offline dataset. We formalize this idea into a framework that accommodates several variants of offline RL incorporation such as final policy recommendation and online fine-tuning. We further introduce convenient techniques to improve its effectiveness in enhancing online learning efficiency. Our extensive and systematic empirical analyses show that 1) the effectiveness of the proposed framework depends strongly on the nature of the task, 2) our proposed techniques greatly enhance its effectiveness, and 3) existing online fine-tuning methods are overall ineffective, calling for more research therein.
Authors: Shitong Luo, Connor W. Coley
Abstract: The constrained nature of synthesizable chemical space poses a significant challenge for sampling molecules that are both synthetically accessible and possess desired properties. In this work, we present PrexSyn, an efficient and programmable model for molecular discovery within synthesizable chemical space. PrexSyn is based on a decoder-only transformer trained on a billion-scale datastream of synthesizable pathways paired with molecular properties, enabled by a real-time, high-throughput C++-based data generation engine. The large-scale training data allows PrexSyn to reconstruct the synthesizable chemical space nearly perfectly at a high inference speed and learn the association between properties and synthesizable molecules. Based on its learned property-pathway mappings, PrexSyn can generate synthesizable molecules that satisfy not only single-property conditions but also composite property queries joined by logical operators, thereby allowing users to ``program'' generation objectives. Moreover, by exploiting this property-based querying capability, PrexSyn can efficiently optimize molecules against black-box oracle functions via iterative query refinement, achieving higher sampling efficiency than even synthesis-agnostic baselines, making PrexSyn a powerful general-purpose molecular optimization tool. Overall, PrexSyn pushes the frontier of synthesizable molecular design by setting a new state of the art in synthesizable chemical space coverage, molecular sampling efficiency, and inference speed.
Authors: Deep Patel, Emmanouil-Vasileios Vlatakis-Gkaragkounis
Abstract: Many emerging applications - such as adversarial training, AI alignment, and robust optimization - can be framed as zero-sum games between neural nets, with von Neumann-Nash equilibria (NE) capturing the desirable system behavior. While such games often involve non-convex non-concave objectives, empirical evidence shows that simple gradient methods frequently converge, suggesting a hidden geometric structure. In this paper, we provide a theoretical framework that explains this phenomenon through the lens of hidden convexity and overparameterization. We identify sufficient conditions - spanning initialization, training dynamics, and network width - that guarantee global convergence to a NE in a broad class of non-convex min-max games. To our knowledge, this is the first such result for games that involve two-layer neural networks. Technically, our approach is twofold: (a) we derive a novel path-length bound for the alternating gradient descent-ascent scheme in min-max games; and (b) we show that the reduction from a hidden convex-concave geometry to two-sided Polyak-{\L}ojasiewicz (P{\L}) min-max condition hold with high probability under overparameterization, using tools from random matrix theory.
Authors: Zhikang Chen, Sen Cui, Deheng Ye, Min Zhang, Gang Niu, Yu Zhang, Masashi Sugiyama, Tingting Zhu
Abstract: Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstrated the effectiveness of combining parameters through strategies such as parameter decomposition, coefficient optimization, and subspace learning, significantly reducing the need for expensive joint training and achieving strong empirical performance across diverse tasks. However, these approaches predominantly treat merging as a problem of parameter space decomposition or fusion coefficient optimization, while overlooking the critical role of directional information in both parameter and feature spaces. In practice, na\"ive merging introduces inconsistencies in dominant parameter directions and disrupts structural coherence across models, which can degrade performance. Moreover, coefficient-based optimization methods implicitly assume compatible feature-space directions across models. However, Neural Collapse indicates that class features follow structured directional patterns, which may differ across independently trained models, making coefficient optimization alone insufficient. In this work, we emphasize the importance of \emph{directional alignment} and introduce a unified geometric framework, \emph{Merging with Directional Alignment} (\method{}), which aligns directional structures consistently in both the parameter and feature spaces. Our analysis shows that directional alignment improves structural coherence, and extensive experiments across benchmarks, model scales, and task configurations further validate the effectiveness of our approach.
Authors: Andrea Procopio, Marco Esposito, Sara Raggiunto, Andrey Gizdov, Alberto Belli, Paola Pierleoni
Abstract: We study on-device time-series analysis for gait detection in Parkinson's disease (PD) from short windows of triaxial acceleration, targeting resource-constrained wearables and edge nodes. We compare magnitude thresholding to three 1D CNNs for time-series analysis: a literature baseline (separable convolutions) and two ultra-light models - one purely separable and one with residual connections. Using the BioStampRC21 dataset, 2 s windows at 30 Hz, and subject-independent leave-one-subject-out (LOSO) validation on 16 PwPD with chest-worn IMUs, our residual separable model (Model 2, 533 params) attains PR-AUC = 94.5%, F1 = 91.2%, MCC = 89.4%, matching or surpassing the baseline (5,552 params; PR-AUC = 93.7%, F1 = 90.5%, MCC = 88.5%) with approximately 10x fewer parameters. The smallest model (Model 1, 305 params) reaches PR-AUC = 94.0%, F1 = 91.0%, MCC = 89.1%. Thresholding obtains high recall (89.0%) but low precision (76.5%), yielding many false positives and high inter-subject variance. Sensor-position analysis (train-on-all) shows chest and thighs are most reliable; forearms degrade precision/recall due to non-gait arm motion; naive fusion of all sites does not outperform the best single site. Both compact CNNs execute within tight memory/latency budgets on STM32-class MCUs (sub-10 ms on low-power boards), enabling on-sensor gating of transmission/storage. Overall, ultra-light separable CNNs provide a superior accuracy-efficiency-generalization trade-off to fixed thresholds for wearable PD gait detection and underscore the value of tailored time-series models for edge deployment.
Authors: Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng, Xiaobing Yu, Yu Zhong, Shangqi Deng, Ufaq Khan, Jianghao Wu, Xiaofeng Liu, Imran Razzak, Xiaojun Chang, Yutong Xie
Abstract: Recent work on autonomous scientific discovery has leveraged LLM-based agents to integrate problem specification, experiment planning, and execution into end-to-end systems. However, these frameworks are often confined to narrow application domains, offer limited real-time interaction with researchers, and lack principled mechanisms for determining when to halt exploration, resulting in inefficiencies, reproducibility challenges, and under-utilized human expertise. To address these gaps, we propose \textit{SelfAI}, a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations, a Cognitive Agent powered by LLMs with optimal stopping criteria to iteratively refine hyperparameter searches, and an Experiment Manager responsible for orchestrating parallel, fault-tolerant training workflows across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback. We further introduce two novel evaluation metrics, Score and $\text{AUP}_D$, to quantify discovery efficiency and search diversity. Across regression, NLP, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials compared to classical Bayesian optimization and LLM-based baselines, while enabling seamless interaction with human researchers.
Authors: Mulin Tian, Ajitesh Srivastava
Abstract: Epidemic outcomes have a complex interplay with human behavior and beliefs. Most of the forecasting literature has focused on the task of predicting epidemic signals using simple mechanistic models or black-box models, such as deep transformers, that ingest all available signals without offering interpretability. However, to better understand the mechanisms and predict the impact of interventions, we need the ability to forecast signals associated with beliefs and behaviors in an interpretable manner. In this work, we propose a graph-based forecasting framework that first constructs a graph of interrelated signals based on trend similarity, and then applies graph neural networks (GNNs) for prediction. This approach enables interpretable analysis by revealing which signals are more predictable and which relationships contribute most to forecasting accuracy. We believe our method provides early steps towards a framework for interpretable modeling in domains with multiple potentially interdependent signals, with implications for building future simulation models that integrate behavior, beliefs, and observations.
Authors: Benjamin D. Ballyk, Ankit Gupta, Sujay Konda, Kavitha Subramanian, Chris Landon, Ahmed Ammar Naseer, Georg Maierhofer, Sumanth Swaminathan, Vasudevan Venkateshwaran
Abstract: Data privacy is a critical challenge in modern medical workflows as the adoption of electronic patient records has grown rapidly. Stringent data protection regulations limit access to clinical records for training and integrating machine learning models that have shown promise in improving diagnostic accuracy and personalized care outcomes. Synthetic data offers a promising alternative; however, current generative models either struggle with time-series data or lack formal privacy guaranties. In this paper, we enhance a state-of-the-art time-series generative model to better handle longitudinal clinical data while incorporating quantifiable privacy safeguards. Using real data from chronic kidney disease and ICU patients, we evaluate our method through statistical tests, a Train-on-Synthetic-Test-on-Real (TSTR) setup, and expert clinical review. Our non-private model (Augmented TimeGAN) outperforms transformer- and flow-based models on statistical metrics in several datasets, while our private model (DP-TimeGAN) maintains a mean authenticity of 0.778 on the CKD dataset, outperforming existing state-of-the-art models on the privacy-utility frontier. Both models achieve performance comparable to real data in clinician evaluations, providing robust input data necessary for developing models for complex chronic conditions without compromising data privacy.
Authors: Guanyu Hu, Tangzheng Lian, Na Yan, Dimitrios Kollias, Xinyu Yang, Oya Celiktutan, Siyang Song, Zeyu Fu
Abstract: Fairness in machine learning has been extensively studied in single-task settings, while fair multi-task learning (MTL), especially with heterogeneous tasks (classification, detection, regression) and partially missing labels, remains largely unexplored. Existing fairness methods are predominantly classification-oriented and fail to extend to continuous outputs, making a unified fairness objective difficult to formulate. Further, existing MTL optimization is structurally misaligned with fairness: constraining only the shared representation, allowing task heads to absorb bias and leading to uncontrolled task-specific disparities. Finally, most work treats fairness as a zero-sum trade-off with utility, enforcing symmetric constraints that achieve parity by degrading well-served groups. We introduce FairMT, a unified fairness-aware MTL framework that accommodates all three task types under incomplete supervision. At its core is an Asymmetric Heterogeneous Fairness Constraint Aggregation mechanism, which consolidates task-dependent asymmetric violations into a unified fairness constraint. Utility and fairness are jointly optimized via a primal--dual formulation, while a head-aware multi-objective optimization proxy provides a tractable descent geometry that explicitly accounts for head-induced anisotropy. Across three homogeneous and heterogeneous MTL benchmarks encompassing diverse modalities and supervision regimes, FairMT consistently achieves substantial fairness gains while maintaining superior task utility. Code will be released upon paper acceptance.
Authors: Yuepeng Sheng, Yuwei Huang, Shuman Liu, Haibo Zhang, Anxiang Zeng
Abstract: Large language model (LLM) reinforcement learning has increasingly relied on group-based policy optimization frameworks, such as GRPO and GSPO, to achieve stable fine-tuning at scale. However, a fundamental trade-off persists between optimization granularity and training stability. While GSPO improves robustness via sequence-level optimization, its monolithic treatment of sequences introduces severe inefficiencies: its conservative clipping mechanism indiscriminately discards valid training samples-a phenomenon we term gradient underutilization-and its uniform credit assignment fails to capture the heterogeneous contributions of critical reasoning steps. In this work, we propose Entropy Importance Sampling Policy Optimization (ESPO), a novel framework that reconciles fine-grained control with training stability. ESPO decomposes sequences into groups based on predictive entropy, enabling (1) Entropy-driven Importance Sampling to capture intra-sequence heterogeneity, and (2) Entropy-adaptive Clipping to dynamically allocate trust regions based on model uncertainty. Extensive experiments on mathematical reasoning benchmarks demonstrate that ESPO not only accelerates convergence but also achieves state-of-the-art performance, notably improving accuracy on the challenging HMMT benchmark from 4.4% to 13.13%.
Authors: Sabrina Islam, Md. Atiqur Rahman, Md. Bakhtiar Hasan, Md. Hasanul Kabir
Abstract: In early stage drug discovery, bioactivity prediction of molecules against target proteins plays a crucial role. Trdaitional QSAR models that utilizes molecular descriptor based data often struggles to predict bioactivity of molecules effectively due to its limitation in capturing structural and contextual information embedded within each compound. To address this challenge, we propose Rep3Net, a unified deep learning architecture that not only incorporates descriptor data but also includes spatial and relational information through graph-based represenation of compounds and contextual information through ChemBERTa generated embeddings from SMILES strings. Our model employing multimodal concatenated features produce reliable bioactivity prediction on Poly [ADP-ribose] polymerase 1 (PARP-1) dataset. PARP-1 is a crucial agent in DNA damage repair and has become a significant theraputic target in malignancies that depend on it for survival and growth. A comprehensive analysis and comparison with conventional standalone models including GCN, GAT, XGBoost, etc. demonstrates that our architecture achieves the highest predictive performance. In computational screening of compounds in drug discovery, our architecture provides a scalable framework for bioactivity prediction.
Authors: Guangjie Zeng, Hao Peng, Angsheng Li, Li Sun, Chunyang Liu, Shengze Li, Yicheng Pan, Philip S. Yu
Abstract: Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two primary challenges: 1) Most methods specify dendrograms without a global objective. 2) Graph-based methods often neglect the significance of graph structure, optimizing objectives on complete or static predefined graphs. In this work, we propose Hyperbolic Continuous Structural Entropy neural networks, namely HypCSE, for structure-enhanced continuous hierarchical clustering. Our key idea is to map data points in the hyperbolic space and minimize the relaxed continuous structural entropy (SE) on structure-enhanced graphs. Specifically, we encode graph vertices in hyperbolic space using hyperbolic graph neural networks and minimize approximate SE defined on graph embeddings. To make the SE objective differentiable for optimization, we reformulate it into a function using the lowest common ancestor (LCA) on trees and then relax it into continuous SE (CSE) by the analogy of hyperbolic graph embeddings and partitioning trees. To ensure a graph structure that effectively captures the hierarchy of data points for CSE calculation, we employ a graph structure learning (GSL) strategy that updates the graph structure during training. Extensive experiments on seven datasets demonstrate the superior performance of HypCSE.
Authors: Isara Liyanage, Uthayasanker Thayasivam
Abstract: The widespread adoption of complex machine learning models in high-stakes domains has brought the "black-box" problem to the forefront of responsible AI research. This paper aims at addressing this issue by improving the Explainable Boosting Machine (EBM), a state-of-the-art glassbox model that delivers both high accuracy and complete transparency. The paper outlines three distinct enhancement methodologies: targeted hyperparameter optimization with Bayesian methods, the implementation of a custom multi-objective function for fairness for hyperparameter optimization, and a novel self-supervised pre-training pipeline for cold-start scenarios. All three methodologies are evaluated across standard benchmark datasets, including the Adult Income, Credit Card Fraud Detection, and UCI Heart Disease datasets. The analysis indicates that while the tuning process yielded marginal improvements in the primary ROC AUC metric, it led to a subtle but important shift in the model's decision-making behavior, demonstrating the value of a multi-faceted evaluation beyond a single performance score. This work is positioned as a critical step toward developing machine learning systems that are not only accurate but also robust, equitable, and transparent, meeting the growing demands of regulatory and ethical compliance.
Authors: Aaryan Gupta, Rishi Saket, Aravindan Raghuveer
Abstract: Given a training dataset, the goal of dataset distillation is to derive a synthetic dataset such that models trained on the latter perform as well as those trained on the training dataset. In this work, we develop and analyze an efficient dataset distillation algorithm for supervised learning, specifically regression in $\mathbb{R}^d$, based on matching the losses on the training and synthetic datasets with respect to a fixed set of randomly sampled regressors without any model training. Our first key contribution is a novel performance guarantee proving that our algorithm needs only $\tilde{O}(d^2)$ sampled regressors to derive a synthetic dataset on which the MSE loss of any bounded linear model is nearly the same as its MSE loss on the given training data. In particular, the model optimized on the synthetic data has close to minimum loss on the training data, thus performing nearly as well as the model optimized on the latter. Complementing this, we also prove a matching lower bound of $\Omega(d^2)$ for the number of sampled regressors showing the tightness of our analysis. Our second contribution is to extend our algorithm to offline RL dataset distillation by matching the Bellman loss, unlike previous works which used a behavioral cloning objective. This is the first such method which leverages both, the rewards and the next state information, available in offline RL datasets, without any policy model optimization. Our algorithm generates a synthetic dataset whose Bellman loss with respect to any linear action-value predictor is close to the latter's Bellman loss on the offline RL training dataset. Therefore, a policy associated with an action-value predictor optimized on the synthetic dataset performs nearly as well as that derived from the one optimized on the training data. We conduct experiments to validate our theoretical guarantees and observe performance gains.
Authors: Akrati Saxena, Harshith Kumar Yadav, Bart Rutten, Shashi Shekhar Jha
Abstract: The Influence Maximization (IM) problem aims to select a set of seed nodes within a given budget to maximize the spread of influence in a social network. However, real-world social networks have several structural inequalities, such as dominant majority groups and underrepresented minority groups. If these inequalities are not considered while designing IM algorithms, the outcomes might be biased, disproportionately benefiting majority groups while marginalizing minorities. In this work, we address this gap by designing a fairness-aware IM method using Reinforcement Learning (RL) that ensures equitable influence outreach across all communities, regardless of protected attributes. Fairness is incorporated using a maximin fairness objective, which prioritizes improving the outreach of the least-influenced group, pushing the solution toward an equitable influence distribution. We propose a novel fairness-aware deep RL method, called DQ4FairIM, that maximizes the expected number of influenced nodes by learning an RL policy. The learnt policy ensures that minority groups formulate the IM problem as a Markov Decision Process (MDP) and use deep Q-learning, combined with the Structure2Vec network embedding, earning together with Structure2Vec network embedding to solve the MDP. We perform extensive experiments on synthetic benchmarks and real-world networks to compare our method with fairness-agnostic and fairness-aware baselines. The results show that our method achieves a higher level of fairness while maintaining a better fairness-performance trade-off than baselines. Additionally, our approach learns effective seeding policies that generalize across problem instances without retraining, such as varying the network size or the number of seed nodes.
Authors: Joud El-Shawa, Elham Bagheri, Sedef Akinli Kocak, Yalda Mohsenzadeh
Abstract: Heatwaves are intensifying worldwide and are among the deadliest weather disasters. The burden falls disproportionately on marginalized populations and the Global South, where under-resourced health systems, exposure to urban heat islands, and the lack of adaptive infrastructure amplify risks. Yet current numerical weather prediction models often fail to capture micro-scale extremes, leaving the most vulnerable excluded from timely early warnings. We present a Graph Neural Network framework for localized, high-resolution temperature forecasting. By leveraging spatial learning and efficient computation, our approach generates forecasts at multiple horizons, up to 48 hours. For Southwestern Ontario, Canada, the model captures temperature patterns with a mean MAE of 1.93$^{\circ}$C across 1-48h forecasts and MAE@48h of 2.93$^{\circ}$C, evaluated using 24h input windows on the largest region. While demonstrated here in a data-rich context, this work lays the foundation for transfer learning approaches that could enable localized, equitable forecasts in data-limited regions of the Global South.
Authors: Bohan Zhang, Michael Chen, A. Pavan, N. V. Vinodchandran, Lin F. Yang, Ruosong Wang
Abstract: Replicability is a fundamental challenge in reinforcement learning (RL), as RL algorithms are empirically observed to be unstable and sensitive to variations in training conditions. To formally address this issue, we study \emph{list replicability} in the Probably Approximately Correct (PAC) RL framework, where an algorithm must return a near-optimal policy that lies in a \emph{small list} of policies across different runs, with high probability. The size of this list defines the \emph{list complexity}. We introduce both weak and strong forms of list replicability: the weak form ensures that the final learned policy belongs to a small list, while the strong form further requires that the entire sequence of executed policies remains constrained. These objectives are challenging, as existing RL algorithms exhibit exponential list complexity due to their instability. Our main theoretical contribution is a provably efficient tabular RL algorithm that guarantees list replicability by ensuring the list complexity remains polynomial in the number of states, actions, and the horizon length. We further extend our techniques to achieve strong list replicability, bounding the number of possible policy execution traces polynomially with high probability. Our theoretical result is made possible by key innovations including (i) a novel planning strategy that selects actions based on lexicographic order among near-optimal choices within a randomly chosen tolerance threshold, and (ii) a mechanism for testing state reachability in stochastic environments while preserving replicability. Finally, we demonstrate that our theoretical investigation sheds light on resolving the \emph{instability} issue of RL algorithms used in practice. In particular, we show that empirically, our new planning strategy can be incorporated into practical RL frameworks to enhance their stability.
Authors: Naman Choudhary, Vedant Singh, Ameet Talwalkar, Nicholas Matthew Boffi, Mikhail Khodak, Tanya Marwah
Abstract: A key aspect of learned partial differential equation (PDE) solvers is that the main cost often comes from generating training data with classical solvers rather than learning the model itself. Another is that there are clear axes of difficulty--e.g., more complex geometries and higher Reynolds numbers--along which problems become (1) harder for classical solvers and thus (2) more likely to benefit from neural speedups. Towards addressing this chicken-and-egg challenge, we study difficulty transfer on 2D incompressible Navier-Stokes, systematically varying task complexity along geometry (number and placement of obstacles), physics (Reynolds number), and their combination. Similar to how it is possible to spend compute to pre-train foundation models and improve their performance on downstream tasks, we find that by classically solving (analogously pre-generating) many low and medium difficulty examples and including them in the training set, it is possible to learn high-difficulty physics from far fewer samples. Furthermore, we show that by combining low and high difficulty data, we can spend 8.9x less compute on pre-generating a dataset to achieve the same error as using only high difficulty examples. Our results highlight that how we allocate classical-solver compute across difficulty levels is as important as how much we allocate overall, and suggest substantial gains from principled curation of pre-generated PDE data for neural solvers. Our code is available at https://github.com/Naman-Choudhary-AI-ML/pregenerating-pde
URLs: https://github.com/Naman-Choudhary-AI-ML/pregenerating-pde
Authors: Giovanni Conforti, Alain Durmus, Le-Tuyet-Nhi Pham
Abstract: We investigate the theoretical underpinnings of Discrete Diffusion Models (DDMs) on discrete state spaces. Unlike in the continuous setting-where diffusion models are well understood both theoretically and empirically-the discrete case poses significant challenges due to its combinatorial structure and the lack of rigorous analysis. In this work, we establish convergence guarantees for DDMs on both the finite space $\mathbb{Z}^d_m=\{0,...,m-1\}^d$ and the countably infinite space $\mathbb{N}^d$ under mild assumptions, focusing on forward masked and random walk dynamics. Similar to the continuous case, the backward process can be characterized by a discrete score function, whose monotonicity plays a central role in deriving the error bounds of the generated data. Notably, the complexity of our model scales linearly up to logarithmic factors, rather than exponentially, with the dimension, making it efficiently scalable to high-dimensional data. To the best of our knowledge, this study provides the first non-asymptotic convergence guarantees that do not rely on the boundedness of the estimated score-covering not only uniform noising processes on $\mathbb{Z}^d_m$ and on $\mathbb{N}^d$, but also masking-based noising dynamics.
Authors: Michael R. Doane
Abstract: This work presents the development and evaluation of an NLP-enabled probabilistic classifier designed to estimate the probability of technical and regulatory success (pTRS) for clinical trials in the field of neuroscience. While pharmaceutical R&D is plagued by high attrition rates and enormous costs, particularly within neuroscience, where success rates are below 10%, timely identification of promising programs can streamline resource allocation and reduce financial risk. Leveraging data from the ClinicalTrials.gov database and success labels from the recently developed Clinical Trial Outcome dataset, the classifier extracts text-based clinical trial features using statistical NLP techniques. These features were integrated into several non-LLM frameworks (logistic regression, gradient boosting, and random forest) to generate calibrated probability scores. Model performance was assessed on a retrospective dataset of 101,145 completed clinical trials spanning 1976-2024, achieving an overall ROC-AUC of 0.64. An LLM-based predictive model was then built using BioBERT, a domain-specific language representation encoder. The BioBERT-based model achieved an overall ROC-AUC of 0.74 and a Brier Score of 0.185, indicating its predictions had, on average, 40% less squared error than would be observed using industry benchmarks. The BioBERT-based model also made trial outcome predictions that were superior to benchmark values 70% of the time overall. By integrating NLP-driven insights into drug development decision-making, this work aims to enhance strategic planning and optimize investment allocation in neuroscience programs.
Authors: Yining Yuan, J. Ben Tamo, Wenqi Shi, Yishan Zhong, Micky C. Nnamdi, B. Randall Brenn, Steven W. Hwang, May D. Wang
Abstract: Fairness in clinical prediction models remains a persistent challenge, particularly in high-stakes applications such as spinal fusion surgery for scoliosis, where patient outcomes exhibit substantial heterogeneity. Many existing fairness approaches rely on coarse demographic adjustments or post-hoc corrections, which fail to capture the latent structure of clinical populations and may unintentionally reinforce bias. We propose FAIR-MTL, a fairness-aware multitask learning framework designed to provide equitable and fine-grained prediction of postoperative complication severity. Instead of relying on explicit sensitive attributes during model training, FAIR-MTL employs a data-driven subgroup inference mechanism. We extract a compact demographic embedding, and apply k-means clustering to uncover latent patient subgroups that may be differentially affected by traditional models. These inferred subgroup labels determine task routing within a shared multitask architecture. During training, subgroup imbalance is mitigated through inverse-frequency weighting, and regularization prevents overfitting to smaller groups. Applied to postoperative complication prediction with four severity levels, FAIR-MTL achieves an AUC of 0.86 and an accuracy of 75%, outperforming single-task baselines while substantially reducing bias. For gender, the demographic parity difference decreases to 0.055 and equalized odds to 0.094; for age, these values reduce to 0.056 and 0.148, respectively. Model interpretability is ensured through SHAP and Gini importance analyses, which consistently highlight clinically meaningful predictors such as hemoglobin, hematocrit, and patient weight. Our findings show that incorporating unsupervised subgroup discovery into a multitask framework enables more equitable, interpretable, and clinically actionable predictions for surgical risk stratification.
Authors: Aur\'elien Delage, Romaric Gaudel
Abstract: We study the combinatorial semi-bandit problem under matroid constraints. The regret achieved by recent approaches is optimal, in the sense that it matches the lower bound. Yet, time complexity remains an issue for large matroids or for matroids with costly membership oracles (e.g. online recommendation that ensures diversity). This paper sheds a new light on the matroid semi-bandit problem by exploiting its underlying unimodal structure. We demonstrate that, with negligible loss in regret, the number of iterations involving the membership oracle can be limited to \mathcal{O}(\log \log T)$. This results in an overall improved time complexity of the learning process. Experiments conducted on various matroid benchmarks show (i) no loss in regret compared to state-of-the-art approaches; and (ii) reduced time complexity and number of calls to the membership oracle.
Authors: Siddhant Karki
Abstract: Graph link prediction has long been a central problem in graph representation learning in both network analysis and generative modeling. Recent progress in deep learning has introduced increasingly sophisticated architectures for capturing relational dependencies within graph-structured data. In this work, we propose the Generalized Graph Transformer Variational Autoencoder (GGT-VAE). Our model integrates Generalized Graph Transformer Architecture with Variational Autoencoder framework for link prediction. Unlike prior GraphVAE, GCN, or GNN approaches, GGT-VAE leverages transformer style global self-attention mechanism along with laplacian positional encoding to model structural patterns across nodes into a latent space without relying on message passing. Experimental results on several benchmark datasets demonstrate that GGT-VAE consistently achieves above-baseline performance in terms of ROC-AUC and Average Precision. To the best of our knowledge, this is among the first studies to explore graph structure generation using a generalized graph transformer backbone in a variational framework.
Authors: Goutham Nalagatla, Shreyas Grandhe
Abstract: Continual learning remains a fundamental challenge in artificial intelligence, with catastrophic forgetting posing a significant barrier to deploying neural networks in dynamic environments. Inspired by biological memory consolidation mechanisms, we propose a novel framework for generative replay that leverages predictive coding principles to mitigate forgetting. We present a comprehensive comparison between predictive coding-based and backpropagation-based gen- erative replay strategies, evaluating their effectiveness on task retention and transfer efficiency across multiple benchmark datasets. Our experimental results demonstrate that predictive coding-based replay achieves superior retention performance (average 15.3% improvement) while maintaining competitive transfer efficiency, suggesting that biologically-inspired mechanisms can offer principled solutions to continual learning challenges. The proposed framework provides insights into the relationship between biological memory processes and artificial learning systems, opening new avenues for neuroscience-inspired AI research.
Authors: Zhiming Lian
Abstract: Financial text classification has increasingly become an important aspect in quantitative trading systems and related tasks, such as financial sentiment analysis and the classification of financial news. In this paper, we assess the performance of the large language model Qwen3-8B on both tasks. Qwen3-8B is a state-of-the-art model that exhibits strong instruction-following and multilingual capabilities, and is distinct from standard models, primarily because it is specifically optimized for efficient fine tuning and high performance on reasoning-based benchmarks, making it suitable for financial applications. To adapt this model, we apply Noisy Embedding Instruction Finetuning and based on our previous work, this method increases robustness by injecting controlled noise into the embedding layers during supervised adaptation. We improve efficiency further with Rank-stabilized Low-Rank Adaptation low-rank optimization approach, and FlashAttention, which allow for faster training with lower GPU memory. For both tasks, we benchmark Qwen3-8B against standard classical transformer models, such as T5, BERT, and RoBERTa, and large models at scale, such as LLaMA1-7B, LLaMA2-7B, and Baichuan2-7B. The findings reveal that Qwen3-8B consistently surpasses these baselines by obtaining better classification accuracy and needing fewer training epochs. The synergy of instruction-based fine-tuning and memory-efficient optimization methods suggests Qwen3-8B can potentially serve as a scalable, economical option for real-time financial NLP applications. Qwen3-8B provides a very promising base for advancing dynamic quantitative trading systems in the future.
Authors: Timur Sattarov, Marco Schreyer, Damian Borth
Abstract: We introduce DP-FinDiff, a differentially private diffusion framework for synthesizing mixed-type tabular data. DP-FinDiff employs embedding-based representations for categorical features, reducing encoding overhead and scaling to high-dimensional datasets. To adapt DP-training to the diffusion process, we propose two privacy-aware training strategies: an adaptive timestep sampler that aligns updates with diffusion dynamics, and a feature-aggregated loss that mitigates clipping-induced bias. Together, these enhancements improve fidelity and downstream utility without weakening privacy guarantees. On financial and medical datasets, DP-FinDiff achieves 16-42% higher utility than DP baselines at comparable privacy levels, demonstrating its promise for safe and effective data sharing in sensitive domains.
Authors: Yaswanth Chittepu, Raghavendra Addanki, Tung Mai, Anup Rao, Branislav Kveton
Abstract: The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature engineering, model selection, and hyperparameter optimization, tasks that require sophisticated planning and iteration. While recent work on building ML agents has explored using large language models (LLMs) for direct code generation, tool-augmented approaches offer greater modularity and reliability. However, existing tool-use benchmarks focus primarily on task-specific tool selection or argument extraction for tool invocation, failing to evaluate the sophisticated planning capabilities required for ML Agents. In this work, we introduce a comprehensive benchmark for evaluating tool-augmented ML agents using a curated set of 61 specialized tools and 15 tabular ML challenges from Kaggle. Our benchmark goes beyond traditional tool-use evaluation by incorporating an in-memory named object management, allowing agents to flexibly name, save, and retrieve intermediate results throughout the workflows. We demonstrate that standard ReAct-style approaches struggle to generate valid tool sequences for complex ML pipelines, and that tree search methods with LLM-based evaluation underperform due to inconsistent state scoring. To address these limitations, we propose two simple approaches: 1) using shaped deterministic rewards with structured textual feedback, and 2) decomposing the original problem into a sequence of sub-tasks, which significantly improves trajectory validity and task performance. Using GPT-4o, our approach improves over ReAct by 16.52 percentile positions, taking the median across all Kaggle challenges. We believe our work provides a foundation for developing more capable tool-augmented planning ML agents.
Authors: Anish Lakkapragada
Abstract: Classical statistical inference and learning theory often fail to explain the success of modern neural networks. A key reason is that these models are non-identifiable (singular), violating core assumptions behind PAC bounds and asymptotic normality. Singular learning theory (SLT), a physics-inspired framework grounded in algebraic geometry, has gained popularity for its ability to close this theory-practice gap. In this paper, we empirically study SLT in toy settings relevant to interpretability and phase transitions. First, we understand the SLT free energy $\mathcal{F}_n$ by testing an Arrhenius-style rate hypothesis using both a grokking modulo-arithmetic model and Anthropic's Toy Models of Superposition. Second, we understand the local learning coefficient $\lambda_{\alpha}$ by measuring how it scales with problem difficulty across several controlled network families (polynomial regressors, low-rank linear networks, and low-rank autoencoders). Our experiments recover known scaling laws while others yield meaningful deviations from theoretical expectations. Overall, our paper illustrates the many merits of SLT for understanding neural network phase transitions, and poses open research questions for the field.
Authors: Bahrul Ilmi Nasution, Floor Eijkelboom, Mark Elliot, Richard Allmendinger, Christian A. Naesseth
Abstract: Synthetic data generation is an important tool for privacy-preserving data sharing. While diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement flow matching for tabular data synthesis. We provide a comprehensive empirical study that compares flow matching (FM and variational FM) with a state-of-the-art diffusion method (TabDDPM and TabSyn) in tabular data synthesis. We evaluate both the standard Optimal Transport (OT) and the Variance Preserving (VP) probability paths, and also compare deterministic and stochastic samplers -- something possible when learning to generate using \textit{variational} flow matching -- characterising the empirical relationship between data utility and privacy risk. Our key findings reveal that flow matching, particularly TabbyFlow, outperforms diffusion baselines. Flow matching methods also achieves better performance with remarkably low function evaluations ($\leq$ 100 steps), offering a substantial computational advantage. The choice of probability path is also crucial, as using the OT path demonstrates superior performance, while VP has potential for producing synthetic data with lower disclosure risk. Lastly, our results show that making flows stochastic not only preserves marginal distributions but, in some instances, enables the generation of high utility synthetic data with reduced disclosure risk.
Authors: Ming-Hsiu Wu, Ziqian Xie, Shuiwang Ji, Degui Zhi
Abstract: Advancements in AI for science unlocks capabilities for critical drug discovery tasks such as protein-ligand binding affinity prediction. However, current models overfit to existing oversimplified datasets that does not represent naturally occurring and biologically relevant proteins with modifications. In this work, we curate a complete and modification-aware version of the widely used DAVIS dataset by incorporating 4,032 kinase-ligand pairs involving substitutions, insertions, deletions, and phosphorylation events. This enriched dataset enables benchmarking of predictive models under biologically realistic conditions. Based on this new dataset, we propose three benchmark settings-Augmented Dataset Prediction, Wild-Type to Modification Generalization, and Few-Shot Modification Generalization-designed to assess model robustness in the presence of protein modifications. Through extensive evaluation of both docking-free and docking-based methods, we find that docking-based model generalize better in zero-shot settings. In contrast, docking-free models tend to overfit to wild-type proteins and struggle with unseen modifications but show notable improvement when fine-tuned on a small set of modified examples. We anticipate that the curated dataset and benchmarks offer a valuable foundation for developing models that better generalize to protein modifications, ultimately advancing precision medicine in drug discovery. The benchmark is available at: https://github.com/ZhiGroup/DAVIS-complete
Authors: Zhuohua Liu, Kaiqi Huang, Qinxin Mei, Yuanqi Hu, Wei W. Xing
Abstract: Analog circuit optimization is typically framed as black-box search over arbitrary smooth functions, yet device physics constrains performance mappings to structured families: exponential device laws, rational transfer functions, and regime-dependent dynamics. Off-the-shelf Gaussian-process surrogates impose globally smooth, stationary priors that are misaligned with these regime-switching primitives and can severely misfit highly nonlinear circuits at realistic sample sizes (50--100 evaluations). We demonstrate that pre-trained tabular models encoding these primitives enable reliable optimization without per-circuit engineering. Circuit Prior Network (CPN) combines a tabular foundation model (TabPFN v2) with Direct Expected Improvement (DEI), computing expected improvement exactly under discrete posteriors rather than Gaussian approximations. Across 6 circuits and 25 baselines, structure-matched priors achieve $R^2 \approx 0.99$ in small-sample regimes where GP-Mat\'ern attains only $R^2 = 0.16$ on Bandgap, deliver $1.05$--$3.81\times$ higher FoM with $3.34$--$11.89\times$ fewer iterations, and suggest a shift from hand-crafting models as priors toward systematic physics-informed structure identification. Our code will be made publicly available upon paper acceptance.
Authors: Fanlong Zeng, Wensheng Gan
Abstract: Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common type of out-of-distribution (OOD) problem, frequently encountered in real-world graph data with complex structures. Existing research has revealed that most out-of-the-box graph neural networks (GNNs) fail to account for covariate shifts. Furthermore, we observe that existing methods aimed at addressing covariate shifts often fail to fully leverage the rich information contained within the latent space. Motivated by the potential of the latent space, we introduce a new method called MPAIACL for More Powerful Adversarial Invariant Augmentation using Contrastive Learning. MPAIACL leverages contrastive learning to unlock the full potential of vector representations by harnessing their intrinsic information. Through extensive experiments, MPAIACL demonstrates its robust generalization and effectiveness, as it performs well compared with other baselines across various public OOD datasets. The code is publicly available at https://github.com/flzeng1/MPAIACL.
Authors: Lingling Fu
Abstract: Reward models play a critical role in Reinforcement Learning from Human Feedback (RLHF) by assessing the consistency between generated outputs and human preferences. However, conventional reward models are prone to reward hacking or over-optimization, where the policy exploits shortcut patterns to obtain high reward scores that do not reflect true human preference. Although Mixture-of-Experts (MoE)-based reward models can enhance discriminative capability, they typically introduce substantial computational overhead. To address these challenges, we propose an upcycle and merge MoE reward modeling approach. We first upcycle a dense reward model into a MoE architecture, where a shared expert captures general knowledge, while normal experts specialize in instruction-specific patterns. We then apply routing-weight normalization and merge experts back into a dense model through a learnable weight-averaging mechanism, preserving performance gains while significantly reducing inference cost. Experimental results demonstrate that our method effectively mitigates reward hacking across various model scales. Our work highlights the potential of upcycle and merge MoE structures for improving both robustness and efficiency of RLHF reward models.
Authors: Xinyue Wang, Yuheng Jia, Hui Liu, Junhui Hou
Abstract: Typical deep clustering methods, while achieving notable progress, can only provide one clustering result per dataset. This limitation arises from their assumption of a fixed underlying data distribution, which may fail to meet user needs and provide unsatisfactory clustering outcomes. Our work investigates how multi-modal large language models (MLLMs) can be leveraged to achieve user-driven clustering, emphasizing their adaptability to user-specified semantic requirements. However, directly using MLLM output for clustering has risks for producing unstructured and generic image descriptions instead of feature-specific and concrete ones. To address these issues, our method first discovers that MLLMs' hidden states of text tokens are strongly related to the corresponding features, and leverages these embeddings to perform clusterings from any user-defined criteria. We also employ a lightweight clustering head augmented with pseudo-label learning, significantly enhancing clustering accuracy. Extensive experiments demonstrate its competitive performance on diverse datasets and metrics.
Authors: Zach Lawrence, Jessica Yao, Chris Qin
Abstract: Wind farms with integrated energy storage, or hybrid wind farms, are able to store energy and dispatch it to the grid following an operational strategy. For individual wind farms with integrated energy storage capacity, data-driven dispatch strategies using localized grid demand and market conditions as input parameters stand to maximize wind energy value. Synthetic power generation data modeled on atmospheric conditions provide another avenue for improving the robustness of data-driven dispatch strategies. To these ends, the present work develops two deep learning frameworks: COVE-NN, an LSTM-based dispatch strategy tailored to individual wind farms, which reduced annual COVE by 32.3% over 43 years of simulated operations in a case study at the Pyron site; and a power generation modeling framework that reduced RMSE by 9.5% and improved power curve similarity by 18.9% when validated on the Palouse wind farm. Together, these models pave the way for more robust, data-driven dispatch strategies and potential extensions to other renewable energy systems.
Authors: Jacob Thompson, Emiliano Garcia-Lopez, Yonatan Bisk
Abstract: Humans build viewpoint-independent cognitive maps through navigation, enabling intuitive reasoning about object permanence and spatial relations. We argue that multimodal large language models (MLLMs), despite extensive video training, lack this fundamental spatial reasoning capability, a critical limitation for embodied applications. To demonstrate these limitations and drive research, we introduce REM (Reasoning over Embodied Multi-Frame Trajectories), a benchmark using controllable 3D environments for long-horizon embodied spatial reasoning. REM systematically evaluates key aspects like object permanence/distinction, spatial relationships, and numerical tracking across dynamic embodied viewpoints. Our evaluation shows that the best-performing current models exhibit promising overall performance, but become increasingly unreliable at even moderate complexity levels easily handled by humans. These findings highlight challenges MLLMs face in developing robust spatial representations from sequential visual input. Consequently, REM provides targeted metrics and diagnostics to foster improved spatial understanding in future models.
Authors: Zongjian Han, Yiran Liang, Ruiwen Wang, Yiwei Luo, Yilin Huang, Xiaotong Song, Dongqing Wei
Abstract: This paper presents a neural network filter method based on contraction operators to address model collapse in recursive training of generative models. Unlike \cite{xu2024probabilistic}, which requires superlinear sample growth ($O(t^{1+s})$), our approach completely eliminates the dependence on increasing sample sizes within an unbiased estimation framework by designing a neural filter that learns to satisfy contraction conditions. We develop specialized neural network architectures and loss functions that enable the filter to actively learn contraction conditions satisfying Assumption 2.3 in exponential family distributions, thereby ensuring practical application of our theoretical results. Theoretical analysis demonstrates that when the learned contraction conditions are satisfied, estimation errors converge probabilistically even with constant sample sizes, i.e., $\limsup_{t\to\infty}\mathbb{P}(\|\mathbf{e}_t\|>\delta)=0$ for any $\delta>0$. Experimental results show that our neural network filter effectively learns contraction conditions and prevents model collapse under fixed sample size settings, providing an end-to-end solution for practical applications.
Authors: Subarna Khanra, Vijay Kumar Kukreja, Indu Bala
Abstract: Demographic forecasting remains a fundamental challenge for policy planning in rapidly evolving nations such as India, where fertility transitions, policy interventions, and age structured dynamics interact in complex ways. In this study, we present a hybrid modelling framework that integrates policy-aware fertility functions into a Physics-Informed Neural Network (PINN) enhanced with Long Short-Term Memory (LSTM) networks to capture physical constraints and temporal dependencies in population dynamics. The model is applied to India's age structured population from 2024 to 2054 under three fertility-policy scenarios: continuation of current fertility decline, stricter population control, and relaxed fertility promotion. The governing transport-reaction partial differential equation is formulated with India-specific demographic indicators, including age-specific fertility and mortality rates. PINNs embed the core population equation and policy-driven fertility changes, while LSTM layers improve long-term forecasting across decades. Results show that fertility policies substantially shape future age distribution, dependency ratios, and workforce size. Stricter controls intensify ageing and reduce labour force participation, whereas relaxed policies support workforce growth but increase population pressure. Our findings suggest that the hybrid LSTM-PINN is an effective approach for demographic forecasting, offering accuracy with interpretability. Beyond methodological novelty, this work provides actionable insights for India's demographic policy debates, highlighting the need for balanced fertility interventions to ensure sustainable socio-economic development.
Authors: Robin Yadav, Shuo Xie, Tianhao Wang, Zhiyuan Li
Abstract: Adaptive optimization methods (such as Adam) play a major role in LLM pretraining, significantly outperforming Gradient Descent (GD). Recent studies have proposed new smoothness assumptions on the loss function to explain the advantages of adaptive algorithms with structured preconditioners, e.g., coordinate-wise or layer-wise, and steepest descent methods w.r.t. non-euclidean norms, e.g., $\ell_\infty$ norm or spectral norm, over GD. However, it remains unclear how these smoothness assumptions manifest in language modelling tasks. In this work, we aim to analyze the benefit of $\ell_\infty$-norm descent (a.k.a. sign descent) directly from properties of the data distribution, namely, heavy-tailed class imbalance. We propose a minimal yet representative setting of next-token prediction, where we can provably show faster convergence of coordinate-wise algorithms such as Sign descent (steepest descent w.r.t. $\ell_\infty$ norm) over normalized GD (steepest descent w.r.t. to $\ell_2$ norm) in the presence of heavy tail class imbalance.
Authors: Hamed Razavi
Abstract: The fast growth of digital health systems has led to a need to better comprehend how they interpret and represent patient-reported symptoms. Chatbots have been used in healthcare to provide clinical support and enhance the user experience, making it possible to provide meaningful clinical patterns from text-based data through chatbots. The proposed research utilises several different natural language processing methods to study the occurrences of symptom descriptions in medicine as well as analyse the patterns that emerge through these conversations within medical bots. Through the use of the Medical Conversations to Disease Dataset which contains 960 multi-turn dialogues divided into 24 Clinical Conditions, a standardised representation of conversations between patient and bot is created for further analysis by computational means. The multi-method approach uses a variety of tools, including Latent Dirichlet Allocation (LDA) to identify latent symptom themes, K-Means to group symptom descriptions by similarity, Transformer-based Named Entity Recognition (NER) to extract medical concepts, and the Apriori algorithm to discover frequent symptom pairs. Findings from the analysis indicate a coherent structure of clinically relevant topics, moderate levels of clustering cohesiveness and several high confidence rates on the relationships between symptoms like fever headache and rash itchiness. The results support the notion that conversational medical data can be a valuable diagnostic signal for early symptom interpretation, assist in strengthening decision support and improve how users interact with tele-health technology. By demonstrating a method for converting unstructured free-flowing dialogue into actionable knowledge regarding symptoms this work provides an extensible framework to further enhance future performance, dependability and clinical utility of selecting medical chatbots.
Authors: Xingchen Zhou, Nan Li, Peng Jia, Yingfeng Liu, Furen Deng, Shuanghao Shu, Ying Li, Liang Cao, Huanyuan Shan, Ayodeji Ibitoye
Abstract: Source extraction is crucial in analyzing data from next-generation, large-scale sky surveys in radio bands, such as the Square Kilometre Array (SKA). Several source extraction programs, including SoFiA and Aegean, have been developed to address this challenge. However, finding optimal parameter configurations when applying these programs to real observations is non-trivial. For example, the outcomes of SoFiA intensely depend on several key parameters across its preconditioning, source-finding, and reliability-filtering modules. To address this issue, we propose a framework to automatically optimize these parameters using an AI agent based on a state-of-the-art reinforcement learning (RL) algorithm, i.e., Soft Actor-Critic (SAC). The SKA Science Data Challenge 2 (SDC2) dataset is utilized to assess the feasibility and reliability of this framework. The AI agent interacts with the environment by adjusting parameters based on the feedback from the SDC2 score defined by the SDC2 Team, progressively learning to select parameter sets that yield improved performance. After sufficient training, the AI agent can automatically identify an optimal parameter configuration that outperform the benchmark set by Team SoFiA within only 100 evaluation steps and with reduced time consumption. Our approach could address similar problems requiring complex parameter tuning, beyond radio band surveys and source extraction. Yet, high-quality training sets containing representative observations and catalogs of ground truth are essential.
Authors: Yue Wang, Qizhou Wang, Zizhuo Zhang, Ang Li, Gang Niu, Bo Han, Masashi Sugiyama
Abstract: Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is supervised learning while PPO is reinforcement learning, yet deeper analyses for the reasons underlying these differences remain lacking. To fill this gap, we analyze their optimization dynamics, revealing distinct algorithmic behaviors and comprehending their underlying causes. First, we examine the target directions of gradient-based updates and find that DPO follows stable targets, whereas PPO follows dynamic targets that balance exploration and exploitation, thus validating the common belief from a new perspective. Second, we examine the roles of positive learning, negative learning, and loss reweighting, which are three key components in PO methods. Our analyses reveal that these components play fairly different roles. In DPO, positive and negative learning jointly shape the learning targets meanwhile mutually offset each other. However, loss reweighting in DPO acts less as a reward signal but more as a regularizer to mitigate overfitting. In PPO, negative learning primarily supports exploration rather than determining the targets. Meanwhile, loss reweighting, related to absolute values of token-level advantages, indicates the distinct roles of token groups in updating targets. Given these findings, we conduct carefully designed ablation studies to further examine how controlling these dynamics impacts optimization efficiency and practical performance. The insights gained from our analyses not only deepen the understanding of PO methods but also inspire the development of more preference-aligned LLMs.
Authors: Libo Wang
Abstract: To address the gap in humanoid robot cognitive systems regarding the lack of a time-updable mediating thought space between semantics and continuous control, this study constructs and trains a VLA model named "Sigma" that runs on a single RTX 4090. It uses the open-source pi05_base model as a foundation and preprocesses svla_so101_pickplace into a training dataset. The researcher independently designed an architecture for a vision-language-action model that combines deep semantic understanding and association to achieve telepathic communication. The training process involved repeated optimizations of data preprocessing, LoRA fine-tuning, and the inference-stage adapter. The experiment employed offline closed-loop replay, comparing Sigma with the untuned pure pi05_base_base model under data conditions. Results showed that Sigma exhibited a stable decrease in control MSE across vector, fragment, and entire trajectory timescales, while maintaining the telepathy norm and semantic-text alignment quality unchanged. It demonstrates that mind-responsive alignment control is quantified through an architecture that combines deep understanding of semantics and association without retraining the base model, which provides reproducible experience for semantic alignment and intention-driven behavior in humanoid robots.
Authors: Jordi P\'erez-Guijarro
Abstract: When the distributions of the training and test data do not coincide, the problem of understanding generalization becomes considerably more complex, prompting a variety of questions. In this work, we focus on a fundamental one: Is it always optimal for the training distribution to be identical to the test distribution? Surprisingly, assuming the existence of one-way functions, we find that the answer is no. That is, matching distributions is not always the best scenario, which contrasts with the behavior of most learning methods. Nonetheless, we also show that when certain regularities are imposed on the target functions, the standard conclusion is recovered in the case of the uniform distribution.
Authors: Liyu Zerihun
Abstract: Deep networks are heavily over-parameterized, yet their learned representations often admit low-rank structure. We introduce a framework for estimating a model's intrinsic dimensionality by treating learned representations as projections onto a low-rank subspace of the model's full capacity. Our approach: train a full-rank teacher, factorize its weights at multiple ranks, and train each factorized student via distillation to measure performance as a function of rank. We define effective rank as a region, not a point: the smallest contiguous set of ranks for which the student reaches 85-95% of teacher accuracy. To stabilize estimates, we fit accuracy vs. rank with a monotone PCHIP interpolant and identify crossings of the normalized curve. We also define the effective knee as the rank maximizing perpendicular distance between the smoothed accuracy curve and its endpoint secant; an intrinsic indicator of where marginal gains concentrate. On ViT-B/32 fine-tuned on CIFAR-100 (one seed, due to compute constraints), factorizing linear blocks and training with distillation yields an effective-rank region of approximately [16, 34] and an effective knee at r* ~ 31. At rank 32, the student attains 69.46% top-1 accuracy vs. 73.35% for the teacher (~94.7% of baseline) while achieving substantial parameter compression. We provide a framework to estimate effective-rank regions and knees across architectures and datasets, offering a practical tool for characterizing the intrinsic dimensionality of deep models.
Authors: Saeed Hedayatian, Stefanos Nikolaidis
Abstract: Quality-Diversity (QD) algorithms constitute a branch of optimization that is concerned with discovering a diverse and high-quality set of solutions to an optimization problem. Current QD methods commonly maintain diversity by dividing the behavior space into discrete regions, ensuring that solutions are distributed across different parts of the space. The QD problem is then solved by searching for the best solution in each region. This approach to QD optimization poses challenges in large solution spaces, where storing many solutions is impractical, and in high-dimensional behavior spaces, where discretization becomes ineffective due to the curse of dimensionality. We present an alternative framing of the QD problem, called \emph{Soft QD}, that sidesteps the need for discretizations. We validate this formulation by demonstrating its desirable properties, such as monotonicity, and by relating its limiting behavior to the widely used QD Score metric. Furthermore, we leverage it to derive a novel differentiable QD algorithm, \emph{Soft QD Using Approximated Diversity (SQUAD)}, and demonstrate empirically that it is competitive with current state of the art methods on standard benchmarks while offering better scalability to higher dimensional problems.
Authors: Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang
Abstract: Multi-label classification (MLC) remains vulnerable to label imbalance, spurious correlations, and distribution shifts, challenges that are particularly detrimental to rare label prediction. To address these limitations, we introduce the Causal Cooperative Game (CCG) framework, which conceptualizes MLC as a cooperative multi-player interaction. CCG unifies explicit causal discovery via Neural Structural Equation Models with a counterfactual curiosity reward to drive robust feature learning. Furthermore, it incorporates a causal invariance loss to ensure generalization across diverse environments, complemented by a specialized enhancement strategy for rare labels. Extensive benchmarking demonstrates that CCG substantially outperforms strong baselines in both rare label prediction and overall robustness. Through rigorous ablation studies and qualitative analysis, we validate the efficacy and interpretability of our components, underscoring the potential of synergizing causal inference with cooperative game theory for advancing multi-label learning.
Authors: Yuchen Zeng, Shuibai Zhang, Wonjun Kang, Shutong Wu, Lynnix Zou, Ying Fan, Heeju Kim, Ziqian Lin, Jungtaek Kim, Hyung Il Koo, Dimitris Papailiopoulos, Kangwook Lee
Abstract: Large Reasoning Models (LRMs) are Large Language Models (LLMs) explicitly trained to generate long-form Chain-of-Thoughts (CoTs), achieving impressive success on challenging tasks like math and programming. However, their underlying reasoning "algorithms" remain poorly understood. To investigate this, we propose ReJump, which represents a reasoning trace as a visitation order over nodes in a tree of intermediate problem-solving steps. Transitions between nodes, which we term jumps, include adjacent moves that capture behaviors such as calculation, and non-adjacent moves that capture behaviors such as backtracking and verification. ReJump enables analyzing LLM reasoning with diverse metrics that quantify exploration, exploitation, overthinking, forgetting, and verification. Using our proposed LLM agent to extract reasoning traces into ReJump format, we evaluate state-of-the-art LRMs on two tasks and find that models with similar accuracy can exhibit distinct reasoning behaviors, while different tasks favor different reasoning styles (e.g., varying balance between exploration and exploitation). To further understand how learning strategies shape reasoning, we use ReJump to compare distilled LRMs with their teachers, CoT-prompted LLMs with LRMs, and to examine how the number of reasoning examples and reinforcement learning affect reasoning behavior. Finally, we show that ReJump can improve reasoning quality at test time through strategies such as ReJump-guided Best-of-N selection and prompt selection. Our code is publicly available at https://github.com/UW-Madison-Lee-Lab/ReJump.
Authors: Adriel Sosa Marco, John Daniel Kirwan, Alexia Toumpa, Simos Gerasimou
Abstract: Quantifying uncertainty in deep regression models is important both for understanding the confidence of the model and for safe decision-making in high-risk domains. Existing approaches that yield prediction intervals overlook distributional information, neglecting the effect of multimodal or asymmetric distributions on decision-making. Similarly, full or approximated Bayesian methods, while yielding the predictive posterior density, demand major modifications to the model architecture and retraining. We introduce MCNF, a novel post hoc uncertainty quantification method that produces both prediction intervals and the full conditioned predictive distribution. MCNF operates on top of the underlying trained predictive model; thus, no predictive model retraining is needed. We provide experimental evidence that the MCNF-based uncertainty estimate is well calibrated, is competitive with state-of-the-art uncertainty quantification methods, and provides richer information for downstream decision-making tasks.
Authors: Wenzhang Du
Abstract: Federated learning (FL) enables collaborative training over distributed multimedia data but suffers acutely from statistical heterogeneity and communication constraints, especially when clients deploy large models. Classic parameter-averaging methods such as FedAvg transmit full model weights and can diverge under nonindependent and identically distributed (non-IID) data. We propose KTA v2, a prediction-space knowledge trading market for FL. Each round, clients locally train on their private data, then share only logits on a small public reference set. The server constructs a client-client similarity graph in prediction space, combines it with reference-set accuracy to form per-client teacher ensembles, and sends back personalized soft targets for a second-stage distillation update. This two-stage procedure can be interpreted as approximate block-coordinate descent on a unified objective with prediction-space regularization. Experiments on FEMNIST, CIFAR-10 and AG News show that, under comparable or much lower communication budgets, KTA v2 consistently outperforms a local-only baseline and strong parameter-based methods (FedAvg, FedProx), and substantially improves over a FedMD-style global teacher. On CIFAR-10 with ResNet-18, KTA v2 reaches 57.7% test accuracy using approximately 1/1100 of FedAvg's communication, while on AG News it attains 89.3% accuracy with approximately 1/300 of FedAvg's traffic.
Authors: Yunbo Long, Jiaquan Zhang, Xi Chen, Alexandra Brintrup
Abstract: Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy while maintaining accuracy without iterative communication. Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings, degrading severely under strong LDP noise and data heterogeneity. We present Gravitational Federated Clustering (GFC), a novel approach to privacy-preserving federated clustering that overcomes the limitations of distance-based methods under varying LDP. Addressing the critical challenge of clustering non-IID data with diverse privacy guarantees, GFC transforms privatized client centroids into a global gravitational potential field where true cluster centers emerge as topologically persistent singularities. Our framework introduces two key innovations: (1) a client-side compactness-aware perturbation mechanism that encodes local cluster geometry as "mass" values, and (2) a server-side topological aggregation phase that extracts stable centroids through persistent homology analysis of the potential field's superlevel sets. Theoretically, we establish a closed-form bound between the privacy budget $\epsilon$ and centroid estimation error, proving the potential field's Lipschitz smoothing properties exponentially suppress noise in high-density regions. Empirically, GFC outperforms state-of-the-art methods on ten benchmarks, especially under strong LDP constraints ($\epsilon < 1$), while maintaining comparable performance at lower privacy budgets. By reformulating federated clustering as a topological persistence problem in a synthetic physics-inspired space, GFC achieves unprecedented privacy-accuracy trade-offs without iterative communication, providing a new perspective for privacy-preserving distributed learning.
Authors: Wenzhang Du
Abstract: Deploying spatio-temporal forecasting models across many cities is difficult: traffic networks differ in size and topology, data availability can vary by orders of magnitude, and new cities may provide only a short history of logs. Existing deep traffic models are typically trained per city and backbone, creating high maintenance cost and poor transfer to data-scarce cities. We ask whether a single, backbone-agnostic layer can condition on "which city this sequence comes from", improve accuracy in full- and low-data regimes, and support better cross-city adaptation with minimal code changes. We propose CityCond, a light-weight city-conditioned memory layer that augments existing spatio-temporal backbones. CityCond combines a city-ID encoder with an optional shared memory bank (CityMem). Given a city index and backbone hidden states, it produces city-conditioned features fused through gated residual connections. We attach CityCond to five representative backbones (GRU, TCN, Transformer, GNN, STGCN) and evaluate three regimes: full-data, low-data, and cross-city few-shot transfer on METR-LA and PEMS-BAY. We also run auxiliary experiments on SIND, a drone-based multi-agent trajectory dataset from a signalized intersection in Tianjin (we focus on pedestrian tracks). Across more than fourteen model variants and three random seeds, CityCond yields consistent improvements, with the largest gains for high-capacity backbones such as Transformers and STGCNs. CityMem reduces Transformer error by roughly one third in full-data settings and brings substantial gains in low-data and cross-city transfer. On SIND, simple city-ID conditioning modestly improves low-data LSTM performance. CityCond can therefore serve as a reusable design pattern for scalable, multi-city forecasting under realistic data constraints.
Authors: Midhun Manoj
Abstract: Probabilistic forecasting is essential for modern risk management, allowing decision-makers to quantify uncertainty in critical systems. This paper tackles this challenge using the volatile REFIT household dataset, which is complicated by a large structural data gap. We first address this by conducting a rigorous comparative experiment to select a Seasonal Imputation method, demonstrating its superiority over linear interpolation in preserving the data's underlying distribution. We then systematically evaluate a hierarchy of models, progressing from classical baselines (SARIMA, Prophet) to machine learning (XGBoost) and advanced deep learning architectures (LSTM). Our findings reveal that classical models fail to capture the data's non-linear, regime-switching behavior. While the LSTM provided the most well-calibrated probabilistic forecast, the Temporal Fusion Transformer (TFT) emerged as the superior all-round model, achieving the best point forecast accuracy (RMSE 481.94) and producing safer, more cautious prediction intervals that effectively capture extreme volatility.
Authors: Praveen Anilkumar Shukla
Abstract: Modern deep networks are heavily overparameterized yet often generalize well, suggesting a form of low intrinsic complexity not reflected by parameter counts. We study this complexity at initialization through the effective rank of the Neural Tangent Kernel (NTK) Gram matrix, $r_{\text{eff}}(K) = (\text{tr}(K))^2/\|K\|_F^2$. For i.i.d. data and the infinite-width NTK $k$, we prove a constant-limit law $\lim_{n\to\infty} \mathbb{E}[r_{\text{eff}}(K_n)] = \mathbb{E}[k(x, x)]^2 / \mathbb{E}[k(x, x')^2] =: r_\infty$, with sub-Gaussian concentration. We further establish finite-width stability: if the finite-width NTK deviates in operator norm by $O_p(m^{-1/2})$ (width $m$), then $r_{\text{eff}}$ changes by $O_p(m^{-1/2})$. We design a scalable estimator using random output probes and a CountSketch of parameter Jacobians and prove conditional unbiasedness and consistency with explicit variance bounds. On CIFAR-10 with ResNet-20/56 (widths 16/32) across $n \in \{10^3, 5\times10^3, 10^4, 2.5\times10^4, 5\times10^4\}$, we observe $r_{\text{eff}} \approx 1.0\text{--}1.3$ and slopes $\approx 0$ in $n$, consistent with the theory, and the kernel-moment prediction closely matches fitted constants.
Authors: Ningning Chen, Weicai Ye, Ying Jiang
Abstract: We introduce HBLLM, a wavelet-enhanced high-fidelity $1$-bit post-training quantization method for Large Language Models (LLMs). By leveraging Haar wavelet transforms to enhance expressive capacity through frequency decomposition, HBLLM significantly improves quantization fidelity while maintaining minimal overhead. This approach features two innovative structure-aware grouping strategies: (1) frequency-aware multi-parameter intra-row grouping and (2) $\ell_2$-norm-based saliency-driven column selection. For non-salient weights, a shared mean is employed across quantization groups within each frequency band to optimize storage efficiency. Experiments conducted on the OPT and LLaMA models demonstrate that HBLLM achieves state-of-the-art performance in $1$-bit quantization, attaining a perplexity of $6.71$ on LLaMA$2$-$13$B with an average weight storage of only $1.08$ bits. Code available at: https://github.com/Yeyke/HBLLM.
Authors: Samuel Kessler, Menglin Xia, Daniel Madrigal Diaz, Dongge Han, Helia Heshemi, Saravan Rajmohan, Victor Ruehle, Jordan T. Ash
Abstract: A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are often produced before any student finetuning, but some work has considered generating new synthetic samples as training progresses. This paper studies and advocates for the latter case, where data are generated in an iterative, closed-loop fashion that is guided by the current state of the student model. For a fixed budget of generated samples, or a budget in terms of compute spent querying a teacher, we show that this curation of finetuning data affords improved student performance over static generation. Further, while there have been several LLM-specific methods proposed that operate in this regime, we find that simple, inexpensive selection criteria from the active learning literature tend to be most performant. We validate these claims across four mathematical and logical reasoning datasets using four different small language models.
Authors: Aayam Bansal, Ishaan Gangwani
Abstract: Zero-shot foundation models (FMs) promise training-free prediction on tabular data, yet their hardware footprint remains poorly characterized. We present a fully reproducible benchmark that reports test accuracy together with wall-clock latency, peak CPU RAM, and peak GPU VRAM on four public datasets: Adult-Income, Higgs-100k, Wine-Quality, and California-Housing. Two open FMs (TabPFN-1.0 and TabICL-base) are compared against tuned XGBoost, LightGBM, and Random Forest baselines on a single NVIDIA T4 GPU. The tree ensembles equal or surpass FM accuracy on three datasets while completing full-test batches in <= 0.40 s and <= 150 MB RAM, using zero VRAM. TabICL achieves a 0.8 percentage-point gain on Higgs but requires roughly 40,000 times more latency (960 s) and 9 GB VRAM. TabPFN matches tree-model accuracy on Wine and Housing but peaks at 4 GB VRAM and cannot process the full 100k-row Higgs table. These results quantify the substantial hardware-versus-accuracy trade-offs in current tabular FMs and provide an open baseline for future efficiency-oriented research.
Authors: Xinzhu Chen, Xuesheng Li, Zhongxiang Sun, Weijie Yu
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models. Recent work studies RLVR through token entropy, arguing that high-entropy tokens drive exploration and should receive stronger updates. However, they overlook the fact that most of a reasoning trajectory consists of low-entropy segments that encode stable and reusable structural patterns. Through qualitative and quantitative analyses, we find that the overlap of low-entropy segments across correct responses strongly correlates with model accuracy, while overlaps involving incorrect responses exhibit stable but unproductive patterns. Motivated by these findings, we propose LESS, a correctness-aware reinforcement framework that performs fine-grained advantage modulation over low-entropy segments. LESS amplifies segments unique to correct responses, suppresses those unique to incorrect ones, and neutralizes segments shared by both, while preserving high-entropy exploration in the underlying RL algorithm. Instantiated on top of the popular GRPO, LESS consistently improves accuracy over strong RL baselines across three backbones and six math benchmarks, achieves stronger robustness of the performance floor.
Authors: Junwoo Chang, Minwoo Park, Joohwan Seo, Roberto Horowitz, Jongmin Lee, Jongeun Choi
Abstract: Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments almost never realize fully group-invariant MDPs; dynamics, actuation limits, and reward design usually break symmetries, often only locally. Under group-invariant Bellman backups for such cases, local symmetry-breaking introduces errors that propagate across the entire state-action space, resulting in global value estimation errors. To address this, we introduce Partially group-Invariant MDP (PI-MDP), which selectively applies group-invariant or standard Bellman backups depending on where symmetry holds. This framework mitigates error propagation from locally broken symmetries while maintaining the benefits of equivariance, thereby enhancing sample efficiency and generalizability. Building on this framework, we present practical RL algorithms -- Partially Equivariant (PE)-DQN for discrete control and PE-SAC for continuous control -- that combine the benefits of equivariance with robustness to symmetry-breaking. Experiments across Grid-World, locomotion, and manipulation benchmarks demonstrate that PE-DQN and PE-SAC significantly outperform baselines, highlighting the importance of selective symmetry exploitation for robust and sample-efficient RL.
Authors: Shaoxun Wang, Xingjun Zhang, Kun Xia, Qianyang Li, Jiawei Cao, Zhendong Tan
Abstract: Accurate Multivariate Time Series (MTS) forecasting is crucial for collaborative design of complex systems, Digital Twin building, and maintenance ahead of time. However, the collaborative industrial environment presents new challenges for MTS forecasting models: models should decouple complex inter-variable dependencies while addressing non-stationary distribution shift brought by environmental changes. To address these challenges and improve collaborative sensing reliability, we propose a Patch-Based Dual-Branch Channel-Temporal Forecasting Network (D-CTNet). Particularly, with a parallel dual-branch design incorporating linear temporal modeling layer and channel attention mechanism, our method explicitly decouples and jointly learns intra-channel temporal evolution patterns and dynamic multivariate correlations. Furthermore, a global patch attention fusion module goes beyond the local window scope to model long range dependencies. Most importantly, aiming at non-stationarity, a Frequency-Domain Stationarity Correction mechanism adaptively suppresses distribution shift impacts from environment change by spectrum alignment. Evaluations on seven benchmark datasets show that our model achieves better forecasting accuracy and robustness compared with state-of-the-art methods. Our work shows great promise as a new forecasting engine for industrial collaborative systems.
Authors: Susmit Agrawal, Krishn Vishwas Kher, Saksham Mittal, Swarnim Maheshwari, Vineeth N. Balasubramanian
Abstract: Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic forgetting, a phenomenon neuroscientists hypothesize, is due to a singular neural circuitry dynamically overlayed by neuromodulatory agents such as dopamine and acetylcholine. In parallel, deep learning research addresses analogous challenges via domain generalization (DG) and continual learning (CL), yet these methods remain siloed, despite the brains ability to perform them seamlessly. In particular, prior work has not explored architectures involving associative memories (AMs), which are an integral part of biological systems, to jointly address these tasks. We propose Memory-Integrated Reconfigurable Adapters (MIRA), a unified framework that integrates Hopfield-style associative memory modules atop a shared backbone. Associative memory keys are learned post-hoc to index and retrieve an affine combination of stored adapter updates for any given task or domain on a per-sample basis. By varying only the task-specific objectives, we demonstrate that MIRA seamlessly accommodates domain shifts and sequential task exposures under one roof. Empirical evaluations on standard benchmarks confirm that our AM-augmented architecture significantly enhances adaptability and retention: in DG, MIRA achieves SoTA out-of-distribution accuracy, and in incremental learning settings, it outperforms architectures explicitly designed to handle catastrophic forgetting using generic CL algorithms. By unifying adapter-based modulation with biologically inspired associative memory, MIRA delivers rapid task switching and enduring knowledge retention in a single extensible architecture, charting a path toward more versatile and memory-augmented AI systems.
Authors: Yansong Liu, Ronnie Stafford, Pramit Khetrapal, Huriye Kocadag, Gra\c{c}a Carvalho, Patricia de Winter, Maryam Imran, Amelia Snook, Adamos Hadjivasiliou, D. Vijay Anand, Weining Lin, John Kelly, Yukun Zhou, Ivana Drobnjak
Abstract: For patients undergoing systemic cancer therapy, the time between clinic visits is full of uncertainties and risks of unmonitored side effects. To bridge this gap in care, we developed and prospectively trialed a multi-modal AI framework for remote patient monitoring (RPM). This system integrates multi-modal data from the HALO-X platform, such as demographics, wearable sensors, daily surveys, and clinical events. Our observational trial is one of the largest of its kind and has collected over 2.1 million data points (6,080 patient-days) of monitoring from 84 patients. We developed and adapted a multi-modal AI model to handle the asynchronous and incomplete nature of real-world RPM data, forecasting a continuous risk of future adverse events. The model achieved an accuracy of 83.9% (AUROC=0.70). Notably, the model identified previous treatments, wellness check-ins, and daily maximum heart rate as key predictive features. A case study demonstrated the model's ability to provide early warnings by outputting escalating risk profiles prior to the event. This work establishes the feasibility of multi-modal AI RPM for cancer care and offers a path toward more proactive patient support.(Accepted at Europe NeurIPS 2025 Multimodal Representation Learning for Healthcare Workshop)
Authors: Jiale Chen, Vage Egiazarian, Torsten Hoefler, Dan Alistarh
Abstract: Quantization to low bitwidth is a standard approach for deploying large language models, however, a few extreme weights and activations stretch the dynamic range and reduce the effective resolution of the quantizer. A common mitigation approach is to apply some fixed orthogonal transforms, such as Hadamard matrices, before quantization, which typically reduces the dynamic range. Yet, these transforms ignore the statistics of the data, and their optimality is currently not understood. In this work, we derive, for the first time, closed-form optimal linear blockwise transforms for joint weight-activation quantization using standard data-free quantizers for common numerical formats. Specifically, we provide derivations of the optimal adaptive (data-aware) transforms for round-to-nearest (RTN), AbsMax-scaled block quantizers for both integer and floating-point formats. The resulting construction, which we call WUSH, combines a Hadamard backbone with a data-dependent component based on second-order moments, yielding a non-orthogonal transform that is provably optimal under mild assumptions and remains structured for efficient implementation. Preliminary experimental results show that our approach consistently improves upon the Hadamard transform for common formats.
Authors: Qi Wang, Mian Wu, Yuyang Zhang, Mingqi Yuan, Wenyao Zhang, Haoxiang You, Yunbo Wang, Xin Jin, Xiaokang Yang, Wenjun Zeng
Abstract: Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not generalize well across different tasks. To address this limitation, we leverage the rich world knowledge contained in pretrained video diffusion models to provide goal-driven reward signals for RL agents without ad-hoc design of reward. Our key idea is to exploit off-the-shelf video diffusion models pretrained on large-scale video datasets as informative reward functions in terms of video-level and frame-level goals. For video-level rewards, we first finetune a pretrained video diffusion model on domain-specific datasets and then employ its video encoder to evaluate the alignment between the latent representations of agent's trajectories and the generated goal videos. To enable more fine-grained goal-achievement, we derive a frame-level goal by identifying the most relevant frame from the generated video using CLIP, which serves as the goal state. We then employ a learned forward-backward representation that represents the probability of visiting the goal state from a given state-action pair as frame-level reward, promoting more coherent and goal-driven trajectories. Experiments on various Meta-World tasks demonstrate the effectiveness of our approach.
Authors: Cynthia Feeney, Shane Williams, Benjamin S. Wessler, Michael C. Hughes
Abstract: Echocardiogram datasets enable training deep learning models to automate interpretation of cardiac ultrasound, thereby expanding access to accurate readings of diagnostically-useful images. However, the gender, sex, race, and ethnicity of the patients in these datasets are underreported and subgroup-specific predictive performance is unevaluated. These reporting deficiencies raise concerns about subgroup validity that must be studied and addressed before model deployment. In this paper, we show that current open echocardiogram datasets are unable to assuage subgroup validity concerns. We improve sociodemographic reporting for two datasets: TMED-2 and MIMIC-IV-ECHO. Analysis of six open datasets reveals no consideration of gender-diverse patients and insufficient patient counts for many racial and ethnic groups. We further perform an exploratory subgroup analysis of two published aortic stenosis detection models on TMED-2. We find insufficient evidence for subgroup validity for sex, racial, and ethnic subgroups. Our findings highlight that more data for underrepresented subgroups, improved demographic reporting, and subgroup-focused analyses are needed to prove subgroup validity in future work.
Authors: Zifeng Huang, Konstantin M. Zuev, Yong Xia, Michael Beer
Abstract: Neural oscillators, originating from the second-order ordinary differential equations (ODEs), have demonstrated competitive performance in stably learning causal mappings between long-term sequences or continuous temporal functions. However, theoretically quantifying the capacities of their neural network architectures remains a significant challenge. In this study, the neural oscillator consisting of a second-order ODE followed by a multilayer perceptron (MLP) is considered. Its upper approximation bound for approximating causal and uniformly continuous operators between continuous temporal function spaces and that for approximating uniformly asymptotically incrementally stable second-order dynamical systems are derived. The established proof method of the approximation bound for approximating the causal continuous operators can also be directly applied to state-space models consisting of a linear time-continuous complex recurrent neural network followed by an MLP. Theoretical results reveal that the approximation error of the neural oscillator for approximating the second-order dynamical systems scales polynomially with the reciprocals of the widths of two utilized MLPs, thus mitigating the curse of parametric complexity. The decay rates of two established approximation error bounds are validated through two numerical cases. These results provide a robust theoretical foundation for the effective application of the neural oscillator in science and engineering.
Authors: Mohit Kumar, Mathias Brucker, Alexander Valentinitsch, Adnan Husakovic, Ali Abbas, Manuela Gei{\ss}, Bernhard A. Moser
Abstract: Federated learning must address heterogeneity, strict communication and computation limits, and privacy while ensuring performance. We propose an operator-theoretic framework that maps the $L^2$-optimal solution into a reproducing kernel Hilbert space (RKHS) via a forward operator, approximates it using available data, and maps back with the inverse operator, yielding a gradient-free scheme. Finite-sample bounds are derived using concentration inequalities over operator norms, and the framework identifies a data-dependent hypothesis space with guarantees on risk, error, robustness, and approximation. Within this space we design efficient kernel machines leveraging the space folding property of Kernel Affine Hull Machines. Clients transfer knowledge via a scalar space folding measure, reducing communication and enabling a simple differentially private protocol: summaries are computed from noise-perturbed data matrices in one step, avoiding per-round clipping and privacy accounting. The induced global rule requires only integer minimum and equality-comparison operations per test point, making it compatible with fully homomorphic encryption (FHE). Across four benchmarks, the gradient-free FL method with fixed encoder embeddings matches or outperforms strong gradient-based fine-tuning, with gains up to 23.7 points. In differentially private experiments, kernel smoothing mitigates accuracy loss in high-privacy regimes. The global rule admits an FHE realization using $Q \times C$ encrypted minimum and $C$ equality-comparison operations per test point, with operation-level benchmarks showing practical latencies. Overall, the framework provides provable guarantees with low communication, supports private knowledge transfer via scalar summaries, and yields an FHE-compatible prediction rule offering a mathematically grounded alternative to gradient-based federated learning under heterogeneity.
Authors: Luigi Assom
Abstract: This study presents an unsupervised method to infer discreteness, syntax and temporal structures of fruit-bats vocalizations, as a case study of graded vocal systems, and evaluates the complexity of communication patterns in relation with behavioral context. The method improved the baseline for unsupervised labeling of vocal units (i.e. syllables) through manifold learning, by investigating how dimen- sionality reduction on mel-spectrograms affects labeling, and comparing it with unsupervised labels based on acoustic similarity. We then encoded vocalizations as syllabic sequences to analyze the type of syntax, and extracted the Maximal Repetitions (MRs) to evaluate syntactical structures. We found evidence for: i) associative syntax, rather than combinatorial (context classification is unaffected by permutation of sequences, F 1 > 0.9); ii) context-dependent use of syllables (Wilcoxon rank-sum tests, p-value < 0.05); iii) heavy-tail distribution of MRs (truncated power-law, exponent {\alpha} < 2), indicative of mechanism encoding com- binatorial complexity. Analysis of MRs and syllabic transition networks revealed that mother-pupil interactions were characterized by repetitions, while commu- nication in conflict-contexts exhibited higher complexity (longer MRs and more interconnected vocal sequences) than non-agonistic contexts. We propose that communicative complexity is higher in scenarios of disagreement, reflecting lower compressibility of information.
Authors: Mansi Maheshwari, John C. Raisbeck, Bruno Castro da Silva
Abstract: Neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experiences declines over time. This decline in learning ability is known as plasticity loss. To restore plasticity, prior work has explored periodically resetting the parameters of the learning network, a strategy that often improves overall performance. However, such resets come at the cost of a temporary drop in performance, which can be dangerous in real-world settings. To overcome this instability, we introduce AltNet, a reset-based approach that restores plasticity without performance degradation by leveraging twin networks. The use of twin networks anchors performance during resets through a mechanism that allows networks to periodically alternate roles: one network learns as it acts in the environment, while the other learns off-policy from the active network's interactions and a replay buffer. At fixed intervals, the active network is reset and the passive network, having learned from prior experiences, becomes the new active network. AltNet restores plasticity, improving sample efficiency and achieving higher performance, while avoiding performance drops that pose risks in safety-critical settings. We demonstrate these advantages in several high-dimensional control tasks from the DeepMind Control Suite, where AltNet outperforms various relevant baseline methods, as well as state-of-the-art reset-based techniques.
Authors: Hetvi Shastri, Pragya Sharma, Walid A. Hanafy, Mani Srivastava, Prashant Shenoy
Abstract: Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs) -- FMs trained on time-series data -- have shown strong performance on classification, regression, and imputation tasks. Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance; however, assembling such pipelines typically requires ad hoc, model-specific implementations that hinder modularity and reproducibility. We introduce FMTK, an open-source, lightweight and extensible toolkit for constructing and fine-tuning TSFM pipelines via standardized backbone and component abstractions. FMTK enables flexible composition across models and tasks, achieving correctness and performance with an average of seven lines of code. https://github.com/umassos/FMTK
Authors: MohammadParsa Dini, Human Jafari, Sajjad Amini, MohammadMahdi Mojahedian
Abstract: Machine Unlearning is essential for large generative models (VAEs, DDPMs) to comply with the right to be forgotten and prevent undesired content generation without costly retraining. Existing approaches, such as Static-lambda SISS for diffusion models, rely on a fixed mixing weight lambda, which is suboptimal because the required unlearning strength varies across samples and training stages. We propose Adaptive-lambda SISS, a principled extension that turns lambda into a latent variable dynamically inferred at each training step. A lightweight inference network parameterizes an adaptive posterior over lambda, conditioned on contextual features derived from the instantaneous SISS loss terms (retain/forget losses and their gradients). This enables joint optimization of the diffusion model and the lambda-inference mechanism via a variational objective, yielding significantly better trade-offs. We further extend the adaptive-lambda principle to score-based unlearning and introduce a multi-class variant of Score Forgetting Distillation. In addition, we present two new directions: (i) a hybrid objective combining the data-free efficiency of Score Forgetting Distillation with the direct gradient control of SISS, and (ii) a Reinforcement Learning formulation that treats unlearning as a sequential decision process, learning an optimal policy over a state space defined by the model's current memory of the forget set. Experiments on an augmented MNIST benchmark show that Adaptive-lambda SISS substantially outperforms the original static-lambda SISS, achieving stronger removal of forgotten classes while better preserving generation quality on the retain set.
Authors: Seokhyun Chin, Junghwan Park, Woojin Cho
Abstract: Precipitation nowcasting, key for early warning of disasters, currently relies on computationally expensive and restrictive methods that limit access to many countries. To overcome this challenge, we propose precipitation nowcasting using satellite imagery with physics constraints for improved accuracy and physical consistency. We use a novel physics-informed dual neural operator (PIANO) structure to enforce the fundamental equation of advection-diffusion during training to predict satellite imagery using a PINN loss. Then, we use a generative model to convert satellite images to radar images, which are used for precipitation nowcasting. Compared to baseline models, our proposed model shows a notable improvement in moderate (4mm/h) precipitation event prediction alongside short-term heavy (8mm/h) precipitation event prediction. It also demonstrates low seasonal variability in predictions, indicating robustness for generalization. This study suggests the potential of the PIANO and serves as a good baseline for physics-informed precipitation nowcasting.
Authors: Taicheng Zheng, Dan Li, Jie Li
Abstract: Multipurpose batch processes become increasingly popular in manufacturing industries since they adapt to low-volume, high-value products and shifting demands. These processes often operate in a dynamic environment, which faces disturbances such as processing delays and demand changes. To minimise long-term cost and system nervousness (i.e., disruptive changes to schedules), schedulers must design rescheduling strategies to address such disturbances effectively. Existing methods often assume complete look-ahead information over the scheduling horizon. This assumption contrasts with realistic situations where schedulers can only access incomplete look-ahead information. Sticking with existing methods may lead to suboptimal long-term costs and high-level system nervousness. In this work we propose a Bayesian dynamic scheduling method. Our method relies on learning a Bayesian Network from the probability distribution of disturbances. Specifically, the Bayesian Network represents how likely each operation will be impacted by disturbances. During the online execution, when new disturbances become observed, this method updates the posterior distribution and therefore guides the rescheduling strategy. We compare our method with the existing periodic rescheduling strategy (which generates new schedules from scratch at fixed intervals) on four benchmark problems. Computational results show that our method achieves statistically better long-term costs and system nervousness. In the theoretical aspect, we prove that if disturbances are mutually independent, the impact-quantifying variables inherently satisfy the independence assumptions required by Bayesian Networks. As an implication, practitioners can extend the method to other scheduling problems (such as job shop scheduling and continuous processes), given that they define the problem-specific dependencies between operations.
Authors: Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang
Abstract: Algorithmic reasoning -- the ability to perform step-by-step logical inference -- has become a core benchmark for evaluating reasoning in graph neural networks (GNNs) and large language models (LLMs). Ideally, one would like to design a single model capable of performing well on multiple algorithmic reasoning tasks simultaneously. However, this is challenging when the execution steps of algorithms differ from one another, causing negative interference when they are trained together. We propose branching neural networks, a principled architecture for multitask algorithmic reasoning. Searching for the optimal $k$-ary tree with $L$ layers over $n$ algorithmic tasks is combinatorial, requiring exploration of up to $k^{nL}$ possible structures. We develop AutoBRANE, an efficient algorithm that reduces this search to $O(nL)$ time by solving a convex relaxation at each layer to approximate an optimal task partition. The method clusters tasks using gradient-based affinity scores and can be used on top of any base model, including GNNs and LLMs. We validate AutoBRANE on a broad suite of graph-algorithmic and text-based reasoning benchmarks. We show that gradient features estimate true task performance within 5% error across four GNNs and four LLMs (up to 34B parameters). On the CLRS benchmark, it outperforms the strongest single multitask GNN by 3.7% and the best baseline by 1.2%, while reducing runtime by 48% and memory usage by 26%. The learned branching structures reveal an intuitively reasonable hierarchical clustering of related algorithms. On three text-based graph reasoning benchmarks, AutoBRANE improves over the best non-branching multitask baseline by 3.2%. Finally, on a large graph dataset with 21M edges and 500 tasks, AutoBRANE achieves a 28% accuracy gain over existing multitask and branching architectures, along with a 4.5$\times$ reduction in runtime.
Authors: Geigh Zollicoffer, Tanush Chopra, Mingkuan Yan, Xiaoxu Ma, Kenneth Eaton, Mark Riedl
Abstract: AI systems deployed in the real world must contend with distractions and out-of-distribution (OOD) noise that can destabilize their policies and lead to unsafe behavior. While robust training can reduce sensitivity to some forms of noise, it is infeasible to anticipate all possible OOD conditions. To mitigate this issue, we develop an algorithm that leverages a world model's inherent measure of surprise to reduce the impact of noise in world model--based reinforcement learning agents. We introduce both multi-representation and single-representation rejection sampling, enabling robustness to settings with multiple faulty sensors or a single faulty sensor. While the introduction of noise typically degrades agent performance, we show that our techniques preserve performance relative to baselines under varying types and levels of noise across multiple environments within self-driving simulation domains (CARLA and Safety Gymnasium). Furthermore, we demonstrate that our methods enhance the stability of two state-of-the-art world models with markedly different underlying architectures: Cosmos and DreamerV3. Together, these results highlight the robustness of our approach across world modeling domains. We release our code at https://github.com/Bluefin-Tuna/WISER .
Authors: Chen Henry Wu, Sachin Goyal, Aditi Raghunathan
Abstract: Parallel sampling promises substantial gains in test-time scaling, but its effectiveness is sharply limited by diversity collapse, where models concentrate on a few modes and repeated samples produce the same mistakes. We propose the mode-conditioning (ModC) framework, which explicitly allocates test-time compute across reasoning modes using either specialist models or mode-specific prefixes. ModC consistently improves scaling across controlled graph-search tasks and large-scale reasoning benchmarks, spanning model families and sizes from 0.5B to 7B. On OpenThoughts, fine-tuning Qwen2.5-7B with ModC achieves a 4x efficiency gain over standard training while also improving the maximum attainable Pass@k. We further show that gradient clustering enables ModC without explicit mode labels, yielding up to 10% gains on datasets such as NuminaMath. Finally, we show that ModC improves reinforcement learning (RL) and can further boost diversity-inducing RL methods. These results demonstrate that standard training underutilizes the diversity in data, and that ModC provides a simple, effective remedy for unlocking the full benefits of diversity in test-time scaling.
Authors: Hamza ElMokhtar Shili, Natasha Patnaik, Isabelle Ruble, Kathryn Jarjoura, Daniel Suarez Aguirre
Abstract: We investigate algorithmic variants of the Frank-Wolfe (FW) optimization method for pruning convolutional neural networks. This is motivated by the "Lottery Ticket Hypothesis", which suggests the existence of smaller sub-networks within larger pre-trained networks that perform comparatively well (if not better). Whilst most literature in this area focuses on Deep Neural Networks more generally, we specifically consider Convolutional Neural Networks for image classification tasks. Building on the hypothesis, we compare simple magnitude-based pruning, a Frank-Wolfe style pruning scheme, and an FW method with momentum on a CNN trained on MNIST. Our experiments track test accuracy, loss, sparsity, and inference time as we vary the dense pre-training budget from 1 to 10 epochs. We find that FW with momentum yields pruned networks that are both sparser and more accurate than the original dense model and the simple pruning baselines, while incurring minimal inference-time overhead in our implementation. Moreover, FW with momentum reaches these accuracies after only a few epochs of pre-training, indicating that full pre-training of the dense model is not required in this setting.
Authors: Konstantin Makarychev, Ilias Papanikolaou, Liren Shan
Abstract: We study the problem of explainable k-medians clustering introduced by Dasgupta, Frost, Moshkovitz, and Rashtchian (2020). In this problem, the goal is to construct a threshold decision tree that partitions data into k clusters while minimizing the k-medians objective. These trees are interpretable because each internal node makes a simple decision by thresholding a single feature, allowing users to trace and understand how each point is assigned to a cluster. We present the first algorithm for explainable k-medians under lp norm for every finite p >= 1. Our algorithm achieves an O(p(log k)^{1 + 1/p - 1/p^2}) approximation to the optimal k-medians cost for any p >= 1. Previously, algorithms were known only for p = 1 and p = 2. For p = 2, our algorithm improves upon the existing bound of O(log^{3/2}k), and for p = 1, it matches the tight bound of log k + O(1) up to a multiplicative O(log log k) factor. We show how to implement our algorithm in a dynamic setting. The dynamic algorithm maintains an explainable clustering under a sequence of insertions and deletions, with amortized update time O(d log^3 k) and O(log k) recourse, making it suitable for large-scale and evolving datasets.
Authors: Dong Liu
Abstract: We propose Fiber Bundle Networks (FiberNet), a novel machine learning framework integrating differential geometry with machine learning. Unlike traditional deep neural networks relying on black-box function fitting, we reformulate classification as interpretable geometric optimization on fiber bundles, where categories form the base space and wavelet-transformed features lie in the fibers above each category. We introduce two innovations: (1) learnable Riemannian metrics identifying important frequency feature components, (2) variational prototype optimization through energy function minimization. Classification is performed via Voronoi tessellation under the learned Riemannian metric, where each prototype defines a decision region and test samples are assigned to the nearest prototype, providing clear geometric interpretability. This work demonstrates that the integration of fiber bundle with machine learning provides interpretability and efficiency, which are difficult to obtain simultaneously in conventional deep learning.
Authors: Shravan Chaudhari, Yoav Wald, Suchi Saria
Abstract: As we deploy machine learning systems in the real world, a core challenge is to maintain a model that is performant even as the data shifts. Such shifts can take many forms: new classes may emerge that were absent during training, a problem known as open-set recognition, and the distribution of known categories may change. Guarantees on open-set recognition are mostly derived under the assumption that the distribution of known classes, which we call \emph{the background distribution}, is fixed. In this paper we develop \ours{}, a method that is guaranteed to solve open-set recognition even in the challenging case where the background distribution shifts. We prove that the method works under benign assumptions that the novel class is separable from the non-novel classes, and provide theoretical guarantees that it outperforms a representative baseline in a simplified overparameterized setting. We develop techniques to make \ours{} scalable and robust, and perform comprehensive empirical evaluations on image and text data. The results show that \ours{} significantly outperforms existing open-set recognition methods under background shift. Moreover, we provide new insights into how factors such as the size of the novel class influences performance, an aspect that has not been extensively explored in prior work.
Authors: Ahmad Ali
Abstract: Density Functional Theory (DFT) is a widely used computational method for estimating the energy and behavior of molecules. Machine Learning Interatomic Potentials (MLIPs) are models trained to approximate DFT-level energies and forces at dramatically lower computational cost. Many modern MLIPs rely on a scalar regression formulation; given information about a molecule, they predict a single energy value and corresponding forces while minimizing absolute error with DFT's calculations. In this work, we explore a multi-class classification formulation that predicts a categorical distribution over energy/force values, providing richer supervision through multiple targets. Most importantly, this approach offers a principled way to quantify model uncertainty. In particular, our method predicts a histogram of the energy/force distribution, converts scalar targets into histograms, and trains the model using cross-entropy loss. Our results demonstrate that this categorical formulation can achieve absolute error performance comparable to regression baselines. Furthermore, this representation enables the quantification of epistemic uncertainty through the entropy of the predicted distribution, offering a measure of model confidence absent in scalar regression approaches.
Authors: Soumyadeep Chandra, Sayeed Shafayet Chowdhury, Kaushik Roy
Abstract: Thermal analysis is increasingly critical in modern integrated circuits, where non-uniform power dissipation and high transistor densities can cause rapid temperature spikes and reliability concerns. Traditional methods, such as FEM-based simulations offer high accuracy but computationally prohibitive for early-stage design, often requiring multiple iterative redesign cycles to resolve late-stage thermal failures. To address these challenges, we propose 'ThermAl', a physics-informed generative AI framework which effectively identifies heat sources and estimates full-chip transient and steady-state thermal distributions directly from input activity profiles. ThermAl employs a hybrid U-Net architecture enhanced with positional encoding and a Boltzmann regularizer to maintain physical fidelity. Our model is trained on an extensive dataset of heat dissipation maps, ranging from simple logic gates (e.g., inverters, NAND, XOR) to complex designs, generated via COMSOL. Experimental results demonstrate that ThermAl delivers precise temperature mappings for large circuits, with a root mean squared error (RMSE) of only 0.71{\deg}C, and outperforms conventional FEM tools by running up to ~200 times faster. We analyze performance across diverse layouts and workloads, and discuss its applicability to large-scale EDA workflows. While thermal reliability assessments often extend beyond 85{\deg}C for post-layout signoff, our focus here is on early-stage hotspot detection and thermal pattern learning. To ensure generalization beyond the nominal operating range 25-55{\deg}C, we additionally performed cross-validation on an extended dataset spanning 25-95{\deg}C maintaining a high accuracy (<2.2% full-scale RMSE) even under elevated temperature conditions representative of peak power and stress scenarios.
Authors: Mohamed Abdallah Salem (North Dakota State University), Manuel Cuevas Perez (North Dakota State University), Ahmed Harb Rabia (North Dakota State University)
Abstract: This study presents a reinforcement learning (RL)-based control strategy for adaptive lighting regulation in controlled environments using a low-power microcontroller. A model-free Q-learning algorithm was implemented to dynamically adjust the brightness of a Light-Emitting Diode (LED) based on real-time feedback from a light-dependent resistor (LDR) sensor. The system was trained to stabilize at 13 distinct light intensity levels (L1 to L13), with each target corresponding to a specific range within the 64-state space derived from LDR readings. A total of 130 trials were conducted, covering all target levels with 10 episodes each. Performance was evaluated in terms of convergence speed, steps taken, and time required to reach target states. Box plots and histograms were generated to analyze the distribution of training time and learning efficiency across targets. Experimental validation demonstrated that the agent could effectively learn to stabilize at varying light levels with minimal overshooting and smooth convergence, even in the presence of environmental perturbations. This work highlights the feasibility of lightweight, on-device RL for energy-efficient lighting control and sets the groundwork for multi-modal environmental control applications in resource-constrained agricultural systems.
Authors: Yuxuan Bao, J. Nathan Kutz
Abstract: The requirements of modern sensing are rapidly evolving, driven by increasing demands for data efficiency, real-time processing, and deployment under limited sensing coverage. Complex physical systems are often characterized through the integration of a limited number of point sensors in combination with scientific computations which approximate the dominant, full-state dynamics. Simulation models, however, inevitably neglect small-scale or hidden processes, are sensitive to perturbations, or oversimplify parameter correlations, leading to reconstructions that often diverge from the reality measured by sensors. This creates a critical need for data assimilation, the process of integrating observational data with predictive simulation models to produce coherent and accurate estimates of the full state of complex physical systems. We propose a machine learning framework for Data Assimilation with a SHallow REcurrent Decoder (DA-SHRED) which bridges the simulation-to-real (SIM2REAL) gap between computational modeling and experimental sensor data. For real-world physics systems modeling high-dimensional spatiotemporal fields, where the full state cannot be directly observed and must be inferred from sparse sensor measurements, we leverage the latent space learned from a reduced simulation model via SHRED, and update these latent variables using real sensor data to accurately reconstruct the full system state. Furthermore, our algorithm incorporates a sparse identification of nonlinear dynamics based regression model in the latent space to identify functionals corresponding to missing dynamics in the simulation model. We demonstrate that DA-SHRED successfully closes the SIM2REAL gap and additionally recovers missing dynamics in highly complex systems, demonstrating that the combination of efficient temporal encoding and physics-informed correction enables robust data assimilation.
Authors: Andrew Du, Roberto Del Prete, Alejandro Mousist, Nick Manser, Fabrice Marre, Andrew Barton, Carl Seubert, Gabriele Meoni, Tat-Jun Chin
Abstract: Geospatial foundation models (GeoFMs) promise broad generalisation capacity for Earth observation (EO) tasks, particularly under data-limited conditions. However, their large size poses a barrier to deployment on resource-constrained space hardware. To address this, we present compact variants of a Vision Transformer (ViT)-based GeoFM that preserve downstream task performance while enabling onboard execution. Evaluation across five downstream tasks and validation in two representative flight environments show that model compression and domain adaptation are critical to reducing size and resource demands while maintaining high performance under operational conditions. We further demonstrate reliable on-orbit inference with the IMAGIN-e payload aboard the International Space Station. These results establish a pathway from large GeoFMs to flight-ready, resource-efficient deployments, expanding the feasibility of onboard AI for EO missions.
Authors: Harshil Vejendla
Abstract: Transformer models often exhibit brittle extrapolation, failing on inputs that are longer or structurally more complex than those seen during training. We introduce Counter-Example-Driven Curricula (CEDC), an automated framework that improves model robustness by iteratively focusing on its own failures. At each step, CEDC uses the current model to generate a diverse set of candidate problems, employs a fast, executable verifier to identify incorrect predictions (counter-examples), and then fine-tunes the model on a dataset enriched with these discovered failures. We evaluate CEDC on a suite of algorithmic and natural language tasks, including integer addition, sorting, Dyck-2 language recognition, and three text classification benchmarks. Compared to static training and standard curriculum learning baselines, CEDC achieves up to 30x greater length extrapolation, is 3.75x more computationally efficient than uniform data augmentation, and requires no manual difficulty heuristics. We provide a detailed analysis of the counter-examples, showing how the curriculum naturally adapts to target progressively more complex error modes. Our findings establish verifier-guided, failure-driven learning as a simple, powerful, and efficient paradigm for enhancing the generalization capabilities of Transformer models.
Authors: Nagham Osman, Keyue Jiang, Davide Buffelli, Xiaowen Dong, Laura Toni
Abstract: Graph generation is a critical task across scientific domains. Existing methods fall broadly into two categories: autoregressive models, which iteratively expand graphs, and one-shot models, such as diffusion, which generate the full graph at once. In this work, we provide an analysis of these two paradigms and reveal a key trade-off: autoregressive models stand out in capturing fine-grained local structures, such as degree and clustering properties, whereas one-shot models excel at modeling global patterns, such as spectral distributions. Building on this, we propose LGDC (latent graph diffusion via spectrum-preserving coarsening), a hybrid framework that combines strengths of both approaches. LGDC employs a spectrum-preserving coarsening-decoarsening to bidirectionally map between graphs and a latent space, where diffusion efficiently generates latent graphs before expansion restores detail. This design captures both local and global properties with improved efficiency. Empirically, LGDC matches autoregressive models on locally structured datasets (Tree) and diffusion models on globally structured ones (Planar, Community-20), validating the benefits of hybrid generation.
Authors: Shihang Li, Zhiqiang Gong, Weien Zhou, Yue Gao, Wen Yao
Abstract: Accurate reconstruction of temperature field of heat-source systems (TFR-HSS) is crucial for thermal monitoring and reliability assessment in engineering applications such as electronic devices and aerospace structures. However, the high cost of measurement acquisition and the substantial distributional shifts in temperature field across varying conditions present significant challenges for developing reconstruction models with robust generalization capabilities. Existing DNNs-based methods typically formulate TFR-HSS as a one-to-one regression problem based solely on target sparse measurements, without effectively leveraging reference simulation data that implicitly encode thermal knowledge. To address this limitation, we propose IPTR, an implicit physics-guided temperature field reconstruction framework that introduces sparse monitoring-temperature field pair from reference simulations as priors to enrich physical understanding. To integrate both reference and target information, we design a dual physics embedding module consisting of two complementary branches: an implicit physics-guided branch employing cross-attention to distill latent physics from the reference data, and an auxiliary encoding branch based on Fourier layers to capture the spatial characteristics of the target observation. The fused representation is then decoded to reconstruct the full temperature field. Extensive experiments under single-condition, multi-condition, and few-shot settings demonstrate that IPTR consistently outperforms existing methods, achieving state-of-the-art reconstruction accuracy and strong generalization capability.
Authors: Vinam Arora, Divyansha Lachi, Ian J. Knight, Mehdi Azabou, Blake Richards, Cole L. Hurwitz, Josh Siegle, Eva L. Dyer
Abstract: Neurons process information in ways that depend on their cell type, connectivity, and the brain region in which they are embedded. However, inferring these factors from neural activity remains a significant challenge. To build general-purpose representations that allow for resolving information about a neuron's identity, we introduce NuCLR, a self-supervised framework that aims to learn representations of neural activity that allow for differentiating one neuron from the rest. NuCLR brings together views of the same neuron observed at different times and across different stimuli and uses a contrastive objective to pull these representations together. To capture population context without assuming any fixed neuron ordering, we build a spatiotemporal transformer that integrates activity in a permutation-equivariant manner. Across multiple electrophysiology and calcium imaging datasets, a linear decoding evaluation on top of NuCLR representations achieves a new state-of-the-art for both cell type and brain region decoding tasks, and demonstrates strong zero-shot generalization to unseen animals. We present the first systematic scaling analysis for neuron-level representation learning, showing that increasing the number of animals used during pretraining consistently improves downstream performance. The learned representations are also label-efficient, requiring only a small fraction of labeled samples to achieve competitive performance. These results highlight how large, diverse neural datasets enable models to recover information about neuron identity that generalize across animals. Code is available at https://github.com/nerdslab/nuclr.
Authors: Yujie Huang, Haibin Wan, Xiangcheng Li, Tuanfa Qin, Yun Li, Jun Li, Wen Chen
Abstract: With the rapid advances in programmable materials, reconfigurable intelligent surfaces (RIS) have become a pivotal technology for future wireless communications. The simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) can both transmit and reflect signals, enabling comprehensive signal control and expanding application scenarios. This paper introduces an unmanned aerial vehicle (UAV) to further enhance system flexibility and proposes an optimization design for the spectrum efficiency of the STAR-RIS-UAV-assisted wireless communication system. We present a deep reinforcement learning (DRL) algorithm capable of iteratively optimizing beamforming, phase shifts, and UAV positioning to maximize the system's sum rate through continuous interactions with the environment. To improve exploration in deterministic policies, we introduce a stochastic perturbation factor, which enhances exploration capabilities. As exploration is strengthened, the algorithm's ability to accurately evaluate the state-action value function becomes critical. Thus, based on the deep deterministic policy gradient (DDPG) algorithm, we propose a convolution-augmented deep deterministic policy gradient (CA-DDPG) algorithm that balances exploration and evaluation to improve the system's sum rate. The simulation results demonstrate that the CA-DDPG algorithm effectively interacts with the environment, optimizing the beamforming matrix, phase shift matrix, and UAV location, thereby improving system capacity and achieving better performance than other algorithms.
Authors: Wen Zhao, Jiawen Ding, Xueting Huang, Yibo Zhang
Abstract: In the context of intelligent manufacturing, this paper conducts a series of experimental studies on the predictive maintenance of industrial milling machine equipment based on the AI4I 2020 dataset. This paper proposes a complete predictive maintenance experimental process combining artificial intelligence technology, including six main links: data preprocessing, model training, model evaluation, model selection, SHAP analysis, and result visualization. By comparing and analyzing the performance of eight machine learning models, it is found that integrated learning methods such as XGBoost and random forest perform well in milling machine fault prediction tasks. In addition, with the help of SHAP analysis technology, the influence mechanism of different features on equipment failure is deeply revealed, among which processing temperature, torque and speed are the key factors affecting failure. This study combines artificial intelligence and manufacturing technology, provides a methodological reference for predictive maintenance practice in an intelligent manufacturing environment, and has practical significance for promoting the digital transformation of the manufacturing industry, improving production efficiency and reducing maintenance costs.
Authors: Alper Y{\i}ld{\i}r{\i}m, \.Ibrahim Y\"uceda\u{g}
Abstract: Standard Transformers suffer from a "Semantic Alignment Tax", a prohibitive optimization cost required to organize a chaotic initialization into a coherent geometric map via local gradient diffusion. We hypothesize that this reliance on diffusive learning creates "Catastrophic Rigidity", rendering models unable to adapt to novel concepts without destroying their pre-trained reasoning capabilities. To isolate this phenomenon, we introduce Iterative Semantic Map Refinement (ISMR), a diagnostic protocol revealing that alignment is a fixed geometric barrier that scaling cannot solve; a 20-layer model overcomes this barrier no faster than a 1-layer model. We introduce the Phase-Resonant Intelligent Spectral Model (PRISM). PRISM encodes semantic identity as resonant frequencies in the complex domain (C^d) and replaces quadratic self-attention with linearithmic O(N log N) Gated Harmonic Convolutions. We validate PRISM on the WMT14 translation task. While the Standard Transformer maintains a slight edge in general competence on static benchmarks (23.88 vs 21.40 BLEU), it fails the "Plasticity-Stability" stress test completely. When injected with novel concepts, the Transformer suffers Catastrophic Forgetting, degrading by -10.55 BLEU points while achieving only 60% acquisition. In contrast, PRISM demonstrates Lossless Plasticity, achieving 96% 5-shot acquisition with negligible degradation (-0.84 BLEU). These results suggest that harmonic representations effectively decouple memory from reasoning, offering a structural solution to the plasticity-stability dilemma in real-time knowledge adaptation.
Authors: Xuanyi Zhao, Jiawen Ding, Xueting Huang, Yibo Zhang
Abstract: With the rapid development of electricity markets, price volatility has significantly increased, making accurate forecasting crucial for power system operations and market decisions. Traditional linear models cannot capture the complex nonlinear characteristics of electricity pricing, necessitating advanced machine learning approaches. This study compares eight machine learning models using Spanish electricity market data, integrating consumption, generation, and meteorological variables. The models evaluated include linear regression, ridge regression, decision tree, KNN, random forest, gradient boosting, SVR, and XGBoost. Results show that KNN achieves the best performance with R^2 of 0.865, MAE of 3.556, and RMSE of 5.240. To enhance interpretability, LIME analysis reveals that meteorological factors and supply-demand indicators significantly influence price fluctuations through nonlinear relationships. This work demonstrates the effectiveness of machine learning models in electricity price forecasting while improving decision transparency through interpretability analysis.
Authors: Xuezhi Liu
Abstract: Optimal Power Flow (OPF) is a core optimization problem in power system operation and planning, aiming to minimize generation costs while satisfying physical constraints such as power flow equations, generator limits, and voltage limits. Traditional OPF solving methods typically employ iterative optimization algorithms (such as interior point methods, sequential quadratic programming, etc.), with limitations including low computational efficiency, initial value sensitivity, and low batch computation efficiency. Most existing deep learning-based OPF methods rely on supervised learning, requiring pre-solving large numbers of cases, and have difficulty guaranteeing physical consistency. This paper proposes an Optimal Power Flow solving method based on neural network dynamics and energy gradient flow, transforming OPF problems into energy minimization problems. By constructing an energy function to measure the degree of deviation from the constraint manifold, and guiding networks to learn optimal solutions that simultaneously satisfy power flow constraints and minimize costs through gradient flow. Neural networks are trained unsupervised by directly minimizing physical residuals, requiring no labeled data, achieving true "end-to-end" physics-constrained learning.
Authors: Ruixiang Feng, Zhenwei An, Yuntao Wen, Ran Le, Yiming Jia, Chen Yang, Zongchao Chen, Lisi Chen, Shen Gao, Shuo Shang, Yang Song, Tao Zhang
Abstract: Answer verification methods are widely employed in language model training pipelines spanning data curation, evaluation, and reinforcement learning with verifiable rewards (RLVR). While prior work focus on developing unified verifiers applicable across multiple reasoning scenarios, significant challenges remain in computation-oriented scientific domains, such as algebraic equivalence checking and physical constant substitution. In this paper, we introduce \model, a tool-augmented verifier that leverages external executors to perform precise computations and symbolic simplifications. \model enables robust verification that goes beyond simple semantic matching. We propose a novel two-stage pipeline, which begin with cold-start fine-tuning and followed by multi-turn reinforcement learning with tool integration. Extensive experiments conducted on STEM subjects, general QA, and long-form reasoning tasks demonstrates strong generalization of \model. The results shows that the \model achieves state-of-the-art performance on VerifyBench-Hard and SCI-Bench. And we also employ our \model in RLVR as a reward model, the results show that it consistently outperforms both rubric-based and model-based verifiers on AIME'24 and AIME'25, demonstrating strong potential to enhance reasoning capabilities of LLM. Our model is released at \hyperlink{https://huggingface.co/Nanbeige/CoSineVerifier-Tool-4B}{https://huggingface.co/Nanbeige/CoSineVerifier-Tool-4B}.
URLs: https://huggingface.co/Nanbeige/CoSineVerifier-Tool-4B, https://huggingface.co/Nanbeige/CoSineVerifier-Tool-4B
Authors: Haoran Li, Jiayu Lv, Congying Han, Zicheng Zhang, Anqi Li, Yan Liu, Tiande Guo, Nan Jiang
Abstract: Achieving optimality and adversarial robustness in deep reinforcement learning has long been regarded as conflicting goals. Nonetheless, recent theoretical insights presented in CAR suggest a potential alignment, raising the important question of how to realize this in practice. This paper first identifies a key gap between theory and practice by comparing standard policy optimization (SPO) and adversarially robust policy optimization (ARPO). Although they share theoretical consistency, a fundamental tension between robustness and optimality arises in practical policy gradient methods. SPO tends toward convergence to vulnerable first-order stationary policies (FOSPs) with strong natural performance, whereas ARPO typically favors more robust FOSPs at the expense of reduced returns. Furthermore, we attribute this tradeoff to the reshaping effect of the strongest adversary in ARPO, which significantly complicates the global landscape by inducing deceptive sticky FOSPs. This improves robustness but makes navigation more challenging. To alleviate this, we develop the BARPO, a bilevel framework unifying SPO and ARPO by modulating adversary strength, thereby facilitating navigability while preserving global optima. Extensive empirical results demonstrate that BARPO consistently outperforms vanilla ARPO, providing a practical approach to reconcile theoretical and empirical performance.
Authors: Yahui Liu, Yang Yue, Jingyuan Zhang, Chenxi Sun, Yang Zhou, Wencong Zeng, Ruiming Tang, Guorui Zhou
Abstract: Recent efforts on Diffusion Mixture-of-Experts (MoE) models have primarily focused on developing more sophisticated routing mechanisms. However, we observe that the underlying architectural configuration space remains markedly under-explored. Inspired by the MoE design paradigms established in large language models (LLMs), we identify a set of crucial architectural factors for building effective Diffusion MoE models--including DeepSeek-style expert modules, alternative intermediate widths, varying expert counts, and enhanced attention positional encodings. Our systematic study reveals that carefully tuning these configurations is essential for unlocking the full potential of Diffusion MoE models, often yielding gains that exceed those achieved by routing innovations alone. Through extensive experiments, we present novel architectures that can be efficiently applied to both latent and pixel-space diffusion frameworks, which provide a practical and efficient training recipe that enables Diffusion MoE models to surpass strong baselines while using equal or fewer activated parameters. All code and models are publicly available at: https://github.com/yhlleo/EfficientMoE.
Authors: Berivan Isik, Matthew Fahrbach, Dima Kuzmin, Nicolas Mayoraz, Emil Praun, Steffen Rendle, Raghavendra Vasudeva
Abstract: Online learning is the cornerstone of applications like recommendation and advertising systems, where models continuously adapt to shifting data distributions. Model training for such systems is remarkably expensive, a cost that multiplies during hyperparameter search. We introduce a two-stage paradigm to reduce this cost: (1) efficiently identifying the most promising configurations, and then (2) training only these selected candidates to their full potential. Our core insight is that focusing on accurate identification in the first stage, rather than achieving peak performance, allows for aggressive cost-saving measures. We develop novel data reduction and prediction strategies that specifically overcome the challenges of sequential, non-stationary data not addressed by conventional hyperparameter optimization. We validate our framework's effectiveness through a dual evaluation: first on the Criteo 1TB dataset, the largest suitable public benchmark, and second on an industrial advertising system operating at a scale two orders of magnitude larger. Our methods reduce the total hyperparameter search cost by up to 10$\times$ on the public benchmark and deliver significant, validated efficiency gains in the industrial setting.
Authors: Yilong Zhao, Jiaming Tang, Kan Zhu, Zihao Ye, Chi-Chih Chang, Chaofan Lin, Jongseok Park, Guangxuan Xiao, Mohamed S. Abdelfattah, Mingyu Gao, Baris Kasikci, Song Han, Ion Stoica
Abstract: Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to memory-bound. To generate each token, the model applies full attention to all previously generated tokens, requiring memory access to an increasingly large KV-Cache. Consequently, longer generations demand more memory access for every step, leading to substantial pressure on memory bandwidth. To address this, we introduce SparseSpec, a speculative decoding framework that reuses the same model as the draft and target models (i.e., self-speculation). SparseSpec features a novel sparse attention mechanism, PillarAttn, as the draft model, which accurately selects critical tokens via elegantly reusing information from the verification stage. Furthermore, SparseSpec co-designs self-speculation with three system innovations: (1) a unified scheduler to batch token drafting and verification, (2) delayed verification for CPU/GPU overlap, and (3) dynamic KV-Cache management to maximize memory utilization. Across various models and datasets, SparseSpec outperforms state-of-the-art solutions, with an up to 2.13x throughput speedup.
Authors: Mudit Gaur, Prashant Trivedi, Shuchin Aeron, Amrit Singh Bedi, George K. Atia, Vaneet Aggarwal
Abstract: Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing empirical success, the theoretical understanding of flow matching remains limited, particularly in terms of sample complexity results. In this work, we provide the first analysis of the sample complexity for flow-matching based generative models without assuming access to the empirical risk minimizer (ERM) of the loss function for estimating the velocity field. Under standard assumptions on the loss function for velocity field estimation and boundedness of the data distribution, we show that a sufficiently expressive neural network can learn a velocity field such that with $\mathcal{O}(\epsilon^{-4})$ samples, such that the Wasserstein-2 distance between the learned and the true distribution is less than $\mathcal{O}(\epsilon)$. The key technical idea is to decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field. Each of these terms are then handled via techniques that may be of independent interest.
Authors: Dmitry Zankov, Pavlo Polishchuk, Michal Sobieraj, Mario Barbatti
Abstract: We introduce milearn, a Python package for multi-instance learning (MIL) that follows the familiar scikit-learn fit/predict interface while providing a unified framework for both classical and neural-network-based MIL algorithms for regression and classification. The package also includes built-in hyperparameter optimization designed specifically for small MIL datasets, enabling robust model selection in data-scarce scenarios. We demonstrate the versatility of milearn across a broad range of synthetic MIL benchmark datasets, including digit classification and regression, molecular property prediction, and protein-protein interaction (PPI) prediction. Special emphasis is placed on the key instance detection (KID) problem, for which the package provides dedicated support.
Authors: Shashank Landge, Abhishek Patil, Tejas kamble, Bhushan Buddhivant, Priyanka Joshi
Abstract: As Large Language Models (LLMs) continue to scale in parameter count, deploying them on commodity hardware has become increasingly challenging. Post-Training Quantization (PTQ) addresses this by reducing the precision of model weights, typically to 4-bit or lower. However, uniform quantization often leads to significant performance degradation due to the presence of ``outlier features'' -- weights that, while few in number, are critical for maintaining model accuracy. Current state-of-the-art methods such as AWQ (Activation-aware Weight Quantization) and SpQR (Sparse Quantization Representations) rely on calibration data to identify these salient weights via activation magnitudes or Hessian sensitivity. In scenarios where data privacy is paramount or calibration data is unavailable, these methods are inapplicable. In this work, we propose a data-free, structure-aware hypothesis: that the weights identified as Principal Components via Singular Value Decomposition (SVD) are intrinsically important to the model's downstream performance. We introduce a novel selection heuristic that preserves the top-$k$ weights aligned with the principal components in FP32, while aggressively quantizing the residual weights. We compare our method against activation-aware (AWQ) and second-order (SpQR) methods across GLUE benchmarks (MRPC, RTE, QNLI) using a DistilBERT backbone. Our experiments reveal that structural importance is highly correlated with functional importance. On the challenging RTE task, our SVD-based method achieves an accuracy of 66.06\%, outperforming both AWQ (65.34\%) and SpQR (65.34\%) at high protection budgets, validating that intrinsic matrix structure can serve as a robust proxy for weight saliency without the need for forward passes or calibration data.
Authors: Yanlin Wang, Nancy M Young, Patrick C M Wong
Abstract: Neural prediction offers a promising approach to forecasting the individual variability of neurocognitive functions and disorders and providing prognostic indicators for personalized invention. However, it is challenging to translate neural predictive models into medical artificial intelligent applications due to the limitations of domain shift and label scarcity. Here, we propose the directed evolution model (DEM), a novel computational model that mimics the trial-and-error processes of biological directed evolution to approximate optimal solutions for predictive modeling tasks. We demonstrated that the directed evolution algorithm is an effective strategy for uncertainty exploration, enhancing generalization in reinforcement learning. Furthermore, by incorporating replay buffer and continual backpropagate methods into DEM, we provide evidence of achieving better trade-off between exploitation and exploration in continuous learning settings. We conducted experiments on four different datasets for children with cochlear implants whose spoken language developmental outcomes vary considerably on the individual-child level. Preoperative neural MRI data has shown to accurately predict the post-operative outcome of these children within but not across datasets. Our results show that DEM can efficiently improve the performance of cross-domain pre-implantation neural predictions while addressing the challenge of label scarcity in target domain.
Authors: Xinyu Jiang, Cuiyun Gao, Wenda Huang, Yiyang Jiang, Binwen Luo, Yuxin Jiang, Mengting Wang, Haoran Wen, Yang Zhao, Xuemei Chen, Songqun Huang
Abstract: Background: Impairment of visual spatial cognitive function is the most common early clinical manifestation of Alzheimer's Disease (AD). When the Montreal Cognitive Assessment (MoCA) uses the "0/1" binary method ("pass/fail") to evaluate the visual spatial cognitive ability represented by the Cube Copying Test(CCT), the elder with less formal education generally score 0 point, resulting in serious bias in the evaluation results. Therefore, this study proposes a fine evaluation method for CCT based on dynamic handwriting feature extraction of DH-SCSM-BLA. method : The Cogni-CareV3.0 software independently developed by our team was used to collect dynamic handwriting data of CCT. Then, the spatial and motion features of segmented dynamic handwriting were extracted, and feature matrix with unequal dimensions were normalized. Finally, a bidirectional long short-term memory network model combined with attention mechanism (BiLSTM-Attention) was adopted for classification. Result: The experimental results showed that: The proposed method has significant superiority compared to similar studies, with a classification accuracy of 86.69%. The distribution of cube drawing ability scores has significant regularity for three aspects such as MCI patients and healthy control group, age, and levels of education. It was also found that score for each cognitive task including cube drawing ability score is negatively correlated with age. Score for each cognitive task including cube drawing ability score, but positively correlated with levels of education significantly. Conclusion: This study provides a relatively objective and comprehensive evaluation method for early screening and personalized intervention of visual spatial cognitive impairment.
Authors: Medha Sawhney, Abhilash Neog, Mridul Khurana, Anuj Karpatne
Abstract: Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routines that use PDE residuals for loss guidance. They additionally suffer from optimization instabilities and are unable to dynamically adapt their inference scheme in the presence of noisy PDE residuals. To address these limitations, we introduce PRISMA (PDE Residual Informed Spectral Modulation with Attention), a conditional diffusion neural operator that embeds PDE residuals directly into the model's architecture via attention mechanisms in the spectral domain, enabling gradient-descent free inference. In contrast to previous methods that use PDE loss solely as external optimization targets, PRISMA integrates PDE residuals as integral architectural features, making it inherently fast, robust, accurate, and free from sensitive hyperparameter tuning. We show that PRISMA has competitive accuracy, at substantially lower inference costs, compared to previous methods across five benchmark PDEs, especially with noisy observations, while using 10x to 100x fewer denoising steps, leading to 15x to 250x faster inference.
Authors: Chujie Zheng, Kai Dang, Bowen Yu, Mingze Li, Huiqiang Jiang, Junrong Lin, Yuqiong Liu, An Yang, Jingren Zhou, Junyang Lin
Abstract: This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy gradient methods such as REINFORCE. Specifically, through a first-order approximation, we show that this surrogate becomes increasingly valid only when both the training-inference discrepancy and policy staleness are minimized. This insight provides a principled explanation for the crucial role of several widely adopted techniques in stabilizing RL training, including importance sampling correction, clipping, and particularly Routing Replay for Mixture-of-Experts (MoE) models. Through extensive experiments with a 30B MoE model totaling hundreds of thousands of GPU hours, we show that for on-policy training, the basic policy gradient algorithm with importance sampling correction achieves the highest training stability. When off-policy updates are introduced to accelerate convergence, combining clipping and Routing Replay becomes essential to mitigate the instability caused by policy staleness. Notably, once training is stabilized, prolonged optimization consistently yields comparable final performance regardless of cold-start initialization. We hope that the shared insights and the developed recipes for stable RL training will facilitate future research.
Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh
Abstract: We present CLAPS, a posterior-aware conformal regression method that pairs a Last-Layer Laplace Approximation with split-conformal calibration. From the resulting Gaussian posterior, CLAPS defines a simple two-sided posterior CDF score that aligns the conformity metric with the full predictive shape, not just a point estimate. This alignment yields narrower prediction intervals at the same target coverage, especially on small to medium tabular datasets where data are scarce and uncertainty modeling matters. We also provide a lightweight diagnostic suite that separates aleatoric and epistemic components and visualizes posterior behavior, helping practitioners understand why intervals shrink when they do. Across multiple benchmarks using the same MLP backbone, CLAPS consistently attains nominal coverage with improved efficiency and minimal overhead, offering a clear, practical upgrade to residual-based conformal baselines.
Authors: Haoyu Lei, Chin Wa Lau, Kaiwen Zhou, Nian Guo, Farzan Farnia
Abstract: Error Correction Codes (ECC) are fundamental to reliable digital communication, yet designing neural decoders that are both accurate and computationally efficient remains challenging. Recent denoising diffusion decoders with transformer backbones achieve state-of-the-art performance, but their iterative sampling limits practicality in low-latency settings. We introduce the Error Correction Consistency Flow Model (ECCFM), an architecture-agnostic training framework for high-fidelity one-step decoding. By casting the reverse denoising process as a Probability Flow Ordinary Differential Equation (PF-ODE) and enforcing smoothness through a differential time regularization, ECCFM learns to map noisy signals along the decoding trajectory directly to the original codeword in a single inference step. Across multiple decoding benchmarks, ECCFM attains lower bit-error rates (BER) than autoregressive and diffusion-based baselines, with notable improvements on longer codes, while delivering inference speeds up from 30x to 100x faster than denoising diffusion decoders.
Authors: Ali Forootani, Mohammad Sadr, Danial Esmaeili Aliabadi, Daniela Thraen
Abstract: Energy system models are increasingly employed to guide long-term planning in multi-sectoral environments where decisions span electricity, heat, transport, land use, and industry. While these models provide rigorous quantitative insights, their outputs are often highly technical, making them difficult to interpret for non-expert stakeholders such as policymakers, planners, and the public. This communication gap limits the accessibility and practical impact of scenario-based modeling, particularly as energy transitions grow more complex with rising shares of renewables, sectoral integration, and deep uncertainties. To address this challenge, we propose the Renewable Energy Large Language Model (RE-LLM), a hybrid framework that integrates Large Language Models (LLMs) directly into the energy system modeling workflow. RE-LLM combines three core elements: (i) optimization-based scenario exploration, (ii) machine learning surrogates that accelerate computationally intensive simulations, and (iii) LLM-powered natural language generation that translates complex results into clear, stakeholder-oriented explanations. This integrated design not only reduces computational burden but also enhances inter-pretability, enabling real-time reasoning about trade-offs, sensitivities, and policy implications. The framework is adaptable across different optimization platforms and energy system models, ensuring broad applicability beyond the case study presented. By merging speed, rigor, and interpretability, RE-LLM advances a new paradigm of human-centric energy modeling. It enables interactive, multilingual, and accessible engagement with future energy pathways, ultimately bridging the final gap between data-driven analysis and actionable decision-making for sustainable transitions.
Authors: Paula Harder, Christian Lessig, Matthew Chantry, Francis Pelletier, David Rolnick
Abstract: Deep learning offers promising capabilities for the statistical downscaling of climate and weather forecasts, with generative approaches showing particular success in capturing fine-scale precipitation patterns. However, most existing models are region-specific, and their ability to generalize to unseen geographic areas remains largely unexplored. In this study, we evaluate the generalization performance of generative downscaling models across diverse regions. Using a global framework, we employ ERA5 reanalysis data as predictors and IMERG precipitation estimates at $0.1^\circ$ resolution as targets. A hierarchical location-based data split enables a systematic assessment of model performance across 15 regions around the world.
Authors: Benjamin Ramtoula, Pierre-Yves Lajoie, Paul Newman, Daniele De Martini
Abstract: Foundation models (FMs) trained with different objectives and data learn diverse representations, making some more effective than others for specific downstream tasks. Existing adaptation strategies, such as parameter-efficient fine-tuning, focus on individual models and do not exploit the complementary strengths across models. Probing methods offer a promising alternative by extracting information from frozen models, but current techniques do not scale well with large feature sets and often rely on dataset-specific hyperparameter tuning. We propose Combined backBones (ComBo), a simple and scalable probing-based adapter that effectively integrates features from multiple models and layers. ComBo compresses activations from layers of one or more FMs into compact token-wise representations and processes them with a lightweight transformer for task-specific prediction. Crucially, ComBo does not require dataset-specific tuning or backpropagation through the backbone models. However, not all models are equally relevant for all tasks. To address this, we introduce a mechanism that leverages ComBo's joint multi-backbone probing to efficiently evaluate each backbone's task-relevance, enabling both practical model comparison and improved performance through selective adaptation. On the 19 tasks of the VTAB-1k benchmark, ComBo outperforms previous probing methods, matches or surpasses more expensive alternatives, such as distillation-based model merging, and enables efficient probing of tuned models. Our results demonstrate that ComBo offers a practical and general-purpose framework for combining diverse representations from multiple FMs.
Authors: Ziqian Wang, Yuxiao Cheng, Jinli Suo
Abstract: Explainability is essential for neural networks that model long time series, yet most existing explainable AI methods only produce point-wise importance scores and fail to capture temporal structures such as trends, cycles, and regime changes. This limitation weakens human interpretability and trust in long-horizon models. To address these issues, we identify four key requirements for interpretable time-series modeling: temporal continuity, pattern-centric explanation, causal disentanglement, and faithfulness to the model's inference process. We propose EXCAP, a unified framework that satisfies all four requirements. EXCAP combines an attention-based segmenter that extracts coherent temporal patterns, a causally structured decoder guided by a pre-trained causal graph, and a latent aggregation mechanism that enforces representation stability. Our theoretical analysis shows that EXCAP provides smooth and stable explanations over time and is robust to perturbations in causal masks. Extensive experiments on classification and forecasting benchmarks demonstrate that EXCAP achieves strong predictive accuracy while generating coherent and causally grounded explanations. These results show that EXCAP offers a principled and scalable approach to interpretable modeling of long time series with relevance to high-stakes domains such as healthcare and finance.
Authors: Valentin Duruisseaux, Jean Kossaifi, Anima Anandkumar
Abstract: Partial differential equations (PDEs) govern a wide variety of dynamical processes in science and engineering, yet obtaining their numerical solutions often requires high-resolution discretizations and repeated evaluations of complex operators, leading to substantial computational costs. Neural operators have recently emerged as a powerful framework for learning mappings between function spaces directly from data, enabling efficient surrogate models for PDE systems. Among these architectures, the Fourier Neural Operator (FNO) has become the most influential and widely adopted due to its elegant spectral formulation, which captures global correlations through learnable transformations in Fourier space while remaining invariant to discretization and resolution. Despite their success, the practical use of FNOs is often hindered by an incomplete understanding among practitioners of their theoretical foundations, practical constraints, and implementation details, which can lead to their incorrect or unreliable application. This work presents a comprehensive and practice-oriented guide to FNOs, unifying their mathematical principles with implementation strategies. We provide an intuitive exposition to the concepts of operator theory and signal-processing that underlie the FNO, detail its spectral parameterization and the computational design of all its components, and address common misunderstandings encountered in the literature. The exposition is closely integrated with the NeuralOperator 2.0.0 library, offering modular state-of-the-art implementations that faithfully reflect the theory. By connecting rigorous foundations with practical insight, this guide aims to establish a clear and reliable framework for applying FNOs effectively across diverse scientific and engineering fields.
Authors: Rohin Manvi, Joey Hong, Tim Seyde, Maxime Labonne, Mathias Lechner, Sergey Levine
Abstract: Large language models excel at reasoning but lack key aspects of introspection, including anticipating their own success and the computation required to achieve it. Humans use real-time introspection to decide how much effort to invest, when to make multiple attempts, when to stop, and when to signal success or failure. Without this, LLMs struggle to make intelligent meta-cognition decisions. Test-time scaling methods like Best-of-N drive up cost and latency by using a fixed budget of samples regardless of the marginal benefit of each one at any point in generation, and the absence of confidence signals can mislead people, prevent appropriate escalation to better tools, and undermine trustworthiness. Learned verifiers or reward models can provide confidence estimates, but do not enable adaptive inference and add substantial cost by requiring extra models or forward passes. We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost. At every token, ZIP-RC reuses reserved or unused logits in the same forward pass as next-token prediction to output a joint distribution over final reward and remaining length -- no extra models, architecture change, or inference overhead. This full joint distribution is used to compute a sampling utility which is the linear combination of the expected maximum reward, total compute, and latency of set of samples if generated to completion. During inference, we maximize this utility with meta-actions that determine which prefix of tokens to continue or initiate sampling from. On mixed-difficulty mathematical benchmarks, ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost, and traces smooth Pareto frontiers between quality, compute, and latency. By providing real-time reward-cost introspection, ZIP-RC enables adaptive, efficient reasoning.
Authors: Kuangpu Guo, Yuhe Ding, Jian Liang, Zilei Wang, Ran He
Abstract: Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models, even on similar tasks, underscoring the need to preserve task-specific information. This paper proposes Decomposition, Thresholding, and Scaling (DTS), an approximation-based personalized merging framework that preserves task-specific information with minimal storage overhead. DTS first applies singular value decomposition to the task-specific information and retains only a small subset of singular values and vectors. It then introduces a novel thresholding strategy that partitions singular vector elements into groups and assigns a scaling factor to each group. To enable generalization to unseen tasks, we further extend DTS with a variant that fuses task-specific information in a data-free manner based on the semantic similarity of task characteristics. Extensive experiments demonstrate that DTS consistently outperforms state-of-the-art baselines while requiring only 1\% additional storage per task. Furthermore, experiments on unseen tasks show that the DTS variant achieves significantly better generalization performance. Our code is available at https://github.com/krumpguo/DTS.
Authors: Hongnan Si, Tong Li, Yujie Chen, Xin Liao
Abstract: Water quality monitoring is a core component of ecological environmental protection. However, due to sensor failure or other inevitable factors, data missing often exists in long-term monitoring, posing great challenges in water quality analysis. This paper proposes a Neural Tucker Convolutional Network (NTCN) model for water quality data imputation, which features the following key components: a) Encode different mode entities into respective embedding vectors, and construct a Tucker interaction tensor by outer product operations to capture the complex mode-wise feature interactions; b) Use 3D convolution to extract fine-grained spatiotemporal features from the interaction tensor. Experiments on three real-world water quality datasets show that the proposed NTCN model outperforms several state-of-the-art imputation models in terms of accuracy.
Authors: Fabian Kresse, Christoph H. Lampert
Abstract: We investigate whether continuous-control policies can be represented and learned as discrete logic circuits instead of continuous neural networks. We introduce Differentiable Weightless Controllers (DWCs), a symbolic-differentiable architecture that maps real-valued observations to actions using thermometer-encoded inputs, sparsely connected boolean lookup-table layers, and lightweight action heads. DWCs can be trained end-to-end by gradient-based techniques, yet compile directly into FPGA-compatible circuits with few- or even single-clock-cycle latency and nanojoule-level energy cost per action. Across five MuJoCo benchmarks, including high-dimensional Humanoid, DWCs achieve returns competitive with weight-based policies (full precision or quantized neural networks), matching performance on four tasks and isolating network capacity as the key limiting factor on HalfCheetah. Furthermore, DWCs exhibit structurally sparse and interpretable connectivity patterns, enabling a direct inspection of which input thresholds influence control decisions.
Authors: Dan Qiao, Yu-Xiang Wang
Abstract: We consider the problem of generalization of arbitrarily overparameterized two-layer ReLU Neural Networks with univariate input. Recent work showed that under square loss, flat solutions (motivated by flat / stable minima and Edge of Stability phenomenon) provably cannot overfit, but it remains unclear whether the same phenomenon holds for logistic loss. This is a puzzling open problem because existing work on logistic loss shows that gradient descent with increasing step size converges to interpolating solutions (at infinity, for the margin-separable cases). In this paper, we prove that the \emph{flatness implied generalization} is more delicate under logistic loss. On the positive side, we show that flat solutions enjoy near-optimal generalization bounds within a region between the left-most and right-most \emph{uncertain} sets determined by each candidate solution. On the negative side, we show that there exist arbitrarily flat yet overfitting solutions at infinity that are (falsely) certain everywhere, thus certifying that flatness alone is insufficient for generalization in general. We demonstrate the effects predicted by our theory in a well-controlled simulation study.
Authors: Gwendal Debaussart-Joniec (CB), Argyris Kalogeratos (CB)
Abstract: This paper introduces a comprehensive unified framework for constructing multi-view diffusion geometries through intertwined multi-view diffusion trajectories (MDTs), a class of inhomogeneous diffusion processes that iteratively combine the random walk operators of multiple data views. Each MDT defines a trajectory-dependent diffusion operator with a clear probabilistic and geometric interpretation, capturing over time the interplay between data views. Our formulation encompasses existing multi-view diffusion models, while providing new degrees of freedom for view interaction and fusion. We establish theoretical properties under mild assumptions, including ergodicity of both the point-wise operator and the process in itself. We also derive MDT-based diffusion distances, and associated embeddings via singular value decompositions. Finally, we propose various strategies for learning MDT operators within the defined operator space, guided by internal quality measures. Beyond enabling flexible model design, MDTs also offer a neutral baseline for evaluating diffusion-based approaches through comparison with randomly selected MDTs. Experiments show the practical impact of the MDT operators in a manifold learning and data clustering context.
Authors: Ali Nafisi, Sina Asghari, Mohammad Saeed Arvenaghi, Hossein Shakibania
Abstract: This report presents solutions to three machine learning challenges: compositional image retrieval, zero-shot anomaly detection, and backdoored model detection. In compositional image retrieval, we developed a system that processes visual and textual inputs to retrieve relevant images, achieving 95.38\% accuracy and ranking first with a clear margin over the second team. For zero-shot anomaly detection, we designed a model that identifies and localizes anomalies in images without prior exposure to abnormal examples, securing 1st place with 73.14\% accuracy. In the backdoored model detection task, we proposed a method to detect hidden backdoor triggers in neural networks, reaching an accuracy of 78\%, which placed our approach in second place. These results demonstrate the effectiveness of our methods in addressing key challenges related to retrieval, anomaly detection, and model security, with implications for real-world applications in industries such as healthcare, manufacturing, and cybersecurity. Code for all solutions is available online.
Authors: Alfredo Reichlin, Miguel Vasco, Danica Kragic
Abstract: Bayesian Neural Networks provide a principled framework for uncertainty quantification by modeling the posterior distribution of network parameters. However, exact posterior inference is computationally intractable, and widely used approximations like the Laplace method struggle with scalability and posterior accuracy in modern deep networks. In this work, we revisit sampling techniques for posterior exploration, proposing a simple variation tailored to efficiently sample from the posterior in over-parameterized networks by leveraging the low-dimensional structure of loss minima. Building on this, we introduce a model that learns a deformation of the parameter space, enabling rapid posterior sampling without requiring iterative methods. Empirical results demonstrate that our approach achieves competitive posterior approximations with improved scalability compared to recent refinement techniques. These contributions provide a practical alternative for Bayesian inference in deep learning.
Authors: Mengyao Du, Gang Yang, Han Fang, Quanjun Yin, Ee-chien Chang
Abstract: The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate with their internal semantics undocumented or even intentionally withheld. Such opaque classifiers, which may expose only hard-label outputs, can operate in unregulated web environments or be repurposed for unknown intents, raising legitimate forensic and auditing concerns. In this paper, we position ourselves as investigators and work to infer the semantic concept each label encodes in an undocumented black-box classifier. Specifically, we introduce label forensics, a black-box framework that reconstructs a label's semantic meaning. Concretely, we represent a label by a sentence embedding distribution from which any sample reliably reflects the concept the classifier has implicitly learned for that label. We believe this distribution should maintain two key properties: precise, with samples consistently classified into the target label, and general, covering the label's broad semantic space. To realize this, we design a semantic neighborhood sampler and an iterative optimization procedure to select representative seed sentences that jointly maximize label consistency and distributional coverage. The final output, an optimized seed sentence set combined with the sampler, constitutes the empirical distribution representing the label's semantics. Experiments on multiple black-box classifiers achieve an average label consistency of around 92.24 percent, demonstrating that the embedding regions accurately capture each classifier's label semantics. We further validate our framework on an undocumented HuggingFace classifier, enabling fine-grained label interpretation and supporting responsible AI auditing.
Authors: Abdo Abouelrous, Laurens Bliek, Yaoxin Wu, Yingqian Zhang
Abstract: In this work, we consider learning-based applications in routing to solve a Vehicle Routing variant characterized by stochasticity and multiple objectives. Such problems are representative of practical settings where decision-makers have to deal with uncertainty in the operational environment as well as multiple conflicting objectives due to different stakeholders. We specifically consider travel time uncertainty. We also consider two objectives, total travel time and route makespan, that jointly target operational efficiency and labor regulations on shift length, although different objectives could be incorporated. Learning-based methods offer earnest computational advantages as they can repeatedly solve problems with limited interference from the decision-maker. We specifically focus on end-to-end deep learning models that leverage the attention mechanism and multiple solution trajectories. These models have seen several successful applications in routing problems. However, since travel times are not a direct input to these models due to the large dimensions of the travel time matrix, accounting for uncertainty is a challenge, especially in the presence of multiple objectives. In turn, we propose a model that simultaneously addresses stochasticity and multi-objectivity and provide a refined training mechanism for this model through scenario clustering to reduce training time. Our results show that our model is capable of constructing a Pareto Front of good quality within acceptable run times compared to three baselines.
Authors: Simon Leszek
Abstract: Change-point detection (CPD) in high-dimensional, large-volume time series is challenging for statistical consistency, scalability, and interpretability. We introduce TimePred, a self-supervised framework that reduces multivariate CPD to univariate mean-shift detection by predicting each sample's normalized time index. This enables efficient offline CPD using existing algorithms and supports the integration of XAI attribution methods for feature-level explanations. Our experiments show competitive CPD performance while reducing computational cost by up to two orders of magnitude. In an industrial manufacturing case study, we demonstrate improved detection accuracy and illustrate the practical value of interpretable change-point insights.
Authors: Sandro Andric
Abstract: We investigate whether Large Language Models (LLMs) exhibit altruistic tendencies, and critically, whether their implicit associations and self-reports predict actual altruistic behavior. Using a multi-method approach inspired by human social psychology, we tested 24 frontier LLMs across three paradigms: (1) an Implicit Association Test (IAT) measuring implicit altruism bias, (2) a forced binary choice task measuring behavioral altruism, and (3) a self-assessment scale measuring explicit altruism beliefs. Our key findings are: (1) All models show strong implicit pro-altruism bias (mean IAT = 0.87, p < .0001), confirming models "know" altruism is good. (2) Models behave more altruistically than chance (65.6% vs. 50%, p < .0001), but with substantial variation (48-85%). (3) Implicit associations do not predict behavior (r = .22, p = .29). (4) Most critically, models systematically overestimate their own altruism, claiming 77.5% altruism while acting at 65.6% (p < .0001, Cohen's d = 1.08). This "virtue signaling gap" affects 75% of models tested. Based on these findings, we recommend the Calibration Gap (the discrepancy between self-reported and behavioral values) as a standardized alignment metric. Well-calibrated models are more predictable and behaviorally consistent; only 12.5% of models achieve the ideal combination of high prosocial behavior and accurate self-knowledge.
Authors: Letian Yi, Tingpeng Zhang, Mingyuan Zhou, Guannan Wang, Quanke Su, Zhilu Lai
Abstract: Reconstructing full fields from extremely sparse and random measurements is a longstanding ill-posed inverse problem. A powerful framework for addressing such challenges is hierarchical probabilistic modeling, where uncertainty is represented by intermediate variables and resolved through marginalization during inference. Inspired by this principle, we propose Cascaded Sensing (Cas-Sensing), a hierarchical reconstruction framework that integrates an autoencoder-diffusion cascade. First, a neural operator-based functional autoencoder reconstructs the dominant structures of the original field - including large-scale components and geometric boundaries - from arbitrary sparse inputs, serving as an intermediate variable. Then, a conditional diffusion model, trained with a mask-cascade strategy, generates fine-scale details conditioned on these large-scale structures. To further enhance fidelity, measurement consistency is enforced via the manifold constrained gradient based on Bayesian posterior sampling during the generation process. This cascaded pipeline substantially alleviates ill-posedness, delivering accurate and robust reconstructions. Experiments on both simulation and real-world datasets demonstrate that Cas-Sensing generalizes well across varying sensor configurations and geometric boundaries, making it a promising tool for practical deployment in scientific and engineering applications.
Authors: Jos\'ephine Raugel, St\'ephane d'Ascoli, J\'er\'emy Rapin, Valentin Wyart, Jean-R\'emi King
Abstract: Recent studies suggest that the representations learned by large language models (LLMs) are partially aligned to those of the human brain. However, whether and why this alignment score arises from a similar sequence of computations remains elusive. In this study, we explore this question by examining temporally-resolved brain signals of participants listening to 10 hours of an audiobook. We study these neural dynamics jointly with a benchmark encompassing 22 LLMs varying in size and architecture type. Our analyses confirm that LLMs and the brain generate representations in a similar order: specifically, activations in the initial layers of LLMs tend to best align with early brain responses, while the deeper layers of LLMs tend to best align with later brain responses. This brain-LLM alignment is consistent across transformers and recurrent architectures. However, its emergence depends on both model size and context length. Overall, this study sheds light on the sequential nature of computations and the factors underlying the partial convergence between biological and artificial neural networks.
Authors: Daniele Masti, Francesco Basciani, Arianna Fedeli, Girgio Gnecco, Francesco Smarra
Abstract: Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. Their mathematically optimal decisions often diverge from human expectations, exposing a persistent gap between algorithmic and bounded human rationality. This work addresses this gap by proposing a framework that operationalizes fairness as a learnable objective within optimization-based Digital Twins. We introduce a preference-driven learning pipeline that infers latent fairness objectives directly from human pairwise preferences over feasible decisions. A novel Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives align optimization outcomes with human-perceived fairness while maintaining computational efficiency. The approach is demonstrated on a COVID-19 hospital resource allocation scenario. This study provides an actionable path toward embedding human-centered fairness in the design of autonomous decision-making systems.
Authors: Valentin No\"el, Elimane Yassine Seidou, Charly Ken Capo-Chichi, Ghanem Amari
Abstract: Legal AI systems powered by retrieval-augmented generation (RAG) face a critical accountability challenge: when an AI assistant cites case law, statutes, or contractual clauses, practitioners need verifiable guarantees that generated text faithfully represents source documents. Existing hallucination detectors rely on semantic similarity metrics that tolerate entity substitutions, a dangerous failure mode when confusing parties, dates, or legal provisions can have material consequences. We introduce HalluGraph, a graph-theoretic framework that quantifies hallucinations through structural alignment between knowledge graphs extracted from context, query, and response. Our approach produces bounded, interpretable metrics decomposed into \textit{Entity Grounding} (EG), measuring whether entities in the response appear in source documents, and \textit{Relation Preservation} (RP), verifying that asserted relationships are supported by context. On structured control documents, HalluGraph achieves near-perfect discrimination ($>$400 words, $>$20 entities), HalluGraph achieves $AUC = 0.979$, while maintaining robust performance ($AUC \approx 0.89$) on challenging generative legal task, consistently outperforming semantic similarity baselines. The framework provides the transparency and traceability required for high-stakes legal applications, enabling full audit trails from generated assertions back to source passages.
Authors: Zhongyuan Wu, Jingyuan Wang, Zexuan Cheng, Yilong Zhou, Weizhi Wang, Juhua Pu, Chao Li, Changqing Ma
Abstract: Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities -- such as time series, system logs, and tabular records -- as exemplified by modern IT systems. Effective AD methods in such environments must therefore possess two critical capabilities: (1) the ability to handle heterogeneous data formats within a unified framework, allowing the model to process and detect multiple modalities in a consistent manner during anomalous events; (2) a strong generalization ability to quickly adapt to new scenarios without extensive retraining. However, most existing methods fall short of these requirements, as they typically focus on single modalities and lack the flexibility to generalize across domains. To address this gap, we introduce a novel paradigm: In-Context Anomaly Detection (ICAD), where anomalies are defined by their dissimilarity to a relevant reference set of normal samples. Under this paradigm, we propose ICAD-LLM, a unified AD framework leveraging Large Language Models' in-context learning abilities to process heterogeneous data within a single model. Extensive experiments demonstrate that ICAD-LLM achieves competitive performance with task-specific AD methods and exhibits strong generalization to previously unseen tasks, which substantially reduces deployment costs and enables rapid adaptation to new environments. To the best of our knowledge, ICAD-LLM is the first model capable of handling anomaly detection tasks across diverse domains and modalities.
Authors: Anubhab, Rupesh Nasre
Abstract: Graph Neural Networks (GNNs) present a fundamental hardware challenge by fusing irregular, memory-bound graph traversals with regular, compute-intensive dense matrix operations. While frameworks such as PyTorch Geometric (PyG) and Deep Graph Library (DGL) prioritize high-level usability, they fail to address these divergent execution characteristics. As a result, they rely on generic kernels that suffer from poor cache locality, excessive memory movement, and substantial intermediate allocations. To address these limitations, we present Morphling, a domain-specific code synthesizer designed to bridge this gap. Morphling compiles high-level GNN specifications into portable, backend-specialized implementations targeting OpenMP, CUDA, and MPI. It achieves this by instantiating a library of optimized, architecture-aware primitives tailored to each execution environment. Morphling also incorporates a runtime sparsity-aware execution engine that dynamically selects dense or sparse execution paths using input feature statistics, reducing unnecessary computation on zero-valued entries. We evaluate Morphling on eleven real-world datasets spanning diverse graph structures, feature dimensionalities, and sparsity regimes. The results show that Morphling improves per-epoch training throughput by an average of 20X on CPUs and 19X on GPUs over PyG and DGL, with peak speedups reaching 66X. Morphling's memory-efficient layouts further reduce peak memory consumption by up to 15X, enabling large-scale GNN training on commodity hardware. These findings demonstrate that specialized, architecture-aware code synthesis provides an effective and scalable path toward high-performance GNN execution across diverse parallel and distributed platforms.
Authors: Bei Zhou, Cesare Corrado, Shuang Qian, Maximilian Balmus, Angela W. C. Lee, Cristobal Rodero, Marco J. W. Gotte, Luuk H. G. A. Hopman, Mengyun Qiao, Steven Niederer
Abstract: Accurate maps of atrial electrical activation are essential for personalised treatment of arrhythmias, yet biophysically detailed simulations remain computationally intensive for real-time clinical use or population-scale analyses. Here we introduce a geometry-independent operator-learning framework that predicts local activation time (LAT) fields across diverse left atrial anatomies with near-instantaneous inference. We generated a dataset of 308,700 simulations using a GPU-accelerated electrophysiology solver, systematically varying multiple pacing sites and physiologically varied conduction properties across 147 patient-specific geometries derived from two independent clinical cohorts. All anatomical and functional data are expressed in a Universal Atrium Coordinate system, providing a consistent representation that decouples electrophysiological patterns from mesh topology. Within this coordinate space, we designed a neural operator with a vision-transformer backbone to learn the mapping from structural and electrophysiological inputs to LAT fields. With a mean prediction error of 5.1 ms over a 455 ms maximum simulation time, the model outperforms established operator-learning approaches and performs inference in 0.12 ms per sample. Our framework establishes a general strategy for learning domain-invariant biophysical mappings across variable anatomical domains and enables integration of computational electrophysiology into real-time and large-scale clinical workflows.
Authors: Yan Huang, Jinming Xu, Jiming Chen, Karl Henrik Johansson
Abstract: In distributed and federated learning algorithms, communication overhead is often reduced by performing multiple local updates between communication rounds. However, due to data heterogeneity across nodes and the local gradient noise within each node, this strategy can lead to the drift of local models away from the global optimum. To address this issue, we revisit the well-known federated learning method Scaffold (Karimireddy et al., 2020) under a gradient tracking perspective, and propose a unified spatio-temporal gradient tracking algorithm, termed ST-GT, for distributed stochastic optimization over time-varying graphs. ST-GT tracks the global gradient across neighboring nodes to mitigate data heterogeneity, while maintaining a running average of local gradients to substantially suppress noise, with slightly more storage overhead. Without assuming bounded data heterogeneity, we prove that ST-GT attains a linear convergence rate for strongly convex problems and a sublinear rate for nonconvex cases. Notably, ST-GT achieves the first linear speed-up in communication complexity with respect to the number of local updates per round $\tau$ for the strongly-convex setting. Compared to traditional gradient tracking methods, ST-GT reduces the topology-dependent noise term from $\sigma^2$ to $\sigma^2/\tau$, where $\sigma^2$ denotes the noise level, thereby improving communication efficiency.
Authors: Marius Tacke, Matthias Busch, Kian Abdolazizi, Jonas Eichinger, Kevin Linka, Christian Cyron, Roland Aydin
Abstract: Large language model (LLM)-based agentic frameworks increasingly adopt the paradigm of dynamically generating task-specific agents. We suggest that not only agents but also specialized software modules for scientific and engineering tasks can be generated on demand. We demonstrate this concept in the field of solid mechanics. There, so-called constitutive models are required to describe the relationship between mechanical stress and body deformation. Constitutive models are essential for both the scientific understanding and industrial application of materials. However, even recent data-driven methods of constitutive modeling, such as constitutive artificial neural networks (CANNs), still require substantial expert knowledge and human labor. We present a framework in which an LLM generates a CANN on demand, tailored to a given material class and dataset provided by the user. The framework covers LLM-based architecture selection, integration of physical constraints, and complete code generation. Evaluation on three benchmark problems demonstrates that LLM-generated CANNs achieve accuracy comparable to or greater than manually engineered counterparts, while also exhibiting reliable generalization to unseen loading scenarios and extrapolation to large deformations. These findings indicate that LLM-based generation of physics-constrained neural networks can substantially reduce the expertise required for constitutive modeling and represent a step toward practical end-to-end automation.
Authors: Pedro M. P. Curvo, Jan-Willem van de Meent, Maksim Zhdanov
Abstract: A key scalability challenge in neural solvers for industrial-scale physics simulations is efficiently capturing both fine-grained local interactions and long-range global dependencies across millions of spatial elements. We introduce the Multi-Scale Patch Transformer (MSPT), an architecture that combines local point attention within patches with global attention to coarse patch-level representations. To partition the input domain into spatially-coherent patches, we employ ball trees, which handle irregular geometries efficiently. This dual-scale design enables MSPT to scale to millions of points on a single GPU. We validate our method on standard PDE benchmarks (elasticity, plasticity, fluid dynamics, porous flow) and large-scale aerodynamic datasets (ShapeNet-Car, Ahmed-ML), achieving state-of-the-art accuracy with substantially lower memory footprint and computational cost.
Authors: Stella Etuk, Ashraf Matrawy
Abstract: Despite advances in the use of large language models (LLMs) in downstream tasks, their ability to memorize information has raised privacy concerns. Therefore, protecting personally identifiable information (PII) during LLM training remains a fundamental challenge. Conventional methods like Differential Privacy-Stochastic Gradient Descent (DP-SGD) provide robust privacy protection via uniform noising, protecting PII regardless of its distinct sensitivity. This comes at the expense of the model's utility, leading to a trade-off. In this paper, we propose SA-ADP, a sensitivity-aware approach that allocates noise based on the sensitivity of individual PII. We evaluated our method on four datasets (ABCD, CUSTOMERSIM, Wikitext-2, and UNSW-NB15 ). Our results show that SA-ADP achieves results comparable to the baseline (No-DP) and the conventional DP-SGD. This means that our method did not degrade the model's utility while still maintaining strong privacy protection.
Authors: Vaidotas Simkus, Anders Christensen, Steven Bennett, Ian Johnson, Mark Neumann, James Gin, Jonathan Godwin, Benjamin Rhodes
Abstract: Mofasa is an all-atom latent diffusion model with state-of-the-art performance for generating Metal-Organic Frameworks (MOFs). These are highly porous crystalline materials used to harvest water from desert air, capture carbon dioxide, store toxic gases and catalyse chemical reactions. In recognition of their value, the development of MOFs recently received a Nobel Prize in Chemistry. In many ways, MOFs are well-suited for exploiting generative models in chemistry: they are rationally-designable materials with a large combinatorial design space and strong structure-property couplings. And yet, to date, a high performance generative model has been lacking. To fill this gap, we introduce Mofasa, a general-purpose latent diffusion model that jointly samples positions, atom-types and lattice vectors for systems as large as 500 atoms. Mofasa avoids handcrafted assembly algorithms common in the literature, unlocking the simultaneous discovery of metal nodes, linkers and topologies. To help the scientific community build on our work, we release MofasaDB, an annotated library of hundreds of thousands of sampled MOF structures, along with a user-friendly web interface for search and discovery: https://mofux.ai/ .
URLs: https://mofux.ai/
Authors: Zhuoqian Yang, Mathieu Salzmann, Sabine S\"usstrunk
Abstract: In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.
Authors: John C. Hill, Tyler LaBonte, Xinchen Zhang, Vidya Muthukumar
Abstract: Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM training -- have garnered interest as an efficient approach to rectify dependence on spurious correlations and improve performance on minority groups. Surprisingly, LLR has been found to improve worst-group accuracy even when the held-out set is an imbalanced subset of the training set. We initially hypothesize that this ``unreasonable effectiveness'' of LLR is explained by its ability to mitigate neural collapse through the held-out set, resulting in the implicit bias of gradient descent benefiting robustness. Our empirical investigation does not support this hypothesis. Instead, we present strong evidence for an alternative hypothesis: that the success of LLR is primarily due to better group balance in the held-out set. We conclude by showing how the recent algorithms CB-LLR and AFR perform implicit group-balancing to elicit a robustness improvement.
Authors: Simon Park, Simran Kaur, Sanjeev Arora
Abstract: While reinforcement learning (RL) successfully enhances reasoning in large language models, its role in fostering compositional generalization (the ability to synthesize novel skills from known components) is often conflated with mere length generalization. To this end, we study what RL post-training teaches about skill composition and how the structure of the composition affects the skill transfer. We focus on the Countdown task (given n numbers and a target, form an expression that evaluates to the target) and analyze model solutions as expression trees, where each subtree corresponds to a reusable subtask and thus can be viewed as a ``skill.'' Tracking tree shapes and their success rates over training, we find: (i) out-of-distribution (OOD) generalization to larger n and to unseen tree shapes, indicating compositional reuse of subtasks; (ii) a structure-dependent hierarchy of learnability -- models master shallow balanced trees (workload is balanced between subtasks) before deep unbalanced ones, with persistent fragility on right-heavy structures (even when the composition depth is the same as some left-heavy structures). Our diagnostic reveals what is learned, in what order, and where generalization fails, clarifying how RL-only post-training induces OOD generalization beyond what standard metrics such as pass@k reveal.
Authors: Chenhao Sun, Yuhao Mao, Martin Vechev
Abstract: Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With RS, achieving high accuracy at small radii requires a small noise variance, while achieving high accuracy at large radii requires a large noise variance. However, the global noise variance used in the standard RS formulation leads to a fundamental limitation: there exists no global noise variance that simultaneously achieves strong performance at both small and large radii. To break through the global variance limitation, we propose a dual RS framework which enables input-dependent noise variances. To achieve that, we first prove that RS remains valid with input-dependent noise variances, provided the variance is locally constant around each input. Building on this result, we introduce two components which form our dual RS framework: (i) a variance estimator first predicts an optimal noise variance for each input, (ii) this estimated variance is then used by a standard RS classifier. The variance estimator is independently smoothed via RS to ensure local constancy, enabling flexible design. We also introduce training strategies to iteratively optimize the two components. Extensive experiments on CIFAR-10 show that our dual RS method provides strong performance for both small and large radii-unattainable with global noise variance-while incurring only a 60% computational overhead at inference. Moreover, it consistently outperforms prior input-dependent noise approaches across most radii, with particularly large gains at radii 0.5, 0.75, and 1.0, achieving relative improvements of 19%, 24%, and 21%, respectively. On ImageNet, dual RS remains effective across all radii. Additionally, the dual RS framework naturally provides a routing perspective for certified robustness, improving the accuracy-robustness trade-off with off-the-shelf expert RS models.
Authors: Maria-Florina Blacan, Hedyeh Beyhaghi
Abstract: We initiate the study of active learning algorithms for classifying strategic agents. Active learning is a well-established framework in machine learning in which the learner selectively queries labels, often achieving substantially higher accuracy and efficiency than classical supervised methods-especially in settings where labeling is costly or time-consuming, such as hiring, admissions, and loan decisions. Strategic classification, however, addresses scenarios where agents modify their features to obtain more favorable outcomes, resulting in observed data that is not truthful. Such manipulation introduces challenges beyond those in learning from clean data. Our goal is to design active and noise-tolerant algorithms that remain effective in strategic environments-algorithms that classify strategic agents accurately while issuing as few label requests as possible. The central difficulty is to simultaneously account for strategic manipulation and preserve the efficiency gains of active learning. Our main result is an algorithm for actively learning linear separators in the strategic setting that preserves the exponential improvement in label complexity over passive learning previously obtained only in the non-strategic case. Specifically, for data drawn uniformly from the unit sphere, we show that a modified version of the Active Perceptron algorithm [DKM05,YZ17] achieves excess error $\epsilon$ using only $\tilde{O}(d \ln \frac{1}{\epsilon})$ label queries and incurs at most $\tilde{O}(d \ln \frac{1}{\epsilon})$ additional mistakes relative to the optimal classifier, even in the nonrealizable case, when a $\tilde{\Omega}(\epsilon)$ fraction of inputs have inconsistent labels with the optimal classifier. The algorithm is computationally efficient and, under these distributional assumptions, requires substantially fewer label queries than prior work on strategic Perceptron [ABBN21].
Authors: Sarah Segel, Helena Graf, Edward Bergman, Kristina Thieme, Marcel Wever, Alexander Tornede, Frank Hutter, Marius Lindauer
Abstract: Hyperparameter optimization (HPO), as a central paradigm of AutoML, is crucial for leveraging the full potential of machine learning (ML) models; yet its complexity poses challenges in understanding and debugging the optimization process. We present DeepCAVE, a tool for interactive visualization and analysis, providing insights into HPO. Through an interactive dashboard, researchers, data scientists, and ML engineers can explore various aspects of the HPO process and identify issues, untouched potentials, and new insights about the ML model being tuned. By empowering users with actionable insights, DeepCAVE contributes to the interpretability of HPO and ML on a design level and aims to foster the development of more robust and efficient methodologies in the future.
Authors: Lama Alssum, Hasan Abed Al Kader Hammoud, Motasem Alfarra, Juan C Leon Alcazar, Bernard Ghanem
Abstract: Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new information. We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches. We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods, which is based exclusively on the expected label distribution, thus making it class-agnostic. As a consequence, IM regularizer can be directly integrated into various rehearsal-based continual learning methods, reducing forgetting and favoring faster convergence. Our empirical validation shows that, across datasets and regardless of the number of tasks, our proposed regularization strategy consistently improves baseline performance at the expense of a minimal computational overhead. The lightweight nature of IM ensures that it remains a practical and scalable solution, making it applicable to real-world continual learning scenarios where efficiency is paramount. Finally, we demonstrate the data-agnostic nature of our regularizer by applying it to video data, which presents additional challenges due to its temporal structure and higher memory requirements. Despite the significant domain gap, our experiments show that IM regularizer also improves the performance of video continual learning methods.
Authors: Yudi Wu, Wenhao Zhao, Dianbo Liu
Abstract: Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottleneck (IB) theory, to analyze the underlying strategies resolving this behavior. The framework models generation as a conflict between a 'Compression Pressure' - a drive to minimize overall codebook entropy - and a 'Diversity Pressure' - a drive to maximize conditional entropy given an input. We further decompose this diversity into two primary sources: 'Path Diversity', representing the choice of high-level generative strategies, and 'Execution Diversity', the randomness in executing a chosen strategy. To make this decomposition operational, we introduce three zero-shot, inference-time interventions that directly perturb the latent generative process and reveal how models allocate and express diversity. Application of this probe-based framework to representative AR, MIM, and Diffusion systems reveals three distinct strategies: "Diversity-Prioritized" (MIM), "Compression-Prioritized" (AR), and "Decoupled" (Diffusion). Our analysis provides a principled explanation for their behavioral differences and informs a novel inference-time diversity enhancement technique.
Authors: Mingxuan Hu, Hongbo Ma, Xinlan Wu, Ziqi Liu, Jiaqi Liu, Yangbin Chen
Abstract: Audio-based depression detection models have demonstrated promising performance but often suffer from gender bias due to imbalanced training data. Epidemiological statistics show a higher prevalence of depression in females, leading models to learn spurious correlations between gender and depression. Consequently, models tend to over-diagnose female patients while underperforming on male patients, raising significant fairness concerns. To address this, we propose a novel Counterfactual Debiasing Framework grounded in causal inference. We construct a causal graph to model the decision-making process and identify gender bias as the direct causal effect of gender on the prediction. During inference, we employ counterfactual inference to estimate and subtract this direct effect, ensuring the model relies primarily on authentic acoustic pathological features. Extensive experiments on the DAIC-WOZ dataset using two advanced acoustic backbones demonstrate that our framework not only significantly reduces gender bias but also improves overall detection performance compared to existing debiasing strategies.
Authors: Philippe Rigollet
Abstract: We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention continuous on the sphere, we connect Transformer dynamics to Wasserstein gradient flows, synchronization models (Kuramoto), and mean-shift clustering. Central to our results is a global clustering phenomenon whereby tokens cluster asymptotically after long metastable states where they are arranged into multiple clusters. We further analyze a tractable equiangular reduction to obtain exact clustering rates, show how commonly used normalization schemes alter contraction speeds, and identify a phase transition for long-context attention. The results highlight both the mechanisms that drive representation collapse and the regimes that preserve expressive, multi-cluster structure in deep attention architectures.
Authors: Ahmed Nebli
Abstract: The training of deep vision models is fundamentally a signal recovery problem amidst high-dimensional stochastic noise. Current optimization paradigms impose a static compromise on information channel capacity. For instance, magnitude-based methods, such as AdamW, operate on the assumption that gradient norms are high-fidelity curvature signals. While this allows for precision in smooth regimes, it leads to catastrophic noise amplification when applied to rugged, non-convex landscapes. Conversely, sign-based methods (e.g., Lion) perform a radical 1-bit quantization of the gradient, which aims to provide robust regularization at the cost of discarding fine-grained descent information. We propose that optimal convergence requires neither static prior, but rather a dynamic modulation of the update bitrate. We introduce \textbf{ThermoLion}, a vision-centric framework that utilizes local Signal-to-Noise Ratio (SNR) gating to autonomously transition parameters between a "low-bit" exploration phase and a "high-precision" exploitation phase. Furthermore, we introduce a Momentum Alignment mechanism that detects constructive interference between historical drift and instantaneous gradients to accelerate convergence during stable trajectories. Empirical benchmarks across 12 diverse vision datasets (including CIFAR, SVHN, and GTSRB) demonstrate that ThermoLion serves as a hyperparameter-free generalist, surpassing both AdamW and Lion in convergence speed and terminal accuracy without architecture-specific tuning.
Authors: Aref Ghoreishee, Abhishek Mishra, Lifeng Zhou, John Walsh, Nagarajan Kandasamy
Abstract: This work proposes an end-to-end multi-modal reinforcement learning framework for high-level decision-making in autonomous vehicles. The framework integrates heterogeneous sensory input, including camera images, LiDAR point clouds, and vehicle heading information, through a cross-attention transformer-based perception module. Although transformers have become the backbone of modern multi-modal architectures, their high computational cost limits their deployment in resource-constrained edge environments. To overcome this challenge, we propose a spiking temporal-aware transformer-like architecture that uses ternary spiking neurons for computationally efficient multi-modal fusion. Comprehensive evaluations across multiple tasks in the Highway Environment demonstrate the effectiveness and efficiency of the proposed approach for real-time autonomous decision-making.
Authors: Adrienne M. Propp, Mauro Perego, Eric C. Cyr, Anthony Gruber, Amanda A. Howard, Alexander Heinlein, Panos Stinis, Daniel M. Tartakovsky
Abstract: Accurate yet efficient surrogate models are essential for large-scale simulations of partial differential equations (PDEs), particularly for uncertainty quantification (UQ) tasks that demand hundreds or thousands of evaluations. We develop a physics-inspired graph neural network (GNN) surrogate that operates directly on unstructured meshes and leverages the flexibility of graph attention. To improve both training efficiency and generalization properties of the model, we introduce a domain decomposition (DD) strategy that partitions the mesh into subdomains, trains local GNN surrogates in parallel, and aggregates their predictions. We then employ transfer learning to fine-tune models across subdomains, accelerating training and improving accuracy in data-limited settings. Applied to ice sheet simulations, our approach accurately predicts full-field velocities on high-resolution meshes, substantially reduces training time relative to training a single global surrogate model, and provides a ripe foundation for UQ objectives. Our results demonstrate that graph-based DD, combined with transfer learning, provides a scalable and reliable pathway for training GNN surrogates on massive PDE-governed systems, with broad potential for application beyond ice sheet dynamics.
Authors: Gaganpreet Jhajj, Fuhua Lin
Abstract: Knowledge graphs (KGs) require continual updates as new information emerges, but neural embedding models suffer from catastrophic forgetting when learning new tasks sequentially. We evaluate Elastic Weight Consolidation (EWC), a regularization-based continual learning method, on KG link prediction using TransE embeddings on FB15k-237. Across multiple experiments with five random seeds, we find that EWC reduces catastrophic forgetting from 12.62% to 6.85%, a 45.7% reduction compared to naive sequential training. We observe that the task partitioning strategy affects the magnitude of forgetting: relation-based partitioning (grouping triples by relation type) exhibits 9.8 percentage points higher forgetting than randomly partitioned tasks (12.62% vs 2.81%), suggesting that task construction influences evaluation outcomes. While focused on a single embedding model and dataset, our results demonstrate that EWC effectively mitigates catastrophic forgetting in KG continual learning and highlight the importance of evaluation protocol design.
Authors: Leo Elmecker-Plakolm, Pierre Fasterling, Philip Sosnin, Calvin Tsay, Matthew Wicker
Abstract: Safety-critical environments are inherently dynamic. Distribution shifts, emerging vulnerabilities, and evolving requirements demand continuous updates to machine learning models. Yet even benign parameter updates can have unintended consequences, such as catastrophic forgetting in classical models or alignment drift in foundation models. Existing heuristic approaches (e.g., regularization, parameter isolation) can mitigate these effects but cannot certify that updated models continue to satisfy required performance specifications. We address this problem by introducing a framework for provably safe model updates. Our approach first formalizes the problem as computing the largest locally invariant domain (LID): a connected region in parameter space where all points are certified to satisfy a given specification. While exact maximal LID computation is intractable, we show that relaxing the problem to parameterized abstract domains (orthotopes, zonotopes) yields a tractable primal-dual formulation. This enables efficient certification of updates - independent of the data or algorithm used - by projecting them onto the safe domain. Our formulation further allows computation of multiple approximately optimal LIDs, incorporation of regularization-inspired biases, and use of lookahead data buffers. Across continual learning and foundation model fine-tuning benchmarks, our method matches or exceeds heuristic baselines for avoiding forgetting while providing formal safety guarantees.
Authors: Sanja Karilanova, Subhrakanti Dey, Ay\c{c}a \"Oz\c{c}elikkale
Abstract: Spiking neural networks (SNNs) are biologically inspired, event-driven models that are suitable for processing temporal data and offer energy-efficient computation when implemented on neuromorphic hardware. In SNNs, richer neuronal dynamic allows capturing more complex temporal dependencies, with delays playing a crucial role by allowing past inputs to directly influence present spiking behavior. We propose a general framework for incorporating delays into SNNs through additional state variables. The proposed mechanism enables each neuron to access a finite temporal input history. The framework is agnostic to neuron models and hence can be seamlessly integrated into standard spiking neuron models such as LIF and adLIF. We analyze how the duration of the delays and the learnable parameters associated with them affect the performance. We investigate the trade-offs in the network architecture due to additional state variables introduced by the delay mechanism. Experiments on the Spiking Heidelberg Digits (SHD) dataset show that the proposed mechanism matches the performance of existing delay-based SNNs while remaining computationally efficient. Moreover, the results illustrate that the incorporation of delays may substantially improve performance in smaller networks.
Authors: Jacob Searcy, Anish Dulal, Scott Bridgham, Ashley Cordes, Lillian Aoki, Brendan Bohannan, Qing Zhu, Lucas C. R. Silva
Abstract: Natural climate solutions (NCS) offer an approach to mitigating carbon dioxide (CO2) emissions. However, monitoring the carbon drawdown of ecosystems over large geographic areas remains challenging. Eddy-flux covariance towers provide ground truth for predictive 'upscaling' models derived from satellite products, but many satellites now produce measurements on spatial scales smaller than a flux tower's footprint. We introduce Footprint-Aware Regression (FAR), a first-of-its-kind, deep-learning framework that simultaneously predicts spatial footprints and pixel-level (30 m scale) estimates of carbon flux. FAR is trained on our AMERI-FAR25 dataset which combines 439 site years of tower data with corresponding Landsat scenes. Our model produces high-resolution predictions and achieves R2 = 0.78 when predicting monthly net ecosystem exchange on test sites from a variety of ecosystems.
Authors: Nico Daheim, Thomas M\"ollenhoff, Ming Liang Ang, Mohammad Emtiyaz Khan
Abstract: Stochastic Variance Reduced Gradient (SVRG) and its variants aim to speed-up training by using gradient corrections, but have seen limited success in deep learning. Here, we show surprising new foundational connections of SVRG to a recently proposed Bayesian method called posterior correction. Specifically, we show that SVRG is recovered as a special case of posterior correction over the isotropic-Gaussian family, while novel extensions are automatically obtained by using more flexible exponential families. We derive two new SVRG variants by using Gaussian families: First, a Newton-like variant that employs novel Hessian corrections, and second, an Adam-like extension that improves pretraining and finetuning of Transformer language models. This is the first work to connect SVRG to Bayes and use it to boost variational training for deep networks.
Authors: Han Zhou, Xingchen Wan, Ivan Vuli\'c, Anna Korhonen
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can conduct effective multi-turn and tool-integrated reasoning. While instructions serve as the primary protocol for defining agents, RLVR typically relies on static and manually designed instructions. However, those instructions may be suboptimal for the base model, and the optimal instruction may change as the agent's policy improves and explores the interaction with the environment. To bridge the gap, we introduce INSPO, a novel Instruction-Policy co-evolution framework that integrates instruction optimization as a dynamic component of the reinforcement learning (RL) loop. INSPO maintains a dynamic population of instruction candidates that are sampled with questions, where reward signals in RL loops are automatically attributed to each instruction, and low performers are periodically pruned. New instructions are generated and verified through an on-policy reflection mechanism, where an LLM-based optimizer analyzes past experience from a replay buffer and evolves more effective strategies given the current policy. We conduct extensive experiments on multi-turn retrieval and reasoning tasks, demonstrating that INSPO substantially outperforms strong baselines relying on static instructions. INSPO discovers innovative instructions that guide the agent toward more strategic reasoning paths, achieving substantial performance gains with only a marginal increase in computational overhead.
Authors: Sai Gokhale, Devleena Das, Rajeev Patwari, Ashish Sirasao, Elliott Delaye
Abstract: Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization, chunked prefill, and model weight quantization have shown promise, their joint effects and optimal configurations for edge deployment remain underexplored. We introduce KV Pareto, a systems-level framework that systematically maps the trade-off frontier between total memory consumption and task accuracy across these three complementary optimization techniques. Our framework evaluates multiple LLM architectures (Qwen, Llama, Mistral) with varying KV quantization schemes (int2/4/8, mixed-precision), granularities (per-token, per-tensor, per-block), and 4-bit weight quantization via AWQ. Our framework identifies model-specific Pareto-optimal configurations that achieve 68-78% total memory reduction with minimal (1-3%) accuracy degradation on long-context tasks. We additionally verify the selected frontiers on additional benchmarks of Needle-in-a-Haystack, GSM8k and MMLU as well as extended context lengths of up to 128k to demonstrate the practical need of joint optimization for efficient LLM inference.
Authors: Haoran Qin, Shansita Sharma, Ali Abbasi, Chayne Thrash, Soheil Kolouri
Abstract: Low-rank approximation methods such as singular value decomposition (SVD) and its variants (e.g., Fisher-weighted SVD, Activation SVD) have recently emerged as effective tools for neural network compression. In this setting, decomposition acts as a "surgical" intervention, followed by fine-tuning that serves as "rehab" to recover accuracy. Inspired by prehabilitation in surgery, we introduce a pre-compression fine-tuning stage, Low-Rank Prehab, that explicitly encourages low-rank structure in weight matrices while preserving task performance. By conditioning the model before SVD, Prehab steers weights toward spectrally compact regions of the parameter space, enabling smoother low-rank approximation and improved recovery. Experiments on large language models (LLMs) and other Transformer-based architectures, including Vision Transformers (ViTs), show that Prehab substantially reduces the immediate accuracy drop after compression and consistently improves post-finetuning performance. Across a wide range of compression ratios, our method outperforms state-of-the-art SVD-based techniques such as SVD-LLM, highlighting the importance of preparing models for compression rather than only improving the compression and recovery stages. Source code is available at https://github.com/niqretnuh/PREHAB-SVD
Authors: Eunjeong Jeong, Giovanni Perin, Howard H. Yang, Nikolaos Pappas
Abstract: Federated Learning (FL) on resource-constrained edge devices faces a critical challenge: The computational energy required for training Deep Neural Networks (DNNs) often dominates communication costs. However, most existing Energy-Harvesting FL (EHFL) strategies fail to account for this reality, resulting in wasted energy due to redundant local computations. For efficient and proactive resource management, algorithms that predict local update contributions must be devised. We propose a lightweight client scheduling framework using the Version Age of Information (VAoI), a semantics-aware metric that quantifies update timeliness and significance. Crucially, we overcome VAoI's typical prohibitive computational cost, which requires statistical distance over the entire parameter space, by introducing a feature-based proxy. This proxy estimates model redundancy using intermediate-layer extraction from a single forward pass, dramatically reducing computational complexity. Experiments conducted under extreme non-IID data distributions and scarce energy availability demonstrate superior learning performance while achieving energy reduction compared to existing baseline selection policies. Our framework establishes semantics-aware scheduling as a practical and vital solution for EHFL in realistic scenarios where training costs dominate transmission costs.
Authors: Suzan Ece Ada, Georg Martius, Emre Ugur, Erhan Oztop
Abstract: Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However, existing offline RL methods often assume stationarity or only consider synthetic perturbations at test time, assumptions that often fail in real-world scenarios characterized by abrupt, time-varying offsets. These offsets can lead to partial observability, causing agents to misperceive their true state and degrade performance. To overcome this challenge, we introduce Forecasting in Non-stationary Offline RL (FORL), a framework that unifies (i) conditional diffusion-based candidate state generation, trained without presupposing any specific pattern of future non-stationarity, and (ii) zero-shot time-series foundation models. FORL targets environments prone to unexpected, potentially non-Markovian offsets, requiring robust agent performance from the onset of each episode. Empirical evaluations on offline RL benchmarks, augmented with real-world time-series data to simulate realistic non-stationarity, demonstrate that FORL consistently improves performance compared to competitive baselines. By integrating zero-shot forecasting with the agent's experience, we aim to bridge the gap between offline RL and the complexities of real-world, non-stationary environments.
Authors: Minglai Yang, Xinyu Guo, Mihai Surdeanu, Liangming Pan
Abstract: Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable features, they often struggle to reliably align these features with human-defined concepts, resulting in entangled and distributed feature representations. To address this, we introduce AlignSAE, a method that aligns SAE features with a defined ontology through a "pre-train, then post-train" curriculum. After an initial unsupervised training phase, we apply supervised post-training to bind specific concepts to dedicated latent slots while preserving the remaining capacity for general reconstruction. This separation creates an interpretable interface where specific relations can be inspected and controlled without interference from unrelated features. Empirical results demonstrate that AlignSAE enables precise causal interventions, such as reliable "concept swaps", by targeting single, semantically aligned slots.
Authors: Sebastian Sanokowski, Kaustubh Patil, Alois Knoll
Abstract: Diffusion models have achieved remarkable success in data-driven learning and in sampling from complex, unnormalized target distributions. Building on this progress, we reinterpret Maximum Entropy Reinforcement Learning (MaxEntRL) as a diffusion model-based sampling problem. We tackle this problem by minimizing the reverse Kullback-Leibler (KL) divergence between the diffusion policy and the optimal policy distribution using a tractable upper bound. By applying the policy gradient theorem to this objective, we derive a modified surrogate objective for MaxEntRL that incorporates diffusion dynamics in a principled way. This leads to simple diffusion-based variants of Soft Actor-Critic (SAC), Proximal Policy Optimization (PPO) and Wasserstein Policy Optimization (WPO), termed DiffSAC, DiffPPO and DiffWPO. All of these methods require only minor implementation changes to their base algorithm. We find that on standard continuous control benchmarks, DiffSAC, DiffPPO and DiffWPO achieve better returns and higher sample efficiency than SAC and PPO.
Authors: Qian Li, Yuyi Wang
Abstract: Constant bit-size Transformers are known to be Turing complete, but existing constructions require $\Omega(s(n))$ chain-of-thought (CoT) steps per simulated Turing machine (TM) step, leading to impractical reasoning lengths. In this paper, we significantly reduce this efficiency gap by proving that any $(t(n),s(n))$-bounded multi-tape TM can be simulated by a constant bit-size Transformer with an optimal $O(s(n))$-long context window and only $O(s(n)^c)$ CoT steps per TM step, where $c>0$ can be made arbitrarily small by letting the Transformers' head-layer product sufficiently large. In addition, our construction shows that sparse attention with fixed geometric offsets suffices for efficient universal computation. Our proof leverages multi-queue TMs as a bridge. The main technical novelty is a more efficient simulation of multi-tape TMs by synchronous multi-queue TMs, improving both time and space complexity under stricter model assumptions.
Authors: Jihang Li, Bing Xu, Zulong Chen, Chuanfei Xu, Minping Chen, Suyu Liu, Ying Zhou, Zeyi Wen
Abstract: Talent search is a cornerstone of modern recruitment systems, yet existing approaches often struggle to capture nuanced job-specific preferences, model recruiter behavior at a fine-grained level, and mitigate noise from subjective human judgments. We present a novel framework that enhances talent search effectiveness and delivers substantial business value through two key innovations: (i) leveraging LLMs to extract fine-grained recruitment signals from job descriptions and historical hiring data, and (ii) employing a role-aware multi-gate MoE network to capture behavioral differences across recruiter roles. To further reduce noise, we introduce a multi-task learning module that jointly optimizes click-through rate (CTR), conversion rate (CVR), and resume matching relevance. Experiments on real-world recruitment data and online A/B testing show relative AUC gains of 1.70% (CTR) and 5.97% (CVR), and a 17.29% lift in click-through conversion rate. These improvements reduce dependence on external sourcing channels, enabling an estimated annual cost saving of millions of CNY.
Authors: Mubarek Mohammed
Abstract: The ever increasing complexity of the hardware design process demands improved hardware design and verification methodologies. With the advent of generative AI various attempts have been made to automate parts of the design and verification process. Large language models (LLMs) as well as specialized models generate hdl and testbenches for small components, having a few leaf level components. However, there are only a few attempts to automate the entire processor design process. Hardware design demands hierarchical and modular design processes. We utilized this best practice systematically and effectively. We propose agentic automated processor design and verification with engineers in the loop. The agent with optional specification tries to break down the design into sub-components, generate HDL and cocotb tests, and verifies the components involving engineer guidance, especially during debugging and synthesis. We designed various digital systems using this approach. However, we selected two simple processors for demonstration purposes in this work. The first one is a LEGv8 like a simple processor verified, synthesized and programmed for the DE-10 Lite FPGA. The second one is a RISC-V like 32-bit processor designed and verified in similar manner and synthesized. However, it is not programmed into the DE-10 Lite. This process is accomplished usually using around a million inference tokens per processor, using a combination of reasoning (e.g gemini-pro) and non-reasoning models (eg. gpt-5-mini) based on the complexity of the task. This indicates that hardware design and verification experimentation can be done cost effectively without using any specialized hardware. The approach is scalable, we even attempted system-on-chip, which we want to experiment in our future work.
Authors: Junzhuo Zhou, Ziwen Wang, Haoxuan Xia, Yuxin Yan, Chengyu Zhu, Ting-Jung Lin, Wei Xing, Lei He
Abstract: Accurate setup/hold time characterization is crucial for modern chip timing closure, but its reliance on potentially millions of SPICE simulations across diverse process-voltagetemperature (PVT) corners creates a major bottleneck, often lasting weeks or months. Existing methods suffer from slow search convergence and inefficient exploration, especially in the multi-corner setting. We introduce SetupKit, a novel framework designed to break this bottleneck using statistical intelligence, circuit analysis and active learning (AL). SetupKit integrates three key innovations: BEIRA, a bias-enhanced interpolation search derived from statistical error modeling to accelerate convergence by overcoming stagnation issues, initial search interval estimation by circuit analysis and AL strategy using Gaussian Process. This AL component intelligently learns PVT-timing correlations, actively guiding the expensive simulations to the most informative corners, thus minimizing redundancy in multicorner characterization. Evaluated on industrial 22nm standard cells across 16 PVT corners, SetupKit demonstrates a significant 2.4x overall CPU time reduction (from 720 to 290 days on a single core) compared to standard practices, drastically cutting characterization time. SetupKit offers a principled, learningbased approach to library characterization, addressing a critical EDA challenge and paving the way for more intelligent simulation management.
Authors: Swastik Bhattacharya, Sanjay Das, Anand Menon, Shamik Kundu, Arnab Raha, Kanad Basu
Abstract: Deep Neural Networks (DNNs) continue to grow in complexity with Large Language Models (LLMs) incorporating vast numbers of parameters. Handling these parameters efficiently in traditional accelerators is limited by data-transmission bottlenecks, motivating Compute-in-Memory (CiM) architectures that integrate computation within or near memory to reduce data movement. Recent work has explored CiM designs using Floating-Point (FP) and Integer (INT) operations. FP computations typically deliver higher output quality due to their wider dynamic range and precision, benefiting precision-sensitive Generative AI applications. These include models such as LLMs, thus driving advancements in FP-CiM accelerators. However, the vulnerability of FP-CiM to hardware faults remains underexplored, posing a major reliability concern in mission-critical settings. To address this gap, we systematically analyze hardware fault effects in FP-CiM by introducing bit-flip faults at key computational stages, including digital multipliers, CiM memory cells, and digital adder trees. Experiments with Convolutional Neural Networks (CNNs) such as AlexNet and state-of-the-art LLMs including LLaMA-3.2-1B and Qwen-0.3B-Base reveal how faults at each stage affect inference accuracy. Notably, a single adder fault can reduce LLM accuracy to 0%. Based on these insights, we propose a fault-resilient design, SafeCiM, that mitigates fault impact far better than a naive FP-CiM with a pre-alignment stage. For example, with 4096 MAC units, SafeCiM reduces accuracy degradation by up to 49x for a single adder fault compared to the baseline FP-CiM architecture.
Authors: Taewook Nam, Sung Ju Hwang
Abstract: Recent advances in robotic policy learning have enabled complex manipulation in real-world environments, yet the execution speed of these policies often lags behind hardware capabilities due to the cost of collecting faster demonstrations. Existing works on policy acceleration reinterpret action sequence for unseen execution speed, thereby encountering distributional shifts from the original demonstrations. Reinforcement learning is a promising approach that adapts policies for faster execution without additional demonstration, but its unguided exploration is sample inefficient. We propose SpeedAug, an RL-based policy acceleration framework that efficiently adapts pre-trained policies for faster task execution. SpeedAug constructs behavior prior that encompasses diverse tempos of task execution by pre-training a policy on speed-augmented demonstrations. Empirical results on robotic manipulation benchmarks show that RL fine-tuning initialized from this tempo-enriched policy significantly improves the sample efficiency of existing RL and policy acceleration methods while maintaining high success rate.
Authors: Sungyu Jeong, Minsu Kim, Byungsub Kim
Abstract: We propose a technique to assist in converting a reference layout of an analog circuit into the procedural layout generator by efficiently reusing available generators for sub-cell creation. The proposed convolutional neural network (CNN) model automatically detects sub-cells that can be generated by available generator scripts in the library, and suggests using them in the hierarchically correct places of the generator software. In experiments, the CNN model examined sub-cells of a high-speed wireline receiver that has a total of 4,885 sub-cell instances including different 145 sub-cell designs. The CNN model classified the sub-cell instances into 51 generatable and one not-generatable classes. One not-generatable class indicates that no available generator can generate the classified sub-cell. The CNN model achieved 99.3% precision in examining the 145 different sub-cell designs. The CNN model greatly reduced the examination time to 18 seconds from 88 minutes required in manual examination. Also, the proposed CNN model could correctly classify unfamiliar sub-cells that are very different from the training dataset.
Authors: Bin Sun, Rengang Zhang, Zhiteng Chao, Zizhen Liu, Jianan Mu, Jing Ye, Huawei Li
Abstract: Automatic test pattern generation (ATPG) is a crucial process in integrated circuit (IC) design and testing, responsible for efficiently generating test patterns. As semiconductor technology progresses, traditional ATPG struggles with long execution times to achieve the expected fault coverage, which impacts the time-to-market of chips. Recent machine learning techniques, like reinforcement learning (RL) and graph neural networks (GNNs), show promise but face issues such as reward delay in RL models and inadequate circuit representation in GNN-based methods. In this paper, we propose InF-ATPG, an intelligent FFR-driven ATPG framework that overcomes these challenges by using advanced circuit representation to guide RL. By partitioning circuits into fanout-free regions (FFRs) and incorporating ATPG-specific features into a novel QGNN architecture, InF-ATPG enhances test pattern generation efficiency. Experimental results show InF-ATPG reduces backtracks by 55.06\% on average compared to traditional methods and 38.31\% compared to the machine learning approach, while also improving fault coverage.
Authors: Venkata Siddharth Dhara, Pawan Kumar
Abstract: In recent times, denoising diffusion probabilistic models (DPMs) have proven effective for medical image generation and denoising, and as representation learners for downstream segmentation. However, segmentation performance is limited by the need for dense pixel-wise labels, which are expensive, time-consuming, and require expert knowledge. We propose FastTextDiff, a label-efficient diffusion-based segmentation model that integrates medical text annotations to enhance semantic representations. Our approach uses ModernBERT, a transformer capable of processing long clinical notes, to tightly link textual annotations with semantic content in medical images. Trained on MIMIC-III and MIMIC-IV, ModernBERT encodes clinical knowledge that guides cross-modal attention between visual and textual features. This study validates ModernBERT as a fast, scalable alternative to Clinical BioBERT in diffusion-based segmentation pipelines and highlights the promise of multi-modal techniques for medical image analysis. By replacing Clinical BioBERT with ModernBERT, FastTextDiff benefits from FlashAttention 2, an alternating attention mechanism, and a 2-trillion-token corpus, improving both segmentation accuracy and training efficiency over traditional diffusion-based models.
Authors: Mohammad Zare
Abstract: We propose SemImage, a novel method for representing a text document as a two-dimensional semantic image to be processed by convolutional neural networks (CNNs). In a SemImage, each word is represented as a pixel in a 2D image: rows correspond to sentences and an additional boundary row is inserted between sentences to mark semantic transitions. Each pixel is not a typical RGB value but a vector in a disentangled HSV color space, encoding different linguistic features: the Hue with two components H_cos and H_sin to account for circularity encodes the topic, Saturation encodes the sentiment, and Value encodes intensity or certainty. We enforce this disentanglement via a multi-task learning framework: a ColorMapper network maps each word embedding to the HSV space, and auxiliary supervision is applied to the Hue and Saturation channels to predict topic and sentiment labels, alongside the main task objective. The insertion of dynamically computed boundary rows between sentences yields sharp visual boundaries in the image when consecutive sentences are semantically dissimilar, effectively making paragraph breaks salient. We integrate SemImage with standard 2D CNNs (e.g., ResNet) for document classification. Experiments on multi-label datasets (with both topic and sentiment annotations) and single-label benchmarks demonstrate that SemImage can achieve competitive or better accuracy than strong text classification baselines (including BERT and hierarchical attention networks) while offering enhanced interpretability. An ablation study confirms the importance of the multi-channel HSV representation and the dynamic boundary rows. Finally, we present visualizations of SemImage that qualitatively reveal clear patterns corresponding to topic shifts and sentiment changes in the generated image, suggesting that our representation makes these linguistic features visible to both humans and machines.
Authors: Yifei Chen, Eric Liang
Abstract: As COVID-19 transitions into an endemic disease that remains constantly present in the population at a stable level, monitoring its prevalence without invasive measures becomes increasingly important. In this paper, we present a deep neural network estimator for the COVID-19 daily case count based on wastewater surveillance data and other confounding factors. This work builds upon the study by Jiang, Kolozsvary, and Li (2024), which connects the COVID-19 case counts with testing data collected early in the pandemic. Using the COVID-19 testing data and the wastewater surveillance data during the period when both data were highly reliable, one can train an artificial neural network that learns the nonlinear relation between the COVID-19 daily case count and the wastewater viral RNA concentration. From a machine learning perspective, the main challenge lies in addressing temporal feature reliability, as the training data has different reliability over different time periods.
Authors: Ifeanyi Okala
Abstract: This work examines how three different image-based methods, VGG16, ViT-B/16, and CoAtNet-Tiny, perform in identifying depression, schizophrenia, and healthy controls using daily actigraphy records. Wrist-worn activity signals from the Psykose and Depresjon datasets were converted into 30 by 48 images and evaluated through a three-fold subject-wise split. Although all methods fitted the training data well, their behaviour on unseen data differed. VGG16 improved steadily but often settled at lower accuracy. ViT-B/16 reached strong results in some runs, but its performance shifted noticeably from fold to fold. CoAtNet-Tiny stood out as the most reliable, recording the highest average accuracy and the most stable curves across folds. It also produced the strongest precision, recall, and F1-scores, particularly for the underrepresented depression and schizophrenia classes. Overall, the findings indicate that CoAtNet-Tiny performed most consistently on the actigraphy images, while VGG16 and ViT-B/16 yielded mixed results. These observations suggest that certain hybrid designs may be especially suited for mental-health work that relies on actigraphy-derived images.
Authors: Miguel A. Mendez, Jan van Den Berghe, Manuel Ratz, Matilde Fiore, Lorenzo Schena
Abstract: This chapter provides three tutorial exercises on physics-constrained regression. These are implemented as toy problems that seek to mimic grand challenges in (1) the super-resolution and data assimilation of the velocity field in image velocimetry, (2) data-driven turbulence modeling, and (3) system identification and digital twinning for forecasting and control. The Python codes for all exercises are provided in the course repository.
Authors: Jiaying Hong, Ting Zhu, Thanet Markchom, Huizhi Liang
Abstract: With the rise of AI-generated content (AIGC), generating perceptually natural and feeling-aligned music from multimodal inputs has become a central challenge. Existing approaches often rely on explicit emotion labels that require costly annotation, underscoring the need for more flexible feeling-aligned methods. To support multimodal music generation, we construct ArtiCaps, a pseudo feeling-aligned image-music-text dataset created by semantically matching descriptions from ArtEmis and MusicCaps. We further propose Art2Music, a lightweight cross-modal framework that synthesizes music from artistic images and user comments. In the first stage, images and text are encoded with OpenCLIP and fused using a gated residual module; the fused representation is decoded by a bidirectional LSTM into Mel-spectrograms with a frequency-weighted L1 loss to enhance high-frequency fidelity. In the second stage, a fine-tuned HiFi-GAN vocoder reconstructs high-quality audio waveforms. Experiments on ArtiCaps show clear improvements in Mel-Cepstral Distortion, Frechet Audio Distance, Log-Spectral Distance, and cosine similarity. A small LLM-based rating study further verifies consistent cross-modal feeling alignment and offers interpretable explanations of matches and mismatches across modalities. These results demonstrate improved perceptual naturalness, spectral fidelity, and semantic consistency. Art2Music also maintains robust performance with only 50k training samples, providing a scalable solution for feeling-aligned creative audio generation in interactive art, personalized soundscapes, and digital art exhibitions.
Authors: Ruo-Syuan Mei, Sixian Jia, Guangze Li, Soo Yeon Lee, Brian Musser, William Keller, Sreten Zakula, Jorge Arinez, Chenhui Shao
Abstract: Machine learning, particularly deep learning, is transforming industrial quality inspection. Yet, training robust machine learning models typically requires large volumes of high-quality labeled data, which are expensive, time-consuming, and labor-intensive to obtain in manufacturing. Moreover, defective samples are intrinsically rare, leading to severe class imbalance that degrades model performance. These data constraints hinder the widespread adoption of machine learning-based quality inspection methods in real production environments. Synthetic data generation (SDG) offers a promising solution by enabling the creation of large, balanced, and fully annotated datasets in an efficient, cost-effective, and scalable manner. This paper presents a hybrid SDG framework that integrates simulation-based rendering, domain randomization, and real background compositing to enable zero-shot learning for computer vision-based industrial part inspection without manual annotation. The SDG pipeline generates 12,960 labeled images in one hour by varying part geometry, lighting, and surface properties, and then compositing synthetic parts onto real image backgrounds. A two-stage architecture utilizing a YOLOv8n backbone for object detection and MobileNetV3-small for quality classification is trained exclusively on synthetic data and evaluated on 300 real industrial parts. The proposed approach achieves an mAP@0.5 of 0.995 for detection, 96% classification accuracy, and 90.1% balanced accuracy. Comparative evaluation against few-shot real-data baseline approaches demonstrates significant improvement. The proposed SDG-based approach achieves 90-91% balanced accuracy under severe class imbalance, while the baselines reach only 50% accuracy. These results demonstrate that the proposed method enables annotation-free, scalable, and robust quality inspection for real-world manufacturing applications.
Authors: Helen Guo, Elizabeth L. Ogburn, Ilya Shpitser
Abstract: Identifying causal effects in the presence of unmeasured variables is a fundamental challenge in causal inference, for which proxy variable methods have emerged as a powerful solution. We contrast two major approaches in this framework: (1) bridge equation methods, which leverage solutions to integral equations to recover causal targets, and (2) array decomposition methods, which recover latent factors composing counterfactual quantities by exploiting unique determination of eigenspaces. We compare the model restrictions underlying these two approaches and provide insight into implications of the underlying assumptions, clarifying the scope of applicability for each method.
Authors: Mohamed Abdallah Salem (North Dakota State University), Nourhan Zein Diab (New Mansoura University)
Abstract: Accurate material recognition is critical for safe and effective laser cutting, as misidentification can lead to poor cut quality, machine damage, or the release of hazardous fumes. Laser speckle sensing has recently emerged as a low-cost and non-destructive modality for material classification; however, prior work has either relied on computationally expensive backbone networks or addressed only limited subsets of materials. In this study, A lightweight convolutional neural network (CNN) tailored for speckle patterns is proposed, designed to minimize parameters while maintaining high discriminative power. Using the complete SensiCut dataset of 59 material classes spanning woods, acrylics, composites, textiles, metals, and paper-based products, the proposed model achieves 95.05% test accuracy, with macro and weighted F1-scores of 0.951. The network contains only 341k trainable parameters (~1.3 MB) -- over 70X fewer than ResNet-50 -- and achieves an inference speed of 295 images per second, enabling deployment on Raspberry Pi and Jetson-class devices. Furthermore, when materials are regrouped into nine and five practical families, recall exceeds 98% and approaches 100%, directly supporting power and speed preset selection in laser cutters. These results demonstrate that compact, domain-specific CNNs can outperform large backbones for speckle-based material classification, advancing the feasibility of material-aware, edge-deployable laser cutting systems.
Authors: Shashanka B R, Mohith Charan R, Seema Banu F
Abstract: Our goal is to consolidate the landscape of multimodal chunking strategies, providing researchers and practitioners with a technical foundation and design space for developing more effective and efficient multimodal AI systems. This survey paves the way for innovations in robust chunking pipelines that scale with modality complexity, enhance processing accuracy, and improve generative coherence in real-world applications. This survey provides a comprehensive taxonomy and technical analysis of chunking strategies tailored for each modality: text, images, audio, video, and cross-modal data. We examine classical and modern approaches such as fixed-size token windowing, recursive text splitting, object-centric visual chunking, silence-based audio segmentation, and scene detection in videos. Each approach is analyzed in terms of its underlying methodology, supporting tools (e.g., LangChain, Detectron2, PySceneDetect), benefits, and challenges, particularly those related to granularity-context trade-offs and multimodal alignment. Furthermore, we explore emerging cross-modal chunking strategies that aim to preserve alignment and semantic consistency across disparate data types [4]. We also include comparative insights, highlight open problems such as asynchronous information density and noisy alignment signals, and identify opportunities for future research in adaptive, learning-based, and task-specific chunking.
Authors: Zag ElSayed, Grace Westerkamp, Gavin Gammoh, Yanchen Liu, Peyton Siekierski, Craig Erickson, Ernest Pedapati
Abstract: We introduce EEG Autoclean Vision Language AI (ICVision) a first-of-its-kind system that emulates expert-level EEG ICA component classification through AI-agent vision and natural language reasoning. Unlike conventional classifiers such as ICLabel, which rely on handcrafted features, ICVision directly interprets ICA dashboard visualizations topography, time series, power spectra, and ERP plots, using a multimodal large language model (GPT-4 Vision). This allows the AI to see and explain EEG components the way trained neurologists do, making it the first scientific implementation of AI-agent visual cognition in neurophysiology. ICVision classifies each component into one of six canonical categories (brain, eye, heart, muscle, channel noise, and other noise), returning both a confidence score and a human-like explanation. Evaluated on 3,168 ICA components from 124 EEG datasets, ICVision achieved k = 0.677 agreement with expert consensus, surpassing MNE ICLabel, while also preserving clinically relevant brain signals in ambiguous cases. Over 97% of its outputs were rated as interpretable and actionable by expert reviewers. As a core module of the open-source EEG Autoclean platform, ICVision signals a paradigm shift in scientific AI, where models do not just classify, but see, reason, and communicate. It opens the door to globally scalable, explainable, and reproducible EEG workflows, marking the emergence of AI agents capable of expert-level visual decision-making in brain science and beyond.
Authors: Jonathan Pipping, Tianshu Feng, R. Paul Sabin
Abstract: Expected goals (xG) models estimate the probability that a shot results in a goal from its context (e.g., location, pressure), but they operate only on observed shots. We propose xG+, a possession-level framework that first estimates the probability that a shot occurs within the next second and its corresponding xG if it were to occur. We also introduce ways to aggregate this joint probability estimate over the course of a possession. By jointly modeling shot-taking behavior and shot quality, xG+ remedies the conditioning-on-shots limitation of standard xG. We show that this improves predictive accuracy at the team level and produces a more persistent player skill signal than standard xG models.
Authors: Jason Lunder
Abstract: In creating sentence embeddings for Natural Language Inference (NLI) tasks, using transformer-based models like BERT leads to high accuracy, but require hundreds of millions of parameters. These models take in sentences as a sequence of tokens, and learn to encode the meaning of the sequence into embeddings such that those embeddings can be used reliably for NLI tasks. Essentially, every word is considered against every other word in the sequence, and the transformer model is able to determine the relationships between them, entirely from scratch. However, a model that accepts explicit linguistic structures like dependency parse trees may be able to leverage prior encoded information about these relationships, without having to learn them from scratch, thus improving learning efficiency. To investigate this, we adapt Graph Matching Networks (GMN) to operate on dependency parse trees, creating Tree Matching Networks (TMN). We compare TMN to a BERT based model on the SNLI entailment task and on the SemEval similarity task. TMN is able to achieve significantly better results with a significantly reduced memory footprint and much less training time than the BERT based model on the SNLI task, while both models struggled to preform well on the SemEval. Explicit structural representations significantly outperform sequence-based models at comparable scales, but current aggregation methods limit scalability. We propose multi-headed attention aggregation to address this limitation.
Authors: Wei Fan, Kevin Tan, Yuting Wei
Abstract: Adaptively collected data has become ubiquitous within modern practice. However, even seemingly benign adaptive sampling schemes can introduce severe biases, rendering traditional statistical inference tools inapplicable. This can be mitigated by a property called stability, which states that if the rate at which an algorithm takes actions converges to a deterministic limit, one can expect that certain parameters are asymptotically normal. Building on a recent line of work for the multi-armed bandit setting, we show that the linear upper confidence bound (LinUCB) algorithm for linear bandits satisfies this property. In doing so, we painstakingly characterize the behavior of the eigenvalues and eigenvectors of the random design feature covariance matrix in the setting where the action set is the unit ball, showing that it decomposes into a rank-one direction that locks onto the true parameter and an almost-isotropic bulk that grows at a predictable $\sqrt{T}$ rate. This allows us to establish a central limit theorem for the LinUCB algorithm, establishing asymptotic normality for the limiting distribution of the estimation error where the convergence occurs at a $T^{-1/4}$ rate. The resulting Wald-type confidence sets and hypothesis tests do not depend on the feature covariance matrix and are asymptotically tighter than existing nonasymptotic confidence sets. Numerical simulations corroborate our findings.
Authors: Martin Andrae, Erik Larsson, So Takao, Tomas Landelius, Fredrik Lindsten
Abstract: Data assimilation (DA) is a cornerstone of scientific and engineering applications, combining model forecasts with sparse and noisy observations to estimate latent system states. Classical DA methods, such as the ensemble Kalman filter, rely on Gaussian approximations and heuristic tuning (e.g., inflation and localization) to scale to high dimensions. While often successful, these approximations can make the methods unstable or inaccurate when the underlying distributions of states and observations depart significantly from Gaussianity. To address this limitation, we introduce DAISI, a scalable filtering algorithm built on flow-based generative models that enables flexible probabilistic inference using data-driven priors. The core idea is to use a stationary, pre-trained generative prior to assimilate observations via guidance-based conditional sampling while incorporating forecast information through a novel inverse-sampling step. This step maps the forecast ensemble into a latent space to provide initial conditions for the conditional sampling, allowing us to encode model dynamics into the DA pipeline without having to retrain or fine-tune the generative prior at each assimilation step. Experiments on challenging nonlinear systems show that DAISI achieves accurate filtering results in regimes with sparse, noisy, and nonlinear observations where traditional methods struggle.
Authors: Woo Hyeon Lim, Ji Young Lee, Jong Hyuk Lee, Saehoon Kim, Hyungjin Kim
Abstract: Purpose: To benchmark open-source or commercial medical image-specific VLMs against real-world radiologist-written reports. Methods: This retrospective study included adult patients who presented to the emergency department between January 2022 and April 2025 and underwent same-day CXR and CT for febrile or respiratory symptoms. Reports from five VLMs (AIRead, Lingshu, MAIRA-2, MedGemma, and MedVersa) and radiologist-written reports were randomly presented and blindly evaluated by three thoracic radiologists using four criteria: RADPEER, clinical acceptability, hallucination, and language clarity. Comparative performance was assessed using generalized linear mixed models, with radiologist-written reports treated as the reference. Finding-level analyses were also performed with CT as the reference. Results: A total of 478 patients (median age, 67 years [interquartile range, 50-78]; 282 men [59.0%]) were included. AIRead demonstrated the lowest RADPEER 3b rate (5.3% [76/1434] vs. radiologists 13.9% [200/1434]; P<.001), whereas other VLMs showed higher disagreement rates (16.8-43.0%; P<.05). Clinical acceptability was the highest with AIRead (84.5% [1212/1434] vs. radiologists 74.3% [1065/1434]; P<.001), while other VLMs performed worse (41.1-71.4%; P<.05). Hallucinations were rare with AIRead, comparable to radiologists (0.3% [4/1425]) vs. 0.1% [1/1425]; P=.21), but frequent with other models (5.4-17.4%; P<.05). Language clarity was higher with AIRead (82.9% [1189/1434]), Lingshu (88.0% [1262/1434]), and MedVersa (88.4% [1268/1434]) compared with radiologists (78.1% [1120/1434]; P<.05). Sensitivity varied substantially across VLMs for the common findings: AIRead, 15.5-86.7%; Lingshu, 2.4-86.7%; MAIRA-2, 6.0-72.0%; MedGemma, 4.8-76.7%; and MedVersa, 20.2-69.3%. Conclusion: Medical VLMs for CXR report generation exhibited variable performance in report quality and diagnostic measures.
Authors: Zeyun Hu, Yang Liu
Abstract: We investigate the static portfolio selection problem of S-shaped and non-concave utility maximization under first-order and second-order stochastic dominance (SD) constraints. In many S-shaped utility optimization problems, one should require a liquidation boundary to guarantee the existence of a finite concave envelope function. A first-order SD (FSD) constraint can replace this requirement and provide an alternative for risk management. We explicitly solve the optimal solution under a general S-shaped utility function with a first-order stochastic dominance constraint. However, the second-order SD (SSD) constrained problem under non-concave utilities is difficult to solve analytically due to the invalidity of Sion's maxmin theorem. For this sake, we propose a numerical algorithm to obtain a plausible and sub-optimal solution for general non-concave utilities. The key idea is to detect the poor performance region with respect to the SSD constraints, characterize its structure and modify the distribution on that region to obtain (sub-)optimality. A key financial insight is that the decision maker should follow the SD constraint on the poor performance scenario while conducting the unconstrained optimal strategy otherwise. We provide numerical experiments to show that our algorithm effectively finds a sub-optimal solution in many cases. Finally, we develop an algorithm-guided piecewise-neural-network framework to learn the solution of the SSD problem, which demonstrates accelerated convergence compared to standard neural network approaches.
Authors: Zhijian Wei, Runze Ma, Zichen Wang, Zhongmin Li, Shuotong Song, Shuangjia Zheng
Abstract: Virtual cell modeling aims to predict cellular responses to perturbations. Existing virtual cell models rely heavily on large-scale single-cell datasets, learning explicit mappings between gene expression and perturbations. Although recent models attempt to incorporate multi-source biological information, their generalization remains constrained by data quality, coverage, and batch effects. More critically, these models often function as black boxes, offering predictions without interpretability or consistency with biological principles, which undermines their credibility in scientific research. To address these challenges, we present VCWorld, a cell-level white-box simulator that integrates structured biological knowledge with the iterative reasoning capabilities of large language models to instantiate a biological world model. VCWorld operates in a data-efficient manner to reproduce perturbation-induced signaling cascades and generates interpretable, stepwise predictions alongside explicit mechanistic hypotheses. In drug perturbation benchmarks, VCWorld achieves state-of-the-art predictive performance, and the inferred mechanistic pathways are consistent with publicly available biological evidence.
Authors: Ruike Hu, Shulei Wu
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language generation and reasoning. However, their integration into automated software ecosystems is often hindered by the "Structure Gap" - the inherent tension between the probabilistic nature of token generation and the deterministic requirements of structured data formats (e.g., JSON, XML). Traditional Supervised Fine-Tuning (SFT) often fails to enforce strict syntactic constraints, leading to "hallucinated" keys or malformed structures, while constrained decoding methods impose significant inference latency. In this paper, we propose a lightweight, efficient Reinforcement Learning (RL) framework to bridge this gap. We introduce a novel Multi-dimensional Reward Function that decomposes the structured output task into a hierarchy of constraints: structural integrity, format correctness, content accuracy, and validity. Leveraging Gradient Regularized Policy Optimization (GRPO), we enable the model to internalize these constraints without the need for a separate critic network, reducing peak VRAM usage by 40% compared to PPO. We validate our approach on multiple tasks, including complex recipe generation and structured math reasoning (GSM8K-JSON). Experimental results demonstrate that our method achieves 89.7% structural accuracy and 92.1% JSON validity, significantly outperforming both zero-shot baselines (e.g., GPT-3.5) and SFT on larger models like LLaMA-3-8B. Furthermore, we provide a detailed analysis of training dynamics, revealing a distinct self-paced curriculum where the model sequentially acquires syntactic proficiency before semantic accuracy. Our model is publicly available at https://huggingface.co/Freakz3z/Qwen-JSON.
Authors: Ruirui Huang, Jiacheng Li
Abstract: We introduce MedCondDiff, a diffusion-based framework for multi-organ medical image segmentation that is efficient and anatomically grounded. The model conditions the denoising process on semantic priors extracted by a Pyramid Vision Transformer (PVT) backbone, yielding a semantically guided and lightweight diffusion architecture. This design improves robustness while reducing both inference time and VRAM usage compared to conventional diffusion models. Experiments on multi-organ, multi-modality datasets demonstrate that MedCondDiff delivers competitive performance across anatomical regions and imaging modalities, underscoring the potential of semantically guided diffusion models as an effective class of architectures for medical imaging tasks.
Authors: Zhijian Yang, Edwin Setiadi Sugeng, Mhedine Alicherif, Tat Loon Chng
Abstract: Machine learning (ML) models have recently been used to reconstruct electric field distributions from EFISH signal profiles-the 'inverse EFISH problem'. This addresses the line-of-sight EFISH inaccuracy caused by the Gouy phase shift in focused beams. A key benefit of this approach is that the accuracy of the reconstructed profile can be directly checked via a 'forward transform' of the EFISH equation. Motivated by this latest success, the present study introduces a novel ML model with markedly improved performance. Based on a more powerful operator-learning architecture, it goes beyond the ANNs and CNNs employed previously. Termed Decoder-DeepONet (DDON), its main strength is learning function-to-function mappings, essential for recovering electric field profiles of unknown shape. The superior performance of DDON is exemplified via a comparison with our published CNN model and the feasibility of a classical mathematical method, as well as its application to both discharge simulations and experimental EFISH data from a nanosecond pulsed discharge. In almost all cases, the DDON model exhibits better generalizability, higher prediction accuracy, and wider applicability. Furthermore, the intrinsic nature of this operator-learning architecture renders it less sensitive to the exact location(s) of the acquired data, enabling electric field reconstruction even with seemingly 'incomplete' input profiles--an issue often accompanying poor signal sensitivity. We also employ Integrated Gradients (IG) to identify the signal regions most critical to reconstruction accuracy, providing guidance on the optimal sampling window for EFISH acquisition. Overall, we believe that the DDON model is a robust and comprehensive model which can be readily applied to reconstruct 'bell-shaped' electric field profiles with an existing axis of symmetry, especially in non-equilibrium plasmas.
Authors: Swadesh Sistla, Max Kleiman-Weiner
Abstract: Large Language Models' (LLMs) programming capabilities enable their participation in open-source games: a game-theoretic setting in which players submit computer programs in lieu of actions. These programs offer numerous advantages, including interpretability, inter-agent transparency, and formal verifiability; additionally, they enable program equilibria, solutions that leverage the transparency of code and are inaccessible within normal-form settings. We evaluate the capabilities of leading open- and closed-weight LLMs to predict and classify program strategies and evaluate features of the approximate program equilibria reached by LLM agents in dyadic and evolutionary settings. We identify the emergence of payoff-maximizing, cooperative, and deceptive strategies, characterize the adaptation of mechanisms within these programs over repeated open-source games, and analyze their comparative evolutionary fitness. We find that open-source games serve as a viable environment to study and steer the emergence of cooperative strategy in multi-agent dilemmas.
Authors: Ajit Kumar, IndraPrakash Jha
Abstract: Protein language models (PLMs) have transformed sequence-based protein analysis, yet most applications rely only on final-layer embeddings, which may overlook biologically meaningful information encoded in earlier layers. We systematically evaluate all 33 layers of ESM-2 for kinase functional prediction using both unsupervised clustering and supervised classification. We show that mid-to-late transformer layers (layers 20-33) outperform the final layer by 32 percent in unsupervised Adjusted Rand Index and improve homology-aware supervised accuracy to 75.7 percent. Domain-level extraction, calibrated probability estimates, and a reproducible benchmarking pipeline further strengthen reliability. Our results demonstrate that transformer depth contains functionally distinct biological signals and that principled layer selection significantly improves kinase function prediction.
Authors: Nikit Phadke
Abstract: We establish a precise mathematical equivalence between witness-based similarity systems (REWA) and Shannon's information theory. We prove that witness overlap is mutual information, that REWA bit complexity bounds arise from channel capacity limitations, and that ranking-preserving encodings obey rate-distortion constraints. This unification reveals that fifty years of similarity search research -- from Bloom filters to locality-sensitive hashing to neural retrieval -- implicitly developed information theory for relational data. We derive fundamental lower bounds showing that REWA's $O(\Delta^{-2} \log N)$ complexity is optimal: no encoding scheme can preserve similarity rankings with fewer bits. The framework establishes that semantic similarity has physical units (bits of mutual information), search is communication (query transmission over a noisy channel), and retrieval systems face fundamental capacity limits analogous to Shannon's channel coding theorem.
Authors: Anas Aziz Khan, Md Shah Fahad, Priyanka, Ramesh Chandra, Guransh Singh
Abstract: Accurate prediction of enzyme kinetic parameters is crucial for drug discovery, metabolic engineering, and synthetic biology applications. Current computational approaches face limitations in capturing complex enzyme-substrate interactions and often focus on single parameters while neglecting the joint prediction of catalytic turnover numbers (Kcat) and Michaelis-Menten constants (Km). We present EnzyCLIP, a novel dual-encoder framework that leverages contrastive learning and cross-attention mechanisms to predict enzyme kinetic parameters from protein sequences and substrate molecular structures. Our approach integrates ESM-2 protein language model embeddings with ChemBERTa chemical representations through a CLIP-inspired architecture enhanced with bidirectional cross-attention for dynamic enzyme-substrate interaction modeling. EnzyCLIP combines InfoNCE contrastive loss with Huber regression loss to learn aligned multimodal representations while predicting log10-transformed kinetic parameters. The model is trained on the CatPred-DB database containing 23,151 Kcat and 41,174 Km experimentally validated measurements, and achieved competitive performance with R2 scores of 0.593 for Kcat and 0.607 for Km prediction. XGBoost ensemble methods applied to the learned embeddings further improved Km prediction (R2 = 0.61) while maintaining robust Kcat performance.
Authors: Mehdi Dagdoug, Clement Dombry, Jean-Jil Duchamps
Abstract: Random Forests and Gradient Boosting are among the most effective algorithms for supervised learning on tabular data. Both belong to the class of tree-based ensemble methods, where predictions are obtained by aggregating many randomized regression trees. In this paper, we develop a theoretical framework for analyzing such methods through Reproducing Kernel Hilbert Spaces (RKHSs) constructed on tree ensembles -- more precisely, on the random partitions generated by randomized regression trees. We establish fundamental analytical properties of the resulting Random Forest kernel, including boundedness, continuity, and universality, and show that a Random Forest predictor can be characterized as the unique minimizer of a penalized empirical risk functional in this RKHS, providing a variational interpretation of ensemble learning. We further extend this perspective to the continuous-time formulation of Gradient Boosting introduced by Dombry and Duchamps, and demonstrate that it corresponds to a gradient flow on a Hilbert manifold induced by the Random Forest RKHS. A key feature of this framework is that both the kernel and the RKHS geometry are data-dependent, offering a theoretical explanation for the strong empirical performance of tree-based ensembles. Finally, we illustrate the practical potential of this approach by introducing a kernel principal component analysis built on the Random Forest kernel, which enhances the interpretability of ensemble models, as well as GVI, a new geometric variable importance criterion.
Authors: Pengyu Zeng, Yuqin Dai, Jun Yin, Jing Zhong, Ziyang Han, Chaoyang Shi, ZhanXiang Jin, Maowei Jiang, Yuxing Han, Shuai Lu
Abstract: Building design directly affects human well-being and carbon emissions, yet generating spatial-functional and energy-compliant floorplans remains manual, costly, and non-scalable. Existing methods produce visually plausible layouts but frequently violate key constraints, yielding invalid results due to the absence of automated evaluation. We present GreenPlanner, an energy- and functionality-aware generative framework that unifies design evaluation and generation. It consists of a labeled Design Feasibility Dataset for learning constraint priors; a fast Practical Design Evaluator (PDE) for predicting energy performance and spatial-functional validity; a Green Plan Dataset (GreenPD) derived from PDE-guided filtering to pair user requirements with regulation-compliant layouts; and a GreenFlow generator trained on GreenPD with PDE feedback for controllable, regulation-aware generation. Experiments show that GreenPlanner accelerates evaluation by over $10^{5}\times$ with $>$99% accuracy, eliminates invalid samples, and boosts design efficiency by 87% over professional architects.
Authors: Jonas D. Rockbach, Sven Fuchs, Maren Bennewitz
Abstract: Due to the progress in artificial intelligence, it is important to understand how capable artificial agents should be used when interacting with humans, since high level authority and responsibility often remain with the human agent. However, integrated frameworks are lacking that can account for heterogeneous agents and draw on different scientific fields, such as human-factors engineering and artificial intelligence. Therefore, joint hybrid intelligence is described as a framework abstracting humans and artificial intelligence as decision making agents. A general definition of intelligence is provided on the basis of decision making competence being applicable to agents of different sorts. This framework is used for proposing the interrelated design space of joint hybrid intelligence being aimed at integrating the heterogeneous capabilities of humans and artificial intelligence. At the core of this design space lies joint agent engineering with the goal of integrating the design subspaces operator training, artificial intelligence engineering, and interface design via developing joint agent patterns. The ''extended swarming'' approach to human-swarm interaction is discussed as an example of such a pattern.
Authors: Binghui Wu, Dinil Mon Divakaran, Levente Csikor, Mohan Gurusamy
Abstract: Tor is a widely used anonymity network that conceals user identities by routing traffic through encrypted relays, yet it remains vulnerable to traffic correlation attacks that deanonymize users by matching patterns in ingress and egress traffic. However, existing correlation methods suffer from two major limitations: limited robustness to noise and partial observations, and poor scalability due to computationally expensive pairwise matching. To address these challenges, we propose RECTor, a machine learning-based framework for traffic correlation under realistic conditions. RECTor employs attention-based Multiple Instance Learning (MIL) and GRU-based temporal encoding to extract robust flow representations, even when traffic data is incomplete or obfuscated. These embeddings are mapped into a shared space via a Siamese network and efficiently matched using approximate nearest neighbor (aNN) search. Empirical evaluations show that RECTor outperforms state-of-the-art baselines such as DeepCorr, DeepCOFFEA, and FlowTracker, achieving up to 60% higher true positive rates under high-noise conditions and reducing training and inference time by over 50%. Moreover, RECTor demonstrates strong scalability: inference cost grows near-linearly as the number of flows increases. These findings reveal critical vulnerabilities in Tor's anonymity model and highlight the need for advanced model-aware defenses.
Authors: Xiaoshan Yu, Ziwei Huang, Shangshang Yang, Ziwen Wang, Haiping Ma, Xingyi Zhang
Abstract: With the rapid advancement of intelligent education, Computerized Adaptive Testing (CAT) has attracted increasing attention by integrating educational psychology with deep learning technologies. Unlike traditional paper-and-pencil testing, CAT aims to efficiently and accurately assess examinee abilities by adaptively selecting the most suitable items during the assessment process. However, its real-time and sequential nature presents limitations in practical scenarios, particularly in large-scale assessments where interaction costs are high, or in sensitive domains such as psychological evaluations where minimizing noise and interference is essential. These challenges constrain the applicability of conventional CAT methods in time-sensitive or resourceconstrained environments. To this end, we first introduce a novel task called one-shot adaptive testing (OAT), which aims to select a fixed set of optimal items for each test-taker in a one-time selection. Meanwhile, we propose PEOAT, a Personalization-guided Evolutionary question assembly framework for One-shot Adaptive Testing from the perspective of combinatorial optimization. Specifically, we began by designing a personalization-aware initialization strategy that integrates differences between examinee ability and exercise difficulty, using multi-strategy sampling to construct a diverse and informative initial population. Building on this, we proposed a cognitive-enhanced evolutionary framework incorporating schema-preserving crossover and cognitively guided mutation to enable efficient exploration through informative signals. To maintain diversity without compromising fitness, we further introduced a diversity-aware environmental selection mechanism. The effectiveness of PEOAT is validated through extensive experiments on two datasets, complemented by case studies that uncovered valuable insights.
Authors: Arad Firouzkouhi (University of Southern California), Omid Mirzaeedodangeh (ETH Z\"urich), Lars Lindemann (ETH Z\"urich)
Abstract: Active imitation learning (AIL) combats covariate shift by querying an expert during training. However, expert action labeling often dominates the cost, especially in GPU-intensive simulators, human-in-the-loop settings, and robot fleets that revisit near-duplicate states. We present Conformalized Rejection Sampling for Active Imitation Learning (CRSAIL), a querying rule that requests an expert action only when the visited state is under-represented in the expert-labeled dataset. CRSAIL scores state novelty by the distance to the $K$-th nearest expert state and sets a single global threshold via conformal prediction. This threshold is the empirical $(1-\alpha)$ quantile of on-policy calibration scores, providing a distribution-free calibration rule that links $\alpha$ to the expected query rate and makes $\alpha$ a task-agnostic tuning knob. This state-space querying strategy is robust to outliers and, unlike safety-gate-based AIL, can be run without real-time expert takeovers: we roll out full trajectories (episodes) with the learner and only afterward query the expert on a subset of visited states. Evaluated on MuJoCo robotics tasks, CRSAIL matches or exceeds expert-level reward while reducing total expert queries by up to 96% vs. DAgger and up to 65% vs. prior AIL methods, with empirical robustness to $\alpha$ and $K$, easing deployment on novel systems with unknown dynamics.
Authors: Thomas Krug, Fabian Raisch, Dominik Aimer, Markus Wirnsberger, Ferdinand Sigg, Felix Koch, Benjamin Sch\"afer, Benjamin Tischler
Abstract: Data-driven modeling of building thermal dynamics is emerging as an increasingly important field of research for large-scale intelligent building control. However, research in data-driven modeling using machine learning (ML) techniques requires massive amounts of thermal building data, which is not easily available. Neither empirical public datasets nor existing data generators meet the needs of ML research in terms of data quality and quantity. Moreover, existing data generation approaches typically require expert knowledge in building simulation. To fill this gap, we present a thermal building data generation framework which we call BuilDa. BuilDa is designed to produce synthetic data of adequate quality and quantity for ML research. The framework does not require profound building simulation knowledge to generate large volumes of data. BuilDa uses a single-zone Modelica model that is exported as a Functional Mock-up Unit (FMU) and simulated in Python. We demonstrate BuilDa by generating data and utilizing it for a transfer learning study involving the fine-tuning of 486 data-driven models.
Authors: Eliabelle Mauduit, Elo\"ise Berthier, Andrea Simonetto
Abstract: Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings. However, for time-varying objectives, it is known that no-regret is unattainable under pure bandit feedback unless strong and often unrealistic assumptions are imposed. In this article, we propose a novel method to optimize time-varying rewards in the frequentist setting, where the objective has bounded RKHS norm. Time variations are captured through uncertainty injection (UI), which enables heteroscedastic GP regression that adapts past observations to the current time step. As no-regret is unattainable in general in the strict bandit setting, we relax the latter allowing additional queries on previously observed points. Building on sparse inference and the effect of UI on regret, we propose \textbf{W-SparQ-GP-UCB}, an online algorithm that achieves no-regret with only a vanishing number of additional queries per iteration. To assess the theoretical limits of this approach, we establish a lower bound on the number of additional queries required for no-regret, proving the efficiency of our method. Finally, we provide a comprehensive analysis linking the degree of time-variation of the function to achievable regret rates, together with upper and lower bounds on the number of additional queries needed in each regime.
Authors: Saeed Mashdour, Andr\'e R. Flores, Rodrigo C. de Lamare
Abstract: This paper presents a robust precoder design for resilient cell-free massive MIMO (CF-mMIMO) systems that minimizes the weighted sum of desired signal mean square error (MSE) and residual interference leakage power under a total transmit power constraint. The proposed robust precoder incorporates channel state information (CSI) error statistics to enhance resilience against CSI imperfections. We employ an alternating optimization algorithm initialized with a minimum MSE-type solution, which iteratively refines the precoder while maintaining low computational complexity and ensuring fast convergence. Numerical results show that the proposed method significantly outperforms conventional linear precoders, providing an effective balance between performance and computational efficiency.
Authors: S M Asiful Islam Saky, Md Rashidul Islam, Md Saiful Arefin, Shahaba Alam
Abstract: Respiratory diseases remain major global health challenges, and traditional auscultation is often limited by subjectivity, environmental noise, and inter-clinician variability. This study presents an explainable multimodal deep learning framework for automatic lung-disease detection using respiratory audio signals. The proposed system integrates two complementary representations: a spectral-temporal encoder based on a CNN-BiLSTM Attention architecture, and a handcrafted acoustic-feature encoder capturing physiologically meaningful descriptors such as MFCCs, spectral centroid, spectral bandwidth, and zero-crossing rate. These branches are combined through late-stage fusion to leverage both data-driven learning and domain-informed acoustic cues. The model is trained and evaluated on the Asthma Detection Dataset Version 2 using rigorous preprocessing, including resampling, normalization, noise filtering, data augmentation, and patient-level stratified partitioning. The study achieved strong generalization with 91.21% accuracy, 0.899 macro F1-score, and 0.9866 macro ROC-AUC, outperforming all ablated variants. An ablation study confirms the importance of temporal modeling, attention mechanisms, and multimodal fusion. The framework incorporates Grad-CAM, Integrated Gradients, and SHAP, generating interpretable spectral, temporal, and feature-level explanations aligned with known acoustic biomarkers to build clinical transparency. The findings demonstrate the framework's potential for telemedicine, point-of-care diagnostics, and real-world respiratory screening.
Authors: Tarun Chintada, Uday Kiran Cheera
Abstract: Analogy-Based Estimation (ABE) is a popular method for non-algorithmic estimation due to its simplicity and effectiveness. The Analogy-Based Estimation (ABE) model was proposed by researchers, however, no optimal approach for reliable estimation was developed. Achieving high accuracy in the ABE might be challenging for new software projects that differ from previous initiatives. This study (conducted in June 2024) proposes a Firefly Algorithm-guided Analogy-Based Estimation (FAABE) model that combines FA with ABE to improve estimation accuracy. The FAABE model was tested on five publicly accessible datasets: Cocomo81, Desharnais, China, Albrecht, Kemerer and Maxwell. To improve prediction efficiency, feature selection was used. The results were measured using a variety of evaluation metrics; various error measures include MMRE, MAE, MSE, and RMSE. Compared to conventional models, the experimental results show notable increases in prediction precision, demonstrating the efficacy of the Firefly-Analogy ensemble.
Authors: Yiqiao Chen, Zijian Huang, Juchi He, Fazheng Xu, Zhenghui Feng
Abstract: Brain-Computer Interfaces (BCIs) based on Motor Execution (ME) and Motor Imagery (MI) electroencephalogram (EEG) signals offer a direct pathway for human-machine interaction. However, developing robust decoding models remains challenging due to the complex spatio-temporal dynamics of EEG, its low signal-to-noise ratio, and the limited generalizability of many existing approaches across subjects and paradigms. To address these issues, this paper proposes Graph-guided Clustering Mixture-of-Experts CNN-GRU (GCMCG), a novel unified framework for MI-ME EEG decoding. Our approach integrates a robust preprocessing stage using Independent Component Analysis and Wavelet Transform (ICA-WT) for effective denoising. We further introduce a pre-trainable graph tokenization module that dynamically models electrode relationships via a Graph Attention Network (GAT), followed by unsupervised spectral clustering to decompose signals into interpretable functional brain regions. Each region is processed by a dedicated CNN-GRU expert network, and a gated fusion mechanism with L1 regularization adaptively combines these local features with a global expert. This Mixture-of-Experts (MoE) design enables deep spatio-temporal fusion and enhances representational capacity. A three-stage training strategy incorporating focal loss and progressive sampling is employed to improve cross-subject generalization and handle class imbalance. Evaluated on three public datasets of varying complexity (EEGmmidb-BCI2000, BCI-IV 2a, and M3CV), GCMCG achieves overall accuracies of 86.60%, 98.57%, and 99.61%, respectively, which demonstrates its superior effectiveness and strong generalization capability for practical BCI applications.
Authors: Alla Chepurova, Aydar Bulatov, Yuri Kuratov, Mikhail Burtsev
Abstract: Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain text by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication. The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets. On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods. Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3$\times$ fewer than AriGraph and $<$1/20 of GraphRAG. The proposed pipeline enhances the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs.
Authors: Bertrand Even, Luca Ganassali
Abstract: We investigate the existence of a statistical-computational gap in multiple Gaussian graph alignment. We first generalize a previously established informational threshold from Vassaux and Massouli\'e (2025) to regimes where the number of observed graphs $p$ may also grow with the number of nodes $n$: when $p \leq O(n/\log(n))$, we recover the results from Vassaux and Massouli\'e (2025), and $p \geq \Omega(n/\log(n))$ corresponds to a regime where the problem is as difficult as aligning one single graph with some unknown "signal" graph. Moreover, when $\log p = \omega(\log n)$, the informational thresholds for partial and exact recovery no longer coincide, in contrast to the all-or-nothing phenomenon observed when $\log p=O(\log n)$. Then, we provide the first computational barrier in the low-degree framework for (multiple) Gaussian graph alignment. We prove that when the correlation $\rho$ is less than $1$, up to logarithmic terms, low degree non-trivial estimation fails. Our results suggest that the task of aligning $p$ graphs in polynomial time is as hard as the problem of aligning two graphs in polynomial time, up to logarithmic factors. These results characterize the existence of a statistical-computational gap and provide another example in which polynomial-time algorithms cannot handle complex combinatorial bi-dimensional structures.
Authors: Mahmoud El Hussieni
Abstract: The increasing prevalence of thyroid cancer globally has led to the development of various computer-aided detection methods. Accurate segmentation of thyroid nodules is a critical first step in the development of AI-assisted clinical decision support systems. This study focuses on instance segmentation of thyroid nodules using YOLOv5 algorithms on ultrasound images. We evaluated multiple YOLOv5 variants (Nano, Small, Medium, Large, and XLarge) across two dataset versions, with and without doppler images. The YOLOv5-Large algorithm achieved the highest performance with a dice score of 91\% and mAP of 0.87 on the dataset including doppler images. Notably, our results demonstrate that doppler images, typically excluded by physicians, can significantly improve segmentation performance. The YOLOv5-Small model achieved 79\% dice score when doppler images were excluded, while including them improved performance across all model variants. These findings suggest that instance segmentation with YOLOv5 provides an effective real-time approach for thyroid nodule detection, with potential clinical applications in automated diagnostic systems.
Authors: Mohammed Latif Siddiq, Arvin Islam-Gomes, Natalie Sekerak, Joanna C. S. Santos
Abstract: Reproducibility is a cornerstone of scientific progress, yet its state in large language model (LLM)-based software engineering (SE) research remains poorly understood. This paper presents the first large-scale, empirical study of reproducibility practices in LLM-for-SE research. We systematically mined and analyzed 640 papers published between 2017 and 2025 across premier software engineering, machine learning, and natural language processing venues, extracting structured metadata from publications, repositories, and documentation. Guided by four research questions, we examine (i) the prevalence of reproducibility smells, (ii) how reproducibility has evolved over time, (iii) whether artifact evaluation badges reliably reflect reproducibility quality, and (iv) how publication venues influence transparency practices. Using a taxonomy of seven smell categories: Code and Execution, Data, Documentation, Environment and Tooling, Versioning, Model, and Access and Legal, we manually annotated all papers and associated artifacts. Our analysis reveals persistent gaps in artifact availability, environment specification, versioning rigor, and documentation clarity, despite modest improvements in recent years and increased adoption of artifact evaluation processes at top SE venues. Notably, we find that badges often signal artifact presence but do not consistently guarantee execution fidelity or long-term reproducibility. Motivated by these findings, we provide actionable recommendations to mitigate reproducibility smells and introduce a Reproducibility Maturity Model (RMM) to move beyond binary artifact certification toward multi-dimensional, progressive evaluation of reproducibility rigor.
Authors: Song Liu
Abstract: We study the problem of learning disentangled signals from data using non-linear Independent Component Analysis (ICA). Motivated by advances in self-supervised learning, we propose to learn self-sufficient signals: A recovered signal should be able to reconstruct a missing value of its own from all remaining components without relying on any other signals. We formulate this problem as the minimization of a conditional KL divergence. Compared to traditional maximum likelihood estimation, our algorithm is prior-free and likelihood-free, meaning that we do not need to impose any prior on the original signals or any observational model, which often restricts the model's flexibility. To tackle the KL divergence minimization problem, we propose a sequential algorithm that reduces the KL divergence and learns an optimal de-mixing flow model at each iteration. This approach completely avoids the unstable adversarial training, a common issue in minimizing the KL divergence. Experiments on toy and real-world datasets show the effectiveness of our method.
Authors: Jungwoo Ho
Abstract: We study a structured permutation scheme for two-sample testing that restricts permutations to single cross-swaps between block-selected representatives. Our analysis yields three main results. First, we provide an exact validity construction that applies to any fixed restricted permutation set. Second, for both the difference of sample means and the unbiased $\widehat{\mathrm{MMD}}^{2}$ estimator, we derive closed-form one-swap increment identities whose conditional variances scale as $O(h^{2})$, in contrast to the $\Theta(h)$ increment variability under full relabeling. This increment-level variance contraction sharpens the Bernstein--Freedman variance proxy and leads to substantially smaller permutation critical values. Third, we obtain explicit, data-dependent expressions for the resulting critical values and statistical power. Together, these results show that block-restricted one-swap permutations can achieve strictly higher power than classical full permutation tests while maintaining exact finite-sample validity, without relying on pessimistic worst-case Lipschitz bounds.
Authors: Ajinkya Borle, Charles Nicholas, Uchenna Chukwu, Mohammad-Ali Miri, Nicholas Chancellor
Abstract: Non-negative matrix factorization (NMF) is a matrix decomposition problem with applications in unsupervised learning. The general form of this problem (along with many of its variants) is NP-hard in nature. In our work, we explore how this problem could be solved with an energy-based optimization method suitable for certain machines with non-von Neumann architectures. We used the Dirac-3, a device based on the entropy computing paradigm and made by Quantum Computing Inc., to evaluate our approach. Our formulations consist of (i) a quadratic unconstrained binary optimization model (QUBO, suitable for Ising machines) and a quartic formulation that allows for real-valued and integer variables (suitable for machines like the Dirac-3). Although current devices cannot solve large NMF problems, the results of our preliminary experiments are promising enough to warrant further research. For non-negative real matrices, we observed that a fusion approach of first using Dirac-3 and then feeding its results as the initial factor matrices to Scikit-learn's NMF procedure outperforms Scikit-learn's NMF procedure on its own, with default parameters in terms of the error in the reconstructed matrices. For our experiments on non-negative integer matrices, we compared the Dirac-3 device to Google's CP-SAT solver (inside the Or-Tools package) and found that for serial processing, Dirac-3 outperforms CP-SAT in a majority of the cases. We believe that future work in this area might be able to identify domains and variants of the problem where entropy computing (and other non-von Neumann architectures) could offer a clear advantage.
Authors: Kiri L. Wagstaff
Abstract: Isolated digit classification has served as a motivating problem for decades of machine learning research. In real settings, numbers often occur as multiple digits, all written by the same person. Examples include ZIP Codes, handwritten check amounts, and appointment times. In this work, we leverage knowledge about the writers of NIST digit images to create more realistic benchmark multi-digit writer (MDW) data sets. As expected, we find that classifiers may perform well on isolated digits yet do poorly on multi-digit number recognition. If we want to solve real number recognition problems, additional advances are needed. The MDW benchmarks come with task-specific performance metrics that go beyond typical error calculations to more closely align with real-world impact. They also create opportunities to develop methods that can leverage task-specific knowledge to improve performance well beyond that of individual digit classification methods.
Authors: Mikhail Mints, Eric Anschuetz
Abstract: Hilbert space fragmentation is a phenomenon in which the Hilbert space of a quantum system is dynamically decoupled into exponentially many Krylov subspaces. We can define the Schur transform as a unitary operation mapping some set of preferred bases of these Krylov subspaces to computational basis states labeling them. We prove that this transformation can be efficiently learned via gradient descent from a set of training data using quantum neural networks, provided that the fragmentation is sufficiently strong such that the summed dimension of the unique Krylov subspaces is polynomial in the system size. To demonstrate this, we analyze the loss landscapes of random quantum neural networks constructed out of Hilbert space fragmented systems. We prove that in this setting, it is possible to eliminate barren plateaus and poor local minima, suggesting efficient trainability when using gradient descent. Furthermore, as the algebra defining the fragmentation is not known a priori and not guaranteed to have sparse algebra elements, to the best of our knowledge there are no existing efficient classical algorithms generally capable of simulating expectation values in these networks. Our setting thus provides a rare example of a physically motivated quantum learning task with no known dequantization.
Authors: Giles Winchester, George Parisis, Luc Berthouze
Abstract: Microservices have transformed software architecture through the creation of modular and independent services. However, they introduce operational complexities in service integration and system management that makes swift and accurate anomaly detection and localisation challenging. Despite the complex, dynamic, and interconnected nature of microservice architectures, prior works that investigate metrics for anomaly detection rarely include explicit information about time-varying interdependencies. And whilst prior works on fault localisation typically do incorporate information about dependencies between microservices, they scale poorly to real world large-scale deployments due to their reliance on computationally expensive causal inference. To address these challenges we propose FC-ADL, an end-to-end scalable approach for detecting and localising anomalous changes from microservice metrics based on the neuroscientific concept of functional connectivity. We show that by efficiently characterising time-varying changes in dependencies between microservice metrics we can both detect anomalies and provide root cause candidates without incurring the significant overheads of causal and multivariate approaches. We demonstrate that our approach can achieve top detection and localisation performance across a wide degree of different fault scenarios when compared to state-of-the-art approaches. Furthermore, we illustrate the scalability of our approach by applying it to Alibaba's extremely large real-world microservice deployment.
Authors: Yandong Sun, Qiang Huang, Ziwei Xu, Yiqun Sun, Yixuan Tang, Anthony K. H. Tung
Abstract: Embedding spaces are fundamental to modern AI, translating raw data into high-dimensional vectors that encode rich semantic relationships. Yet, their internal structures remain opaque, with existing approaches often sacrificing semantic coherence for structural regularity or incurring high computational overhead to improve interpretability. To address these challenges, we introduce the Semantic Field Subspace (SFS), a geometry-preserving, context-aware representation that captures local semantic neighborhoods within the embedding space. We also propose SAFARI (SemAntic Field subspAce deteRmInation), an unsupervised, modality-agnostic algorithm that uncovers hierarchical semantic structures using a novel metric called Semantic Shift, which quantifies how semantics evolve as SFSes evolve. To ensure scalability, we develop an efficient approximation of Semantic Shift that replaces costly SVD computations, achieving a 15~30x speedup with average errors below 0.01. Extensive evaluations across six real-world text and image datasets show that SFSes outperform standard classifiers not only in classification but also in nuanced tasks such as political bias detection, while SAFARI consistently reveals interpretable and generalizable semantic hierarchies. This work presents a unified framework for structuring, analyzing, and scaling semantic understanding in embedding spaces.
Authors: Xingyu Zhu, Beier Zhu, Yunfan Li, Junfeng Fang, Shuo Wang, Kesen Zhao, Hanwang Zhang
Abstract: Image clustering is a classic problem in computer vision, which categorizes images into different groups. Recent studies utilize nouns as external semantic knowledge to improve clus- tering performance. However, these methods often overlook the inherent ambiguity of nouns, which can distort semantic representations and degrade clustering quality. To address this issue, we propose a hierarChical semAntic alignmEnt method for image clustering, dubbed CAE, which improves cluster- ing performance in a training-free manner. In our approach, we incorporate two complementary types of textual seman- tics: caption-level descriptions, which convey fine-grained attributes of image content, and noun-level concepts, which represent high-level object categories. We first select relevant nouns from WordNet and descriptions from caption datasets to construct a semantic space aligned with image features. Then, we align image features with selected nouns and captions via optimal transport to obtain a more discriminative semantic space. Finally, we combine the enhanced semantic and image features to perform clustering. Extensive experiments across 8 datasets demonstrate the effectiveness of our method, notably surpassing the state-of-the-art training-free approach with a 4.2% improvement in accuracy and a 2.9% improvement in adjusted rand index (ARI) on the ImageNet-1K dataset.
Authors: Abdelghafour Halimi, Ali Alibrahim, Didier Barradas-Bautista, Ronell Sicat, Abdulkader M. Afifi
Abstract: This study presents a comprehensive deep learning pipeline for the automated classification of 12 foraminifera species using 2D micro-CT slices derived from 3D scans. We curated a scientifically rigorous dataset comprising 97 micro-CT scanned specimens across 27 species, selecting 12 species with sufficient representation for robust machine learning. To ensure methodological integrity and prevent data leakage, we employed specimen-level data splitting, resulting in 109,617 high-quality 2D slices (44,103 for training, 14,046 for validation, and 51,468 for testing). We evaluated seven state-of-the-art 2D convolutional neural network (CNN) architectures using transfer learning. Our final ensemble model, combining ConvNeXt-Large and EfficientNetV2-Small, achieved a test accuracy of 95.64%, with a top-3 accuracy of 99.6% and an area under the ROC curve (AUC) of 0.998 across all species. To facilitate practical deployment, we developed an interactive advanced dashboard that supports real-time slice classification and 3D slice matching using advanced similarity metrics, including SSIM, NCC, and the Dice coefficient. This work establishes new benchmarks for AI-assisted micropaleontological identification and provides a fully reproducible framework for foraminifera classification research, bridging the gap between deep learning and applied geosciences.
Authors: Dimitri Meunier, Jakub Wornbard, Vladimir R. Kostic, Antoine Moulin, Alek Fr\"ohlich, Karim Lounici, Massimiliano Pontil, Arthur Gretton
Abstract: We address the problem of causal effect estimation in the presence of hidden confounders using nonparametric instrumental variable (IV) regression. An established approach is to use estimators based on learned spectral features, that is, features spanning the top singular subspaces of the operator linking treatments to instruments. While powerful, such features are agnostic to the outcome variable. Consequently, the method can fail when the true causal function is poorly represented by these dominant singular functions. To mitigate, we introduce Augmented Spectral Feature Learning, a framework that makes the feature learning process outcome-aware. Our method learns features by minimizing a novel contrastive loss derived from an augmented operator that incorporates information from the outcome. By learning these task-specific features, our approach remains effective even under spectral misalignment. We provide a theoretical analysis of this framework and validate our approach on challenging benchmarks.
Authors: Somangchan Park, Heesang Ann, Min-hwan Oh
Abstract: We study the multi-objective linear contextual bandit problem, where multiple possible conflicting objectives must be optimized simultaneously. We propose \texttt{MOL-TS}, the \textit{first} Thompson Sampling algorithm with Pareto regret guarantees for this problem. Unlike standard approaches that compute an empirical Pareto front each round, \texttt{MOL-TS} samples parameters across objectives and efficiently selects an arm from a novel \emph{effective Pareto front}, which accounts for repeated selections over time. Our analysis shows that \texttt{MOL-TS} achieves a worst-case Pareto regret bound of $\widetilde{O}(d^{3/2}\sqrt{T})$, where $d$ is the dimension of the feature vectors, $T$ is the total number of rounds, matching the best known order for randomized linear bandit algorithms for single objective. Empirical results confirm the benefits of our proposed approach, demonstrating improved regret minimization and strong multi-objective performance.
Authors: Ahmed Mustafa Younes
Abstract: Transformer models have significantly advanced Natural Language Processing (NLP), demonstrating strong performance in English. However, their effectiveness in Arabic, particularly for Named Entity Recognition (NER), remains limited, even with larger pre-trained models. This performance gap stems from multiple factors, including tokenisation, dataset quality, and annotation inconsistencies. Existing studies often analyze these issues in isolation, failing to capture their joint effect on system behaviour and performance. We introduce DeformAr (Debugging and Evaluation Framework for Transformer-based NER Systems), a novel framework designed to investigate and explain the performance discrepancy between Arabic and English NER systems. DeformAr integrates a data extraction library and an interactive dashboard, supporting two modes of evaluation: cross-component analysis and behavioural analysis. The framework divides each language into dataset and model components to examine their interactions. The analysis proceeds in two stages. First, cross-component analysis provides systematic diagnostic measures across data and model subcomponents, addressing the "what," "how," and "why" behind observed discrepancies. The second stage applies behavioural analysis by combining interpretability techniques with token-level metrics, interactive visualisations, and representation space analysis. These stages enable a component-aware diagnostic process that detects model behaviours and explains them by linking them to underlying representational patterns and data factors. DeformAr is the first Arabic-specific, component-based interpretability tool, offering a crucial resource for advancing model analysis in under-resourced languages.
Authors: Mintong Kang, Chong Xiang, Sanjay Kariyappa, Chaowei Xiao, Bo Li, Edward Suh
Abstract: Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense framework based on instruction-following intent analysis. The key insight of IntentGuard is that the decisive factor in IPIAs is not the presence of malicious text, but whether the LLM intends to follow instructions from untrusted data. Building on this insight, IntentGuard leverages an instruction-following intent analyzer (IIA) to identify which parts of the input prompt the model recognizes as actionable instructions, and then flag or neutralize any overlaps with untrusted data segments. To instantiate the framework, we develop an IIA that uses three "thinking intervention" strategies to elicit a structured list of intended instructions from reasoning-enabled LLMs. These techniques include start-of-thinking prefilling, end-of-thinking refinement, and adversarial in-context demonstration. We evaluate IntentGuard on two agentic benchmarks (AgentDojo and Mind2Web) using two reasoning-enabled LLMs (Qwen-3-32B and gpt-oss-20B). Results demonstrate that IntentGuard achieves (1) no utility degradation in all but one setting and (2) strong robustness against adaptive prompt injection attacks (e.g., reducing attack success rates from 100% to 8.5% in a Mind2Web scenario).
Authors: Haotian Liang, Xinyi Chen, Bin Wang, Mingkang Chen, Yitian Liu, Yuhao Zhang, Zanxin Chen, Tianshuo Yang, Yilun Chen, Jiangmiao Pang, Dong Liu, Xiaokang Yang, Yao Mu, Wenqi Shao, Ping Luo
Abstract: A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT.
Authors: Victor Saquicela, Kenneth Palacio-Baus, Mario Chifla
Abstract: Principal Component Analysis (PCA) and K-means constitute fundamental techniques in multivariate analysis. Although they are frequently applied independently or sequentially to cluster observations, the relationship between them, especially when K-means is used to cluster variables rather than observations, has been scarcely explored. This study seeks to address this gap by proposing an innovative method that analyzes the relationship between clusters of variables obtained by applying K-means on transposed data and the principal components of PCA. Our approach involves applying PCA to the original data and K-means to the transposed data set, where the original variables are converted into observations. The contribution of each variable cluster to each principal component is then quantified using measures based on variable loadings. This process provides a tool to explore and understand the clustering of variables and how such clusters contribute to the principal dimensions of variation identified by PCA.
Authors: Dominik Luszczynski, Richard Fei Yin, Nicholas Afonin, Andrew S. P. Lim
Abstract: Objectives: We present and evaluate a Mamba-based deep-learning model for diagnosis and event-level characterization of sleep disordered breathing based on signals from the ANNE One, a non-intrusive dual-module wireless wearable system measuring chest electrocardiography, triaxial accelerometry, chest and finger temperature, and finger phototplethysmography. Methods: We obtained concurrent PSG and wearable sensor recordings from 384 adults attending a tertiary care sleep laboratory. Respiratory events in the PSG were manually annotated in accordance with AASM guidelines. Wearable sensor and PSG recordings were automatically aligned based on the ECG signal, alignment confirmed by visual inspection, and PSG-derived respiratory event labels were used to train and evaluate a deep sequential neural network based on the Mamba architecture. Results: In 57 recordings in our test set (mean age 56, mean AHI 10.8, 43.86\% female) the model-predicted AHI was highly correlated with that derived form the PSG labels (R=0.95, p=8.3e-30, men absolute error 2.83). This performance did not vary with age or sex. At a threshold of AHI$>$5, the model had a sensitivity of 0.96, specificity of 0.87, and kappa of 0.82, and at a threshold of AHI$>$15, the model had a sensitivity of 0.86, specificity of 0.98, and kappa of 0.85. At the level of 30-sec epochs, the model had a sensitivity of 0.93 and specificity of 0.95, with a kappa of 0.68 regarding whether any given epoch contained a respiratory event. Conclusions: Applied to data from the ANNE One, a Mamba-based deep learning model can accurately predict AHI and identify SDB at clinically relevant thresholds, achieves good epoch- and event-level identification of individual respiratory events, and shows promise at physiological characterization of these events including event type (central vs. other) and event duration.
Authors: Vansh Sharma, Venkat Raman
Abstract: Agentic large language models are proposed as autonomous code generators for scientific computing, yet their reliability in high-stakes problems remains unclear. Developing computational scientific software from natural-language queries remains challenging broadly due to (a) sparse representation of domain codes during training and (b) the limited feasibility of RLHF with a small expert community. To address these limitations, this work conceptualizes an inverse approach to code design, embodied in the Chain of Unit-Physics framework: a first-principles (or primitives)-centric, multi-agent system in which human expert knowledge is encoded as unit-physics tests that explicitly constrain code generation. The framework is evaluated on a nontrivial combustion task, used here as a representative benchmark for scientific problem with realistic physical constraints. Closed-weight systems and code-focused agentic variants fail to produce correct end-to-end solvers, despite tool and web access, exhibiting four recurrent error classes: interface (syntax/API) hallucinations, overconfident assumptions, numerical/physical incoherence, and configuration fragility. Open-weight models with chain-of-thought (CoT) decoding reduce interface errors but still yield incorrect solutions. On the benchmark task, the proposed framework converges within 5-6 iterations, matches the human-expert implementation (mean error of $3.1\times10^{-3}$ %), with a $\sim$33.4 % faster runtime and a $\sim$30 % efficient memory usage at a cost comparable to mid-sized commercial APIs, yielding a practical template for physics-grounded scientific code generation. As datasets and models evolve, zero-shot code accuracy will improve; however, the Chain of Unit-Physics framework goes further by embedding first-principles analysis that is foundational to scientific codes.
Authors: Jiaming Tang, Yufei Sun, Yilong Zhao, Shang Yang, Yujun Lin, Zhuoyang Zhang, James Hou, Yao Lu, Zhijian Liu, Song Han
Abstract: Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks. However, their real-world deployment remains slow and inefficient: demonstration videos are often sped up by 5-10x to appear smooth, with noticeable action stalls and delayed reactions to environmental changes. Asynchronous inference offers a promising solution to achieve continuous and low-latency control by enabling robots to execute actions and perform inference simultaneously. However, because the robot and environment continue to evolve during inference, a temporal misalignment arises between the prediction and execution intervals. This leads to significant action instability, while existing methods either degrade accuracy or introduce runtime overhead to mitigate it. We propose VLASH, a general asynchronous inference framework for VLAs that delivers smooth, accurate, and fast reaction control without additional overhead or architectural changes. VLASH estimates the future execution-time state by rolling the robot state forward with the previously generated action chunk, thereby bridging the gap between prediction and execution. Experiments show that VLASH achieves up to 2.03x speedup and reduces reaction latency by up to 17.4x compared to synchronous inference while fully preserving the original accuracy. Moreover, it empowers VLAs to handle fast-reaction, high-precision tasks such as playing ping-pong and playing whack-a-mole, where traditional synchronous inference fails. Code is available at https://github.com/mit-han-lab/vlash
Authors: Aladin Djuhera, Fernando Koch, Alecio Binotto
Abstract: Inference over large-scale foundation models within heterogeneous edge environments necessitates a fundamentally reconfigurable orchestration substrate. Static partitioning of model layers presumes temporal stability across compute and network resources, which is misaligned with the volatility of real-world deployments. We introduce a framework in which both the spatial placement and internal segmentation of foundation models are elevated to runtime-resolved constructs. The orchestration problem is formalized as a constrained optimization over layer-wise assignments, subject to evolving latency, utilization, and privacy gradients. The framework implements reactive inference composition responsive to infrastructural fluctuations by integrating model-aware capacity profiling with dynamic graph re-partitioning and reallocation. We introduce architectural and algorithmic components, along with a representative use case in 6G multi-access edge computing.
Authors: Hadi Nekoei, Alexandre Blondin Mass\'e, Rachid Hassani, Sarath Chandar, Vincent Mai
Abstract: Reinforcement learning (RL) is a powerful framework for optimizing decision-making in complex systems under uncertainty, an essential challenge in real-world settings, particularly in the context of the energy transition. A representative example is remote microgrids that supply power to communities disconnected from the main grid. Enabling the energy transition in such systems requires coordinated control of renewable sources like wind turbines, alongside fuel generators and batteries, to meet demand while minimizing fuel consumption and battery degradation under exogenous and intermittent load and wind conditions. These systems must often conform to extensive regulations and complex operational constraints. To ensure that RL agents respect these constraints, it is crucial to provide interpretable guarantees. In this paper, we introduce Shielded Controller Units (SCUs), a systematic and interpretable approach that leverages prior knowledge of system dynamics to ensure constraint satisfaction. Our shield synthesis methodology, designed for real-world deployment, decomposes the environment into a hierarchical structure where each SCU explicitly manages a subset of constraints. We demonstrate the effectiveness of SCUs on a remote microgrid optimization task with strict operational requirements. The RL agent, equipped with SCUs, achieves a 24% reduction in fuel consumption without increasing battery degradation, outperforming other baselines while satisfying all constraints. We hope SCUs contribute to the safe application of RL to the many decision-making challenges linked to the energy transition.
Authors: Tanmay Ambadkar, {\DJ}or{\dj}e \v{Z}ikeli\'c, Abhinav Verma
Abstract: Logical specifications have been shown to help reinforcement learning algorithms in achieving complex tasks. However, when a task is under-specified, agents might fail to learn useful policies. In this work, we explore the possibility of improving coarse-grained logical specifications via an exploration-guided strategy. We propose \textsc{AutoSpec}, a framework that searches for a logical specification refinement whose satisfaction implies satisfaction of the original specification, but which provides additional guidance therefore making it easier for reinforcement learning algorithms to learn useful policies. \textsc{AutoSpec} is applicable to reinforcement learning tasks specified via the SpectRL specification logic. We exploit the compositional nature of specifications written in SpectRL, and design four refinement procedures that modify the abstract graph of the specification by either refining its existing edge specifications or by introducing new edge specifications. We prove that all four procedures maintain specification soundness, i.e. any trajectory satisfying the refined specification also satisfies the original. We then show how \textsc{AutoSpec} can be integrated with existing reinforcement learning algorithms for learning policies from logical specifications. Our experiments demonstrate that \textsc{AutoSpec} yields promising improvements in terms of the complexity of control tasks that can be solved, when refined logical specifications produced by \textsc{AutoSpec} are utilized.
Authors: Shubham Aggarwal, Dipankar Maity, Tamer Ba\c{s}ar
Abstract: Accurate remote state estimation is a fundamental component of many autonomous and networked dynamical systems, where multiple decision-making agents interact and communicate over shared, bandwidth-constrained channels. These communication constraints introduce an additional layer of complexity, namely, the decision of when to communicate. This results in a fundamental trade-off between estimation accuracy and communication resource usage. Traditional extensions of classical estimation algorithms (e.g., the Kalman filter) treat the absence of communication as 'missing' information. However, silence itself can carry implicit information about the system's state, which, if properly interpreted, can enhance the estimation quality even in the absence of explicit communication. Leveraging this implicit structure, however, poses significant analytical challenges, even in relatively simple systems. In this paper, we propose CALM (Communication-Aware Learning and Monitoring), a novel learning-based framework that jointly addresses the dual challenges of communication scheduling and estimator design. Our approach entails learning not only when to communicate but also how to infer useful information from periods of communication silence. We perform comparative case studies on multiple benchmarks to demonstrate that CALM is able to decode the implicit coordination between the estimator and the scheduler to extract information from the instances of 'silence' and enhance the estimation accuracy.
Authors: Anantha Padmanaban Krishna Kumar (Boston University)
Abstract: Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on ViT-B/16 trained on ImageNet-1K, we study two simple parameter-reduction strategies applied to the MLP blocks, each removing 32.7\% of the baseline parameters. Our \emph{GroupedMLP} variant shares MLP weights between adjacent transformer blocks and achieves 81.47\% top-1 accuracy while maintaining the baseline computational cost. Our \emph{ShallowMLP} variant halves the MLP hidden dimension and reaches 81.25\% top-1 accuracy with a 38\% increase in inference throughput. Both models outperform the 86.6M-parameter baseline (81.05\%) and exhibit substantially improved training stability, reducing peak-to-final accuracy degradation from 0.47\% to the range 0.03\% to 0.06\%. These results suggest that, for ViT-B/16 on ImageNet-1K with a standard training recipe, the model operates in an overparameterized regime in which MLP capacity can be reduced without harming performance and can even slightly improve it. More broadly, our findings suggest that architectural constraints such as parameter sharing and reduced width may act as useful inductive biases, and highlight the importance of how parameters are allocated when designing Vision Transformers. All code is available at: https://github.com/AnanthaPadmanaban-KrishnaKumar/parameter-efficient-vit-mlps.
URLs: https://github.com/AnanthaPadmanaban-KrishnaKumar/parameter-efficient-vit-mlps.
Authors: Evan Dramko, Yizhi Zhu, Aleksandar Krivokapic, Geoffroy Hautier, Thomas Reps, Christopher Jermaine, Anastasios Kyrillidis
Abstract: Vital to the creation of advanced materials is performing structural relaxations. Traditional approaches built on physics-derived first-principles calculations are computationally expensive, motivating the creation of machine-learning interatomic potentials (MLIPs). Traditional approaches to training MLIPs for structural relaxations involves training models to faithfully reproduce first-principles computed forces. We propose a fine-tuning method to be used on a pretrained MLIP in which we create a fully-differentiable end-to-end simulation loop that optimizes the predicted final structures directly. Trajectories are unrolled and gradients are tracked through the entire relaxation. We show that this method achieves substantial performance gains when applied to pretrained models, leading to a nearly $50\%$ reduction in test error across the sample datasets. Interestingly, we show the process is robust to substantial variation in the relaxation setup, achieving negligibly different results across varied hyperparameter and procedural modifications. Experimental results indicate this is due to a ``preference'' of BPTT to modify the MLIP rather than the other trainable parameters. Of particular interest to practitioners is that this approach lowers the data requirements for producing an effective domain-specific MLIP, addressing a common bottleneck in practical deployment.
Authors: Benhour Amirian, Ashley S. Dale, Sergei Kalinin, Jason Hattrick-Simpers
Abstract: Accelerated material discovery increasingly relies on artificial intelligence and machine learning, collectively termed "AI/ML". A key challenge in using AI is ensuring that human scientists trust the models are valid and reliable. Accordingly, we define a trustworthy AI framework GIFTERS for materials science and discovery to evaluate whether reported machine learning methods are generalizable, interpretable, fair, transparent, explainable, robust, and stable. Through a critical literature review, we highlight that these are the trustworthiness principles most valued by the materials discovery community. However, we also find that comprehensive approaches to trustworthiness are rarely reported; this is quantified by a median GIFTERS score of 5/7. We observe that Bayesian studies frequently omit fair data practices, while non-Bayesian studies most frequently omit interpretability. Finally, we identify approaches for improving trustworthiness methods in artificial intelligence and machine learning for materials science by considering work accomplished in other scientific disciplines such as healthcare, climate science, and natural language processing with an emphasis on methods that may transfer to materials discovery experiments. By combining these observations, we highlight the necessity of human-in-the-loop, and integrated approaches to bridge the gap between trustworthiness and uncertainty quantification for future directions of materials science research. This ensures that AI/ML methods not only accelerate discovery, but also meet ethical and scientific norms established by the materials discovery community. This work provides a road map for developing trustworthy artificial intelligence systems that will accurately and confidently enable material discovery.
Authors: Stephen Fitz
Abstract: The Machine Consciousness Hypothesis states that consciousness is a substrate-free functional property of computational systems capable of second-order perception. I propose a research program to investigate this idea in silico by studying how collective self-models (coherent, self-referential representations) emerge from distributed learning systems embedded within universal self-organizing environments. The theory outlined here starts from the supposition that consciousness is an emergent property of collective intelligence systems undergoing synchronization of prediction through communication. It is not an epiphenomenon of individual modeling but a property of the language that a system evolves to internally describe itself. For a model of base reality, I begin with a minimal but general computational world: a cellular automaton, which exhibits both computational irreducibility and local reducibility. On top of this computational substrate, I introduce a network of local, predictive, representational (neural) models capable of communication and adaptation. I use this layered model to study how collective intelligence gives rise to self-representation as a direct consequence of inter-agent alignment. I suggest that consciousness does not emerge from modeling per se, but from communication. It arises from the noisy, lossy exchange of predictive messages between groups of local observers describing persistent patterns in the underlying computational substrate (base reality). It is through this representational dialogue that a shared model arises, aligning many partial views of the world. The broader goal is to develop empirically testable theories of machine consciousness, by studying how internal self-models may form in distributed systems without centralized control.
Authors: Simon Kohaut, Daniel Ochs, Shun Zhang, Benedict Flade, Julian Eggert, Kristian Kersting, Devendra Singh Dhami
Abstract: We present CycliST, a novel benchmark dataset designed to evaluate Video Language Models (VLM) on their ability for textual reasoning over cyclical state transitions. CycliST captures fundamental aspects of real-world processes by generating synthetic, richly structured video sequences featuring periodic patterns in object motion and visual attributes. CycliST employs a tiered evaluation system that progressively increases difficulty through variations in the number of cyclic objects, scene clutter, and lighting conditions, challenging state-of-the-art models on their spatio-temporal cognition. We conduct extensive experiments with current state-of-the-art VLMs, both open-source and proprietary, and reveal their limitations in generalizing to cyclical dynamics such as linear and orbital motion, as well as time-dependent changes in visual attributes like color and scale. Our results demonstrate that present-day VLMs struggle to reliably detect and exploit cyclic patterns, lack a notion of temporal understanding, and are unable to extract quantitative insights from scenes, such as the number of objects in motion, highlighting a significant technical gap that needs to be addressed. More specifically, we find no single model consistently leads in performance: neither size nor architecture correlates strongly with outcomes, and no model succeeds equally well across all tasks. By providing a targeted challenge and a comprehensive evaluation framework, CycliST paves the way for visual reasoning models that surpass the state-of-the-art in understanding periodic patterns.
Authors: Zachary Terner, Alexander Petersen, Yuedong Wang
Abstract: We introduce Smart Bayes, a new classification framework that bridges generative and discriminative modeling by integrating likelihood-ratio-based generative features into a logistic-regression-style discriminative classifier. From the generative perspective, Smart Bayes relaxes the fixed unit weights of Naive Bayes by allowing data-driven coefficients on density-ratio features. From a discriminative perspective, it constructs transformed inputs as marginal log-density ratios that explicitly quantify how much more likely each feature value is under one class than another, thereby providing predictors with stronger class separation than the raw covariates. To support this framework, we develop a spline-based estimator for univariate log-density ratios that is flexible, robust, and computationally efficient. Through extensive simulations and real-data studies, Smart Bayes often outperforms both logistic regression and Naive Bayes. Our results highlight the potential of hybrid approaches that exploit generative structure to enhance discriminative performance.
Authors: Muhammad Yousuf, Akshat Bagade, Chhittebbayi Penugonda, Maanas Baraya
Abstract: Developers routinely work with source files whose variable names are generic or misleading, and with teams moving quickly, many functions are left undocumented. This slows comprehension, increases the risk of subtle bugs, and makes it harder for both humans and large language models (LLMs) to reason about code. We study variable name repair: given a real C++ function where all occurrences of one local or parameter name have been replaced by a placeholder (e.g. ID 1), the goal is to generate a natural, descriptive replacement name. We automatically construct this task from the C++ portion of BigCode's The Stack by parsing functions with Tree-sitter, masking a single identifier, and treating the original name as supervision. On top of Llama 3.1-8B, we build a pipeline with (i) warmup and dropout schedules for more stable fine-tuning, (ii) LoRA adapters for efficient specialization on identifier repair, and (iii) a dual-encoder reranker over top-k generator candidates. We evaluate using exact match, Top-5 Hit, and an embedding-based partial similarity score (0-100) that gives credit for near synonyms and format variants (e.g., jsonValue vs. json). On a held-out set of 200 C++ functions, a zero-shot Llama 3.1 baseline reaches 6.1 percent exact match. Our best LoRA-tuned model (with warmup and dropout) achieves 43.1 percent exact match, 50.2 percent Top-5 Hit, and an 82.03 partial-match score. A dual encoder reranker further improves selection quality without modifying the underlying generator, suggesting that task-specific fine-tuning plus reranking is a promising approach for practical identifier repair tools.
Authors: Krishna Taduri (GP), Shaunak Dhande (GP), Giacinto Paolo (GP), Saggese, Paul Smith
Abstract: Predictive maintenance in manufacturing environments presents a challenging optimization problem characterized by extreme cost asymmetry, where missed failures incur costs roughly fifty times higher than false alarms. Conventional machine learning approaches typically optimize statistical accuracy metrics that do not reflect this operational reality and cannot reliably distinguish causal relationships from spurious correlations. This study evaluates eight predictive models, ranging from baseline statistical approaches to formal causal inference methods, on a dataset of 10,000 CNC machines with a 3.3% failure prevalence. The formal causal inference model (L5) achieved estimated annual cost savings of 1.16 million USD (a 70.2 percent reduction), outperforming the best correlation-based decision tree model (L3) by approximately 80,000 USD per year. The causal model matched the highest observed recall (87.9 percent) while reducing false alarms by 97 percent (from 165 to 5) and attained a precision of 92.1 percent, with a train-test performance gap of only 2.6 percentage points. These results indicate that causal AI methods, when combined with domain knowledge, can yield superior financial outcomes and more interpretable predictions compared to correlation-based approaches in predictive maintenance applications.
Authors: Han-Jin Lee, Han-Ju Lee, Jin-Seong Kim, Seok-Hwan Choi
Abstract: Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and nominal trajectories accumulate. We formalize this degradation as a path-space Kullback-Leibler divergence(path-KL) between controlled and nominal (uncontrolled) diffusion processes, thereby showing via Girsanov's theorem that it exactly equals the control energy. Building on this stochastic optimal control (SOC) view, we theoretically establish that minimizing this path-KL simultaneously tightens upper bounds on both the 2-Wasserstein distance and Fr\'echet Inception Distance (FID), revealing a principled connection between adversarial control energy and perceptual fidelity. From a variational perspective, we derive a first-order optimality condition for the control: among all directions that yield the same classification gain, the component tangent to iso-(log-)density surfaces (i.e., orthogonal to the score) minimizes path-KL, whereas the normal component directly increases distributional drift. This leads to DPAC (Distribution-Preserving Adversarial Control), a diffusion guidance rule that projects adversarial gradients onto the tangent space defined by the generative score geometry. We further show that in discrete solvers, the tangent projection cancels the O({\Delta}t) leading error term in the Wasserstein distance, achieving an O({\Delta}t^2) quality gap; moreover, it remains second-order robust to score or metric approximation. Empirical studies on ImageNet-100 validate the theoretical predictions, confirming that DPAC achieves lower FID and estimated path-KL at matched attack success rates.
Authors: Tao Xue, Yanwu Yang, Panyu Zhai
Abstract: Conversion and conversion rate (CVR) prediction play a critical role in efficient advertising decision-making. In past decades, although researchers have developed plenty of models for CVR prediction, the methodological evolution and relationships between different techniques have been precluded. In this paper, we conduct a comprehensive literature review on CVR prediction in online advertising, and classify state-of-the-art CVR prediction models into six categories with respect to the underlying techniques and elaborate on connections between these techniques. For each category of models, we present the framework of underlying techniques, their advantages and disadvantages, and discuss how they are utilized for CVR prediction. Moreover, we summarize the performance of various CVR prediction models on public and proprietary datasets. Finally, we identify research trends, major challenges, and promising future directions. We observe that results of performance evaluation reported in prior studies are not unanimous; semantics-enriched, attribution-enhanced, debiased CVR prediction and jointly modeling CTR and CVR prediction would be promising directions to explore in the future. This review is expected to provide valuable references and insights for future researchers and practitioners in this area.
Authors: Jiajia Yu, Junghwan Lee, Yao Xie, Xiuyuan Cheng
Abstract: Mean-field games (MFGs) study the Nash equilibrium of systems with a continuum of interacting agents, which can be formulated as the fixed-point of optimal control problems. They provide a unified framework for a variety of applications, including optimal transport (OT) and generative models. Despite their broad applicability, solving high-dimensional MFGs remains a significant challenge due to fundamental computational and analytical obstacles. In this work, we propose a particle-based deep Flow Matching (FM) method to tackle high-dimensional MFG computation. In each iteration of our proximal fixed-point scheme, particles are updated using first-order information, and a flow neural network is trained to match the velocity of the sample trajectories in a simulation-free manner. Theoretically, in the optimal control setting, we prove that our scheme converges to a stationary point sublinearly, and upgrade to linear (exponential) convergence under additional convexity assumptions. Our proof uses FM to induce an Eulerian coordinate (density-based) from a Lagrangian one (particle-based), and this also leads to certain equivalence results between the two formulations for MFGs when the Eulerian solution is sufficiently regular. Our method demonstrates promising performance on non-potential MFGs and high-dimensional OT problems cast as MFGs through a relaxed terminal-cost formulation.
Authors: Shan Gao, Yanwu Yang
Abstract: This research designs a unified architecture of CTR prediction benchmark (Bench-CTR) platform that offers flexible interfaces with datasets and components of a wide range of CTR prediction models. Moreover, we construct a comprehensive system of evaluation protocols encompassing real-world and synthetic datasets, a taxonomy of metrics, standardized procedures and experimental guidelines for calibrating the performance of CTR prediction models. Furthermore, we implement the proposed benchmark platform and conduct a comparative study to evaluate a wide range of state-of-the-art models from traditional multivariate statistical to modern large language model (LLM)-based approaches on three public datasets and two synthetic datasets. Experimental results reveal that, (1) high-order models largely outperform low-order models, though such advantage varies in terms of metrics and on different datasets; (2) LLM-based models demonstrate a remarkable data efficiency, i.e., achieving the comparable performance to other models while using only 2% of the training data; (3) the performance of CTR prediction models has achieved significant improvements from 2015 to 2016, then reached a stage with slow progress, which is consistent across various datasets. This benchmark is expected to facilitate model development and evaluation and enhance practitioners' understanding of the underlying mechanisms of models in the area of CTR prediction. Code is available at https://github.com/NuriaNinja/Bench-CTR.
Authors: Edward S. Hu, Jie Wang, Xingfang Yuan, Fiona Luo, Muyao Li, Gaspard Lambrechts, Oleh Rybkin, Dinesh Jayaraman
Abstract: A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard robot learning techniques struggle to produce such active perception behaviors. We propose a simple real-world robot learning recipe to efficiently train active perception policies. Our approach, asymmetric advantage weighted regression (AAWR), exploits access to "privileged" extra sensors at training time. The privileged sensors enable training high-quality privileged value functions that aid in estimating the advantage of the target policy. Bootstrapping from a small number of potentially suboptimal demonstrations and an easy-to-obtain coarse policy initialization, AAWR quickly acquires active perception behaviors and boosts task performance. In evaluations on 8 manipulation tasks on 3 robots spanning varying degrees of partial observability, AAWR synthesizes reliable active perception behaviors that outperform all prior approaches. When initialized with a "generalist" robot policy that struggles with active perception tasks, AAWR efficiently generates information-gathering behaviors that allow it to operate under severe partial observability for manipulation tasks. Website: https://penn-pal-lab.github.io/aawr/
Authors: Chunzheng Zhu, Jialin Shao, Jianxin Lin, Yijun Wang, Jing Wang, Jinhui Tang, Kenli Li
Abstract: Understanding how the brain responds to external stimuli and decoding this process has been a significant challenge in neuroscience. While previous studies typically concentrated on brain-to-image and brain-to-language reconstruction, our work strives to reconstruct gestures associated with speech stimuli perceived by brain. Unfortunately, the lack of paired \{brain, speech, gesture\} data hinders the deployment of deep learning models for this purpose. In this paper, we introduce a novel approach, \textbf{fMRI2GES}, that allows training of fMRI-to-gesture reconstruction networks on unpaired data using \textbf{Dual Brain Decoding Alignment}. This method relies on two key components: (i) observed texts that elicit brain responses, and (ii) textual descriptions associated with the gestures. Then, instead of training models in a completely supervised manner to find a mapping relationship among the three modalities, we harness an fMRI-to-text model, a text-to-gesture model with paired data and an fMRI-to-gesture model with unpaired data, establishing dual fMRI-to-gesture reconstruction patterns. Afterward, we explicitly align two outputs and train our model in a self-supervision way. We show that our proposed method can reconstruct expressive gestures directly from fMRI recordings. We also investigate fMRI signals from different ROIs in the cortex and how they affect generation results. Overall, we provide new insights into decoding co-speech gestures, thereby advancing our understanding of neuroscience and cognitive science.
Authors: Jonathan Baxter
Abstract: In this paper we investigate a neural network model in which weights between computational nodes are modified according to a local learning rule. To determine whether local learning rules are sufficient for learning, we encode the network architectures and learning dynamics genetically and then apply selection pressure to evolve networks capable of learning the four boolean functions of one variable. The successful networks are analysed and we show how learning behaviour emerges as a distributed property of the entire network. Finally the utility of genetic algorithms as a tool of discovery is discussed.
Authors: Yangbangyan Jiang, Qianqian Xu, Huiyang Shao, Zhiyong Yang, Shilong Bao, Xiaochun Cao, Qingming Huang
Abstract: As a variant of the Area Under the ROC Curve (AUC), the partial AUC (PAUC) focuses on a specific range of false positive rate (FPR) and/or true positive rate (TPR) in the ROC curve. It is a pivotal evaluation metric in real-world scenarios with both class imbalance and decision constraints. However, selecting instances within these constrained intervals during its calculation is NP-hard, and thus typically requires approximation techniques for practical resolution. Despite the progress made in PAUC optimization over the last few years, most existing methods still suffer from uncontrollable approximation errors or a limited scalability when optimizing the approximate PAUC objectives. In this paper, we close the approximation gap of PAUC optimization by presenting two simple instance-wise minimax reformulations: one with an asymptotically vanishing gap, the other with the unbiasedness at the cost of more variables. Our key idea is to first establish an equivalent instance-wise problem to lower the time complexity, simplify the complicated sample selection procedure by threshold learning, and then apply different smoothing techniques. Equipped with an efficient solver, the resulting algorithms enjoy a linear per-iteration computational complexity w.r.t. the sample size and a convergence rate of $O(\epsilon^{-1/3})$ for typical one-way and two-way PAUCs. Moreover, we provide a tight generalization bound of our minimax reformulations. The result explicitly demonstrates the impact of the TPR/FPR constraints $\alpha$/$\beta$ on the generalization and exhibits a sharp order of $\tilde{O}(\alpha^{-1}\n_+^{-1} + \beta^{-1}\n_-^{-1})$. Finally, extensive experiments on several benchmark datasets validate the strength of our proposed methods.
Authors: Samet Demir, Zafer Dogan
Abstract: Many online learning algorithms, including classical online PCA methods, enforce explicit normalization steps that discard the evolving norm of the parameter vector. We show that this norm can in fact encode meaningful information about the underlying statistical structure of the problem, and that exploiting this information leads to improved learning behavior. Motivated by this principle, we introduce Implicitly Normalized Online PCA (INO-PCA), an online PCA algorithm that removes the unit-norm constraint and instead allows the parameter norm to evolve dynamically through a simple regularized update. We prove that in the high-dimensional limit the joint empirical distribution of the estimate and the true component converges to a deterministic measure-valued process governed by a nonlinear PDE. This analysis reveals that the parameter norm obeys a closed-form ODE coupled with the cosine similarity, forming an internal state variable that regulates learning rate, stability, and sensitivity to signal-to-noise ratio (SNR). The resulting dynamics uncover a three-way relationship between the norm, SNR, and optimal step size, and expose a sharp phase transition in steady-state performance. Both theoretically and experimentally, we show that INO-PCA consistently outperforms Oja's algorithm and adapts rapidly in non-stationary environments. Overall, our results demonstrate that relaxing norm constraints can be a principled and effective way to encode and exploit problem-relevant information in online learning algorithms.
Authors: Yunchuan Zhang, Jiechen Chen, Junshuo Liu, Robert C. Qiu
Abstract: Radio resource management in modern cellular networks often calls for the optimization of complex utility functions that are potentially conflicting between different base stations (BSs). Coordinating the resource allocation strategies efficiently across BSs to ensure stable network service poses significant challenges, especially when each utility is accessible only via costly, black-box evaluations. This paper considers formulating the resource allocation among spectrum sharing BSs as a non-cooperative game, with the goal of aligning their allocation incentives toward a stable outcome. To address this challenge, we propose PPR-UCB, a novel Bayesian optimization (BO) strategy that learns from sequential decision-evaluation pairs to approximate pure Nash equilibrium (PNE) solutions. PPR-UCB applies martingale techniques to Gaussian process (GP) surrogates and constructs high probability confidence bounds for utilities uncertainty quantification. Experiments on downlink transmission power allocation in a multi-cell multi-antenna system demonstrate the efficiency of PPR-UCB in identifying effective equilibrium solutions within a few data samples.
Authors: Junfeng Wu, Xiangmin Zhou, Erica Kuligowski, Dhirendra Singh, Enrico Ronchi, Max Kinateder
Abstract: Traditional data sources on bushfire evacuation behaviour, such as quantitative surveys and manual observations have severe limitations. Mining social media data related to bushfire evacuations promises to close this gap by allowing the collection and processing of a large amount of behavioural data, which are low-cost, accurate, possibly including location information and rich contextual information. However, social media data have many limitations, such as being scattered, incomplete, informal, etc. Together, these limitations represent several challenges to their usefulness to better understand bushfire evacuation. To overcome these challenges and provide guidance on which and how social media data can be used, this scoping review of the literature reports on recent advances in relevant data mining techniques. In addition, future applications and open problems are discussed. We envision future applications such as evacuation model calibration and validation, emergency communication, personalised evacuation training, and resource allocation for evacuation preparedness. We identify open problems such as data quality, bias and representativeness, geolocation accuracy, contextual understanding, crisis-specific lexicon and semantics, and multimodal data interpretation.
Authors: Zehua Zhao, Zhixian Huang, Junren Li, Siyu Lin, Junting Zhou, Fengqi Cao, Kun Zhou, Rui Ge, Tingting Long, Yuexiang Zhu, Yan Liu, Jie Zheng, Junnian Wei, Rong Zhu, Peng Zou, Wenyu Li, Zekai Cheng, Tian Ding, Yaxuan Wang, Yizhao Yan, Tingru Wei, Haowei Ming, Weijie Mao, Chen Sun, Yiming Liu, Zichen Wang, Zuo Zhang, Tong Yang, Hao Ma, Zhen Gao, Jian Pei
Abstract: Current benchmarks for evaluating the chemical reasoning capabilities of Large Language Models (LLMs) are limited by oversimplified tasks, lack of process-level evaluation, and misalignment with expert-level chemistry skills. To address these issues, we introduce SUPERChem, a benchmark of 500 expert-curated reasoning-intensive chemistry problems, covering diverse subfields and provided in both multimodal and text-only formats. Original content and an iterative curation pipeline eliminate flawed items and mitigate data contamination. Each problem is paired with an expert-authored solution path, enabling Reasoning Path Fidelity (RPF) scoring to evaluate reasoning quality beyond final-answer accuracy. Evaluations against a human baseline of 40.3% accuracy show that even the best-performing model, GPT-5 (High), reaches only 38.5%, followed closely by Gemini 2.5 Pro (37.9%) and DeepSeek-V3.1-Think (37.3%). SUPERChem elicits multi-step, multimodal reasoning, reveals model-dependent effects of visual information, and distinguishes high-fidelity reasoners from heuristic ones. By providing a challenging benchmark and a reliable evaluation framework, SUPERChem aims to facilitate the advancement of LLMs toward expert-level chemical intelligence. The dataset of the benchmark is available at https://huggingface.co/datasets/ZehuaZhao/SUPERChem.
Authors: Guy Blanc, Caleb Koch, Jane Lange, Carmen Strassle, Li-Yang Tan
Abstract: The standard definition of PAC learning (Valiant 1984) requires learners to succeed under all distributions -- even ones that are intractable to sample from. This stands in contrast to samplable PAC learning (Blum, Furst, Kearns, and Lipton 1993), where learners only have to succeed under samplable distributions. We study this distinction and show that samplable PAC substantially expands the power of efficient learners. We first construct a concept class that requires exponential sample complexity in standard PAC but is learnable with polynomial sample complexity in samplable PAC. We then lift this statistical separation to the computational setting and obtain a separation relative to a random oracle. Our proofs center around a new complexity primitive, explicit evasive sets, that we introduce and study. These are sets for which membership is easy to determine but are extremely hard to sample from. Our results extend to the online setting to similarly show how its landscape changes when the adversary is assumed to be efficient instead of computationally unbounded.
Authors: Song Zhang, Ruohan Guo, Xiaohua Ge, Perter Mahon, Weixiang Shen
Abstract: Reliable health assessment of retired lithium-ion batteries is essential for safe and economically viable second-life deployment, yet remains difficult due to sparse measurements, incomplete historical records, heterogeneous chemistries, and limited or noisy battery health labels. Conventional laboratory diagnostics, such as full charge-discharge cycling, pulse tests, Electrochemical Impedance Spectroscopy (EIS) measurements, and thermal characterization, provide accurate degradation information but are too time-consuming, equipment-intensive, or condition-sensitive to be applied at scale during retirement-stage sorting, leaving real-world datasets fragmented and inconsistent. This review synthesizes recent advances that address these constraints through physical health indicators, experiment testing methods, data-generation and augmentation techniques, and a spectrum of learning-based modeling routes spanning supervised, semi-supervised, weakly supervised, and unsupervised paradigms. We highlight how minimal-test features, synthetic data, domain-invariant representations, and uncertainty-aware prediction enable robust inference under limited or approximate labels and across mixed chemistries and operating histories. A comparative evaluation further reveals trade-offs in accuracy, interpretability, scalability, and computational burden. Looking forward, progress toward physically constrained generative models, cross-chemistry generalization, calibrated uncertainty estimation, and standardized benchmarks will be crucial for building reliable, scalable, and deployment-ready health prediction tools tailored to the realities of retired-battery applications.
Authors: Shinji Mai, Yunpeng Zhai, Ziqian Chen, Cheng Chen, Anni Zou, Shuchang Tao, Zhaoyang Liu, Bolin Ding
Abstract: Large language model based agents are increasingly deployed in complex, tool augmented environments. While reinforcement learning provides a principled mechanism for such agents to improve through interaction, its effectiveness critically depends on the availability of structured training tasks. In many realistic settings, however, no such tasks exist a challenge we term task scarcity, which has become a key bottleneck for scaling agentic RL. Existing approaches typically assume predefined task collections, an assumption that fails in novel environments where tool semantics and affordances are initially unknown. To address this limitation, we formalize the problem of Task Generation for Agentic RL, where an agent must learn within a given environment that lacks predefined tasks. We propose CuES, a Curiosity driven and Environment grounded Synthesis framework that autonomously generates diverse, executable, and meaningful tasks directly from the environment structure and affordances, without relying on handcrafted seeds or external corpora. CuES drives exploration through intrinsic curiosity, abstracts interaction patterns into reusable task schemas, and refines them through lightweight top down guidance and memory based quality control. Across three representative environments, AppWorld, BFCL, and WebShop, CuES produces task distributions that match or surpass manually curated datasets in both diversity and executability, yielding substantial downstream policy improvements. These results demonstrate that curiosity driven, environment grounded task generation provides a scalable foundation for agents that not only learn how to act, but also learn what to learn. The code is available at https://github.com/modelscope/AgentEvolver/research/CuES.
URLs: https://github.com/modelscope/AgentEvolver/research/CuES.
Authors: Koki Natsumi, Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
Abstract: Minimum Bayes risk (MBR) decoding generates high-quality translations by maximizing the expected utility of output candidates, but it evaluates all pairwise scores over the candidate set; hence, it takes quadratic time with respect to the number of candidates. To reduce the number of utility function calls, probabilistic MBR (PMBR) decoding partially evaluates quality scores using sampled pairs of candidates and completes the missing scores with a matrix completion algorithm. Nevertheless, it degrades the translation quality as the number of utility function calls is reduced. Therefore, to improve the trade-off between quality and cost, we propose agreement-constrained PMBR (AC-PMBR) decoding, which leverages a knowledge distilled model to guide the completion of the score matrix. Our AC-PMBR decoding improved approximation errors of matrix completion by up to 3 times and achieved higher translation quality compared with PMBR decoding at a comparable computational cost on the WMT'23 En$\leftrightarrow$De translation tasks.
Authors: Juan Hernandez, Diego Fern\'andez, Manuel Cifuentes, Denis Parra, Rodrigo Toro Icarte
Abstract: The Never Give Up (NGU) algorithm has proven effective in reinforcement learning tasks with sparse rewards by combining episodic novelty and intrinsic motivation. In this work, we extend NGU to multi-agent environments and evaluate its performance in the simple_tag environment from the PettingZoo suite. Compared to a multi-agent DQN baseline, NGU achieves moderately higher returns and more stable learning dynamics. We investigate three design choices: (1) shared replay buffer versus individual replay buffers, (2) sharing episodic novelty among agents using different k thresholds, and (3) using heterogeneous values of the beta parameter. Our results show that NGU with a shared replay buffer yields the best performance and stability, highlighting that the gains come from combining NGU intrinsic exploration with experience sharing. Novelty sharing performs comparably when k = 1 but degrades learning for larger values. Finally, heterogeneous beta values do not improve over a small common value. These findings suggest that NGU can be effectively applied in multi-agent settings when experiences are shared and intrinsic exploration signals are carefully tuned.
Authors: Omar Farooq Khan Suri, John McCrae
Abstract: Large Language Models (LLMs) are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specific fine-tuning approach that trains non-instruction-tuned base models to perform a single function, thereby reducing susceptibility to adversarial instructions. In this study, we evaluate the robustness of JATMO against HOUYI, a genetic attack framework that systematically mutates and optimizes adversarial prompts. We adapt HOUYI by introducing custom fitness scoring, modified mutation logic, and a new harness for local model testing, enabling a more accurate assessment of defense effectiveness. We fine-tuned LLaMA 2-7B, Qwen1.5-4B, and Qwen1.5-0.5B models under the JATMO methodology and compared them with a fine-tuned GPT-3.5-Turbo baseline. Results show that while JATMO reduces attack success rates relative to instruction-tuned models, it does not fully prevent injections; adversaries exploiting multilingual cues or code-related disruptors still bypass defenses. We also observe a trade-off between generation quality and injection vulnerability, suggesting that better task performance often correlates with increased susceptibility. Our results highlight both the promise and limitations of fine-tuning-based defenses and point toward the need for layered, adversarially informed mitigation strategies.
Authors: A S M Ahsanul Sarkar Akib, Raduana Khawla, Abdul Hasib
Abstract: Stroke is a major cause of death and permanent impairment, making it a major worldwide health concern. For prompt intervention and successful preventative tactics, early risk assessment is essential. To address this challenge, we used ensemble modeling and explainable AI (XAI) techniques to create an interpretable machine learning framework for stroke risk prediction. A thorough evaluation of 10 different machine learning models using 5-fold cross-validation across several datasets was part of our all-inclusive strategy, which also included feature engineering and data pretreatment (using Random Over-Sampling (ROS) to solve class imbalance). Our optimized ensemble model (Random Forest + ExtraTrees + XGBoost) performed exceptionally well, obtaining a strong 99.09% accuracy on the Stroke Prediction Dataset (SPD). We improved the model's transparency and clinical applicability by identifying three important clinical variables using LIME-based interpretability analysis: age, hypertension, and glucose levels. Through early prediction, this study highlights how combining ensemble learning with explainable AI (XAI) can deliver highly accurate and interpretable stroke risk assessment. By enabling data-driven prevention and personalized clinical decisions, our framework has the potential to transform stroke prediction and cardiovascular risk management.
Authors: Zhongjie Jiang
Abstract: Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human text. Prolonged training on such statistically optimal but cognitively impoverished data accelerates model collapse. This paper proposes a paradigm shift: instead of imitating the surface properties of data, we simulate the cognitive processes that generate human text. We introduce the Prompt-driven Cognitive Computing Framework (PMCSF), whose core consists of a Cognitive State Decoder (CSD) that reverse-engineers unstructured text into structured cognitive vectors, and a Cognitive Text Encoder (CTE) that re-materializes these states into text enriched with human-typical imperfections via mathematically defined Cognitive Perturbation Operators. The framework is validated through a two-stage objective evaluation pipeline. First, in cognitive codec verification, CTE text yields a Jensen-Shannon divergence of 0.0614 from human text (vs. 0.4431 for standard LLM output), passes double-blind professional media review, and achieves an intraclass correlation coefficient ICC > 0.9 for cognitive profile alignment across heterogeneous models. Second, in functional gain evaluation, isomorphic stress tests in the A-share market show that strategies incorporating CTE-generated data reduce maximum drawdown by 47.4% during the 2015 crash and deliver 8.6% Defensive Alpha, exceeding transaction costs by a factor of 33. Our findings demonstrate that modelling human cognitive limitations -- not copying surface data -- enables synthetic data with genuine functional gain, offering a viable technical pathway toward resolving the AI data-collapse crisis.
Authors: Junsung Park, Hogun Kee, Songhwai Oh
Abstract: This paper presents a modality-augmented fine-tuning framework designed to adapt foundation robot policies to diverse humanoid embodiments. We validate our approach across two distinct settings: (i) the GR1 embodiment, utilizing public datasets where we introduce post-processed modalities, including binary contact signals and ZoeDepth-generated metric depth; and (ii) the Unitree G1 embodiment, for which we contribute a novel multi-modal dataset incorporating cuRobo motion planning, inverse kinematics, and ground-truth contact-force measurements. Our experiments demonstrate that modality augmentation consistently enhances policy performance across different embodiments. Specifically, for the GR1, integrating contact-state cues and RGB-D fusion improves online success rates from 51% to 63%. Furthermore, in the G1 "Pick Apple to Bowl" task, our contact-augmented model achieves a success rate of 94%, significantly outperforming the 48% achieved by standard fine-tuning and the 0% baseline of zero-shot transfer. These results highlight that lightweight post-processing effectively strengthens policies for GR1, while high-quality multi-modal data is crucial for reliable transfer to the Unitree G1. Consequently, this work establishes a unified, data-centric pathway for extending foundation robot policies through targeted modality design and multi-modal fine-tuning.
Authors: Jiaguo Tian, Zhengbang Zhu, Shenyu Zhang, Li Xu, Bo Zheng, Xu Liu, Weiji Peng, Shizeng Yao, Weinan Zhang
Abstract: The generation of realistic and diverse traffic scenarios in simulation is essential for developing and evaluating autonomous driving systems. However, most simulation frameworks rely on rule-based or simplified models for scene generation, which lack the fidelity and diversity needed to represent real-world driving. While recent advances in generative modeling produce more realistic and context-aware traffic interactions, they often overlook how social preferences influence driving behavior. SocialDriveGen addresses this gap through a hierarchical framework that integrates semantic reasoning and social preference modeling with generative trajectory synthesis. By modeling egoism and altruism as complementary social dimensions, our framework enables controllable diversity in driver personalities and interaction styles. Experiments on the Argoverse 2 dataset show that SocialDriveGen generates diverse, high-fidelity traffic scenarios spanning cooperative to adversarial behaviors, significantly enhancing policy robustness and generalization to rare or high-risk situations.
Authors: Swati Kumari, Shiva Raj Pokhrel, Swathi Chandrasekhar, Navneet Singh, Hridoy Sankar Dutta, Adnan Anwar, Sutharshan Rajasegarar, Robin Doss
Abstract: Network traffic anomaly detection is a critical cy- bersecurity challenge requiring robust solutions for complex Internet of Things (IoT) environments. We present a novel hybrid quantum-classical framework integrating an enhanced Quantum Support Vector Machine (QSVM) with the Quantum Haar Wavelet Packet Transform (QWPT) for superior anomaly classification under realistic noisy intermediate-scale Quantum conditions. Our methodology employs amplitude-encoded quan- tum state preparation, multi-level QWPT feature extraction, and behavioral analysis via Shannon Entropy profiling and Chi-square testing. Features are classified using QSVM with fidelity-based quantum kernels optimized through hybrid train- ing with simultaneous perturbation stochastic approximation (SPSA) optimizer. Evaluation under noiseless and depolarizing noise conditions demonstrates exceptional performance: 96.67% accuracy on BoT-IoT and 89.67% on IoT-23 datasets, surpassing quantum autoencoder approaches by over 7 percentage points.
Authors: Yunzhe Li, Jiajun Yan, Yuzhou Wei, Kechen Liu, Yize Zhao, Chong Zhang, Hongzi Zhu, Li Lu, Shan Chang, Minyi Guo
Abstract: Failing to be aware of speeding vehicles approaching from behind poses a huge threat to the road safety of pedestrians and cyclists. In this paper, we propose BlinkBud, which utilizes a single earbud and a paired phone to online detect hazardous objects approaching from behind of a user. The core idea is to accurately track visually identified objects utilizing a small number of sampled camera images taken from the earbud. To minimize the power consumption of the earbud and the phone while guaranteeing the best tracking accuracy, a novel 3D object tracking algorithm is devised, integrating both a Kalman filter based trajectory estimation scheme and an optimal image sampling strategy based on reinforcement learning. Moreover, the impact of constant user head movements on the tracking accuracy is significantly eliminated by leveraging the estimated pitch and yaw angles to correct the object depth estimation and align the camera coordinate system to the user's body coordinate system, respectively. We implement a prototype BlinkBud system and conduct extensive real-world experiments. Results show that BlinkBud is lightweight with ultra-low mean power consumptions of 29.8 mW and 702.6 mW on the earbud and smartphone, respectively, and can accurately detect hazards with a low average false positive ratio (FPR) and false negative ratio (FNR) of 4.90% and 1.47%, respectively.
Authors: Oguz Bedir (Electrical & Computer Engineering, Texas A&M University, USA), Nurullah Sevim (Electrical & Computer Engineering, Texas A&M University, USA), Mostafa Ibrahim (Engineering Technology & Industrial Distribution, Texas A&M University, USA), Sabit Ekin (Engineering Technology & Industrial Distribution, Texas A&M University, USA, Electrical & Computer Engineering, Texas A&M University, USA)
Abstract: Recent breakthroughs in natural language processing show that attention mechanism in Transformer networks, trained via masked-token prediction, enables models to capture the semantic context of the tokens and internalize the grammar of language. While the application of Transformers to communication systems is a burgeoning field, the notion of context within physical waveforms remains under-explored. This paper addresses that gap by re-examining inter-symbol contribution (ISC) caused by pulse-shaping overlap. Rather than treating ISC as a nuisance, we view it as a deterministic source of contextual information embedded in oversampled complex baseband signals. We propose Masked Symbol Modeling (MSM), a framework for the physical (PHY) layer inspired by Bidirectional Encoder Representations from Transformers methodology. In MSM, a subset of symbol aligned samples is randomly masked, and a Transformer predicts the missing symbol identifiers using the surrounding "in-between" samples. Through this objective, the model learns the latent syntax of complex baseband waveforms. We illustrate MSM's potential by applying it to the task of demodulating signals corrupted by impulsive noise, where the model infers corrupted segments by leveraging the learned context. Our results suggest a path toward receivers that interpret, rather than merely detect communication signals, opening new avenues for context-aware PHY layer design.
Authors: Xabier de Zuazo, Ibon Saratxaga, Eva Navas
Abstract: We present Conformer-based decoders for the LibriBrain 2025 PNPL competition, targeting two foundational MEG tasks: Speech Detection and Phoneme Classification. Our approach adapts a compact Conformer to raw 306-channel MEG signals, with a lightweight convolutional projection layer and task-specific heads. For Speech Detection, a MEG-oriented SpecAugment provided a first exploration of MEG-specific augmentation. For Phoneme Classification, we used inverse-square-root class weighting and a dynamic grouping loader to handle 100-sample averaged examples. In addition, a simple instance-level normalization proved critical to mitigate distribution shifts on the holdout split. Using the official Standard track splits and F1-macro for model selection, our best systems achieved 88.9% (Speech) and 65.8% (Phoneme) on the leaderboard, surpassing the competition baselines and ranking within the top-10 in both tasks. For further implementation details, the technical documentation, source code, and checkpoints are available at https://github.com/neural2speech/libribrain-experiments.
URLs: https://github.com/neural2speech/libribrain-experiments.
Authors: Jozef Kub\'ik, Marek \v{S}uppa, Martin Tak\'a\v{c}
Abstract: Limited data for low-resource languages typically yield weaker language models (LMs). Since pre-training is compute-intensive, it is more pragmatic to target improvements during fine-tuning. In this work, we examine the use of Active Learning (AL) methods augmented by structured data selection strategies which we term 'Active Learning schedulers', to boost the fine-tuning process with a limited amount of training data. We connect the AL to data clustering and propose an integrated fine-tuning pipeline that systematically combines AL, clustering, and dynamic data selection schedulers to enhance model's performance. Experiments in the Slovak, Maltese, Icelandic and Turkish languages show that the use of clustering during the fine-tuning phase together with AL scheduling can simultaneously produce annotation savings up to 30% and performance improvements up to four F1 score points, while also providing better fine-tuning stability.
Authors: Jan-Frederik Schulte, Benjamin Ramhorst, Chang Sun, Jovan Mitrevski, Nicol\`o Ghielmetti, Enrico Lupi, Dimitrios Danopoulos, Vladimir Loncar, Javier Duarte, David Burnette, Lauri Laatu, Stylianos Tzelepis, Konstantinos Axiotis, Quentin Berthet, Haoyan Wang, Paul White, Suleyman Demirsoy, Marco Colombo, Thea Aarrestad, Sioni Summers, Maurizio Pierini, Giuseppe Di Guglielmo, Jennifer Ngadiuba, Javier Campos, Ben Hawks, Abhijith Gandrakota, Farah Fahim, Nhan Tran, George Constantinides, Zhiqiang Que, Wayne Luk, Alexander Tapper, Duc Hoang, Noah Paladino, Philip Harris, Bo-Cheng Lai, Manuel Valentin, Ryan Forelli, Seda Ogrenci, Lino Gerlach, Rian Flynn, Mia Liu, Daniel Diaz, Elham Khoda, Melissa Quinnan, Russell Solares, Santosh Parajuli, Mark Neubauer, Christian Herwig, Ho Fung Tsoi, Dylan Rankin, Shih-Chieh Hsu, Scott Hauck
Abstract: We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). With its flexible and modular design, hls4ml supports a large number of deep learning frameworks and can target HLS compilers from several vendors, including Vitis HLS, Intel oneAPI and Catapult HLS. Together with a wider eco-system for software-hardware co-design, hls4ml has enabled the acceleration of ML inference in a wide range of commercial and scientific applications where low latency, resource usage, and power consumption are critical. In this paper, we describe the structure and functionality of the hls4ml platform. The overarching design considerations for the generated HLS code are discussed, together with selected performance results.
Authors: Jindi Lv, Yuhao Zhou, Zheng Zhu, Xiaofeng Wang, Guan Huang, Jiancheng Lv
Abstract: Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible alternatives. Recent methods attempt to address this by generating soft abstract tokens to enable reasoning in a continuous semantic space. However, we find that such approaches remain constrained by the greedy nature of autoregressive decoding, which fundamentally isolates the model from alternative reasoning possibilities. In this work, we propose Multi-Path Perception Policy Optimization (M3PO), a novel reinforcement learning framework that explicitly injects collective insights into the reasoning process. M3PO leverages parallel policy rollouts as naturally diverse reasoning sources and integrates cross-path interactions into policy updates through a lightweight collaborative mechanism. This design allows each trajectory to refine its reasoning with peer feedback, thereby cultivating more reliable multi-step reasoning patterns. Empirical results show that M3PO achieves state-of-the-art performance on both knowledge- and reasoning-intensive benchmarks. Models trained with M3PO maintain interpretability and inference efficiency, underscoring the promise of multi-path collaborative learning for robust reasoning.
Authors: Tuguldur Bayarsaikhan, Altannar Chinchuluun, Ashwin Arulselvan, Panos Pardalos
Abstract: Given a network, the critical node detection problem finds a subset of nodes whose removal disrupts the network connectivity. Since many real-world systems are naturally modeled as graphs, assessing the vulnerability of the network is essential, with applications in transportation systems, traffic forecasting, epidemic control, and biological networks. In this paper, we consider a stochastic version of the critical node detection problem, where the existence of edges is given by certain probabilities. We propose heuristics and learning-based methods for the problem and compare them with existing algorithms. Experimental results performed on random graphs from small to larger scales, with edge-survival probabilities drawn from different distributions, demonstrate the effectiveness of the methods. Heuristic methods often illustrate the strongest results with high scalability, while learning-based methods maintain nearly constant inference time as the network size and density grow.
Authors: Daniel Armstrong, Zlatko Jon\v{c}ev, Andres M Bran, Philippe Schwaller
Abstract: Modern computer-assisted synthesis planning (CASP) systems show promises at generating chemically valid reaction steps but struggle to incorporate strategic considerations such as convergent assembly, protecting group minimization, and optimal ring-forming sequences. We introduce a methodology that leverages Large Language Models to distill synthetic knowledge into code. Our system analyzes synthesis routes and translates strategic principles into Python functions representing diverse strategic and tactical rules, such as strategic functional group interconversions and ring construction strategies. By formalizing this knowledge as verifiable code rather than simple heuristics, we create testable, interpretable representations of synthetic strategy. We release the complete codebase and the USPTO-ST dataset -- synthesis routes annotated with strategic tags. This framework unlocks a novel capability for CASP: natural language-based route retrieval, achieving 75\% Top-3 accuracy on our benchmark. We further validate our library through temporal analysis of historical trends and chemically intuitive route clustering that offers more granular partitioning than common previous methods. This work bridges the tactical-strategic divide in CASP, enabling specification, search, and evaluation of routes by strategic criteria rather than structure alone.
Authors: Patrick Odagiu, Vasilis Belis, Lennart Schulze, Panagiotis Barkoutsos, Michele Grossi, Florentin Reiter, G\"unther Dissertori, Ivano Tavernelli, Sofia Vallecorsa
Abstract: Data sets that are specified by a large number of features are currently outside the area of applicability for quantum machine learning algorithms. An immediate solution to this impasse is the application of dimensionality reduction methods before passing the data to the quantum algorithm. We investigate six conventional feature extraction algorithms and five autoencoder-based dimensionality reduction models to a particle physics data set with 67 features. The reduced representations generated by these models are then used to train a quantum support vector machine for solving a binary classification problem: whether a Higgs boson is produced in proton collisions at the LHC. We show that the autoencoder methods learn a better lower-dimensional representation of the data, with the method we design, the Sinkclass autoencoder, performing 40% better than the baseline. The methods developed here open up the applicability of quantum machine learning to a larger array of data sets. Moreover, we provide a recipe for effective dimensionality reduction in this context.
Authors: Franz Thaler, Martin Urschler, Mateusz Kozinski, Matthias AF Gsell, Gernot Plank, Darko Stern
Abstract: We tackle the challenging problem of single-source domain generalization (DG) for medical image segmentation. To this end, we aim for training a network on one domain (e.g., CT) and directly apply it to a different domain (e.g., MR) without adapting the model and without requiring images or annotations from the new domain during training. We propose a novel method for promoting DG when training deep segmentation networks, which we call SRCSM. During training, our method diversifies the source domain through semantic-aware random convolution, where different regions of a source image are augmented differently, based on their annotation labels. At test-time, we complement the randomization of the training domain via mapping the intensity of target domain images, making them similar to source domain data. We perform a comprehensive evaluation on a variety of cross-modality and cross-center generalization settings for abdominal, whole-heart and prostate segmentation, where we outperform previous DG techniques in a vast majority of experiments. Additionally, we also investigate our method when training on whole-heart CT or MR data and testing on the diastolic and systolic phase of cine MR data captured with different scanner hardware, where we make a step towards closing the domain gap in this even more challenging setting. Overall, our evaluation shows that SRCSM can be considered a new state-of-the-art in DG for medical image segmentation and, moreover, even achieves a segmentation performance that matches the performance of the in-domain baseline in several settings.
Authors: Sigurd Vargdal, Paula Reis, Henrik Andersen Sveinsson, Gaute Linga
Abstract: Permeability is a central concept in the macroscopic description of flow through porous media, with applications spanning from oil recovery to hydrology. Traditional methods for determining the permeability tensor involving flow simulations or experiments can be time consuming and resource-intensive, while analytical methods, e.g., based on the Kozeny-Carman equation, may be too simplistic for accurate prediction based on pore-scale features. In this work, we explore deep learning as a more efficient alternative for predicting the permeability tensor based on two-dimensional binary images of porous media, segmented into solid ($1$) and void ($0$) regions. We generate a dataset of 24,000 synthetic random periodic porous media samples with specified porosity and characteristic length scale. Using Lattice-Boltzmann simulations, we compute the permeability tensor for flow through these samples with values spanning three orders of magnitude. We evaluate three families of image-based deep learning models: ResNet (ResNet-$50$ and ResNet-$101$), Vision Transformers (ViT-T$16$ and ViT-S$16$) and ConvNeXt (Tiny and Small). To improve model generalisation, we employ techniques such as weight decay, learning rate scheduling, and data augmentation. The effect of data augmentation and dataset size on model performance is studied, and we find that they generally increase the accuracy of permeability predictions. We also show that ConvNeXt and ResNet converge faster than ViT and degrade in performance if trained for too long. ConvNeXt-Small achieved the highest $R^2$ score of $0.99460$ on $4,000$ unseen test samples. These findings underscore the potential to use image-based neural networks to predict permeability tensors accurately.
Authors: Tal Shuster, Eliya Nachmani
Abstract: Recent neural audio codecs have achieved impressive reconstruction quality, typically relying on quantization methods such as Residual Vector Quantization (RVQ), Vector Quantization (VQ) and Finite Scalar Quantization (FSQ). However, these quantization techniques limit the geometric structure of the latent space, make it harder to capture correlations between features leading to inefficiency in representation learning, codebook utilization and token rate. In this paper we introduce Two Dimensional Quantization (Q2D2), a quantization scheme in which feature pairs are projected onto structured 2D grids such as hexagonal, rhombic, or rectangular tiling and quantized to the nearest grid values, yielding an implicit codebook defined by the product of grid levels, with codebook sizes comparable to conventional methods. Despite its simple geometric formulation, Q2D2 improves audio compression efficiency, with low token rates and high codebook utilization while maintaining state of the art reconstruction quality. Specifically, Q2D2 achieves competitive to superior performance in various objective and subjective reconstruction metrics, across extensive experiments in speech domain compared to state of the art models. Comprehensive ablation studies further confirm the effectiveness of our design choices.
Authors: Yuma Ichikawa, Yudai Fujimoto, Akira Sakai
Abstract: Post-training quantization (PTQ) aims to preserve model-level behavior; however, most methods focus on individual linear layers. Even recent extensions, such as QEP and LoaQ, which mitigate error propagation or target specific submodules, still rely on layer-wise formulations and fail to capture the behavior of larger submodules. We introduce Layer-Projected Coordinate Descent (LPCD), a unified framework that extends PTQ beyond layers by optimizing relaxed objectives across arbitrary submodules and projecting the solutions with layer-wise quantizers. LPCD generalizes existing methods and provides a principled approach to quantizing complex submodules while maintaining the efficiency and compatibility of layer-wise PTQ pipelines. Across diverse LLM architectures and bit-widths, LPCD-based submodule quantization consistently enhances both layer-wise PTQ methods and existing submodule approaches.
Authors: Zhiyuan Wang, Aniri, Tianlong Chen, Yue Zhang, Heng Tao Shen, Xiaoshuang Shi, Kaidi Xu
Abstract: Large language models (LLMs) often generate unreliable answers, while heuristic uncertainty methods fail to fully distinguish correct from incorrect predictions, causing users to accept erroneous answers without statistical guarantees. We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level. To achieve this in a principled way, we propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint over selection and error indicators. Then, we establish a finite-sample sufficient condition, which relies only on a held-out set of exchangeable calibration samples, to compute an FDR-constrained, coverage-maximizing threshold. Furthermore, we extend LEC to a two-model routing mechanism: given a prompt, if the current model's uncertainty exceeds its calibrated threshold, we delegate it to a stronger model, while maintaining a unified FDR guarantee. Evaluations on closed-ended and open-ended question-answering (QA) datasets show that LEC achieves tighter FDR control and substantially improves sample retention over prior methods. Moreover, the two-model routing mechanism achieves lower risk levels while accepting more correct samples than each individual model.
Authors: Yiqiao Chen, Fazheng Xu, Zijian Huang, Juchi He, Zhenghui Feng
Abstract: Cardiovascular disease (CVD) is a leading cause of morbidity and mortality worldwide, and sustained hypertension is an often silent risk factor, making cuffless continuous blood pressure (BP) monitoring with wearable devices important for early screening and long-term management. Most existing cuffless BP estimation methods use only photoplethysmography (PPG) and electrocardiography (ECG) signals, alone or in combination. These models are typically developed under resting or quasi-static conditions and struggle to maintain robust accuracy in multi-motion-state scenarios. In this study, we propose a six-modal BP estimation framework that jointly leverages ECG, multi-channel PPG, attachment pressure, sensor temperature, and triaxial acceleration and angular velocity. Each modality is processed by a lightweight branch encoder, contrastive learning enforces cross-modal semantic alignment, and a mixture-of-experts (MoE) regression head adaptively maps the fused features to BP across motion states. Comprehensive experiments on the public Pulse Transit Time PPG Dataset, which includes running, walking, and sitting data from 22 subjects, show that the proposed method achieves mean absolute errors (MAE) of 3.60 mmHg for systolic BP (SBP) and 3.01 mmHg for diastolic BP (DBP). From a clinical perspective, it attains Grade A for SBP, DBP, and mean arterial pressure (MAP) according to the British Hypertension Society (BHS) protocol and meets the numerical criteria of the Association for the Advancement of Medical Instrumentation (AAMI) standard for mean error (ME) and standard deviation of error (SDE).
Authors: Jimin Choi, Max Z. Li
Abstract: Collaborative Combat Aircraft (CCAs) are envisioned to enable autonomous Intelligence, Surveillance, and Reconnaissance (ISR) missions in contested environments, where adversaries may act strategically to deceive or evade detection. These missions pose challenges due to model uncertainty and the need for safe, real-time decision-making. Robust Markov Decision Processes (RMDPs) provide worst-case guarantees but are limited by static ambiguity sets that capture initial uncertainty without adapting to new observations. This paper presents an adaptive RMDP framework tailored to ISR missions with CCAs. We introduce a mission-specific formulation in which aircraft alternate between movement and sensing states. Adversarial tactics are modeled as a finite set of transition kernels, each capturing assumptions about how adversarial sensing or environmental conditions affect rewards. Our approach incrementally refines policies by eliminating inconsistent threat models, allowing agents to shift from conservative to aggressive behaviors while maintaining robustness. We provide theoretical guarantees showing that the adaptive planner converges as credible sets contract to the true threat and maintains safety under uncertainty. Experiments under Gaussian and non-Gaussian threat models across diverse network topologies show higher mission rewards and fewer exposure events compared to nominal and static robust planners.
Authors: Ghita Fassy El Fehri, Aur\'elien Bellet, Philippe Bastien
Abstract: Learning the structure of a Bayesian network from decentralized data poses two major challenges: (i) ensuring rigorous privacy guarantees for participants, and (ii) avoiding communication costs that scale poorly with dimensionality. In this work, we introduce Fed-Sparse-BNSL, a novel federated method for learning linear Gaussian Bayesian network structures that addresses both challenges. By combining differential privacy with greedy updates that target only a few relevant edges per participant, Fed-Sparse-BNSL efficiently uses the privacy budget while keeping communication costs low. Our careful algorithmic design preserves model identifiability and enables accurate structure estimation. Experiments on synthetic and real datasets demonstrate that Fed-Sparse-BNSL achieves utility close to non-private baselines while offering substantially stronger privacy and communication efficiency.
Authors: Louis Lacoste, Pierre Barbillon, Sophie Donnet
Abstract: Bipartite networks are widely used to encode the ecological interactions. Being able to compare the organization of bipartite networks is a first step toward a better understanding of how environmental factors shape community structure and resilience. Yet current methods for structure detection in bipartite networks overlook shared patterns across collections of networks. We introduce the \emph{colBiSBM}, a family of probabilistic models for collections of bipartite networks that extends the classical Latent Block Model (LBM). The proposed framework assumes that networks are independent realizations of a shared mesoscale structure, encoded through common inter-block connectivity parameters. We establish identifiability conditions for the different variants of \emph{colBiSBM} and develop a variational EM algorithm for parameter estimation, coupled with an adaptation of the Integrated Classification Likelihood (ICL) criterion for model selection. We demonstrate how our approach can be used to classify networks based on their topology or organization. Simulation studies highlight the ability of \emph{colBiSBM} to recover common structures, improve clustering performance, and enhance link prediction by borrowing strength across networks. An application to plant--pollinator networks highlights how the method uncovers shared ecological roles and partitions networks into sub-collections with similar connectivity patterns. These results illustrate the methodological and practical advantages of joint modeling over separate network analyses in the study of bipartite systems.
Authors: Kai Zhang, Wentao Yu, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief
Abstract: Integrated sensing and communication (ISAC) is a key enabler for low-altitude wireless networks (LAWNs), providing simultaneous environmental perception and data transmission in complex aerial scenarios. By combining heterogeneous sensing modalities such as visual, radar, lidar, and positional information, multimodal ISAC can improve both situational awareness and robustness of LAWNs. However, most existing multimodal fusion approaches use static fusion strategies that treat all modalities equally and cannot adapt to channel heterogeneity or time-varying modality reliability in dynamic low-altitude environments. To address this fundamental limitation, we propose a mixture-of-experts (MoE) framework for multimodal ISAC in LAWNs. Each modality is processed by a dedicated expert network, and a lightweight gating module adaptively assigns fusion weights according to the instantaneous informativeness and reliability of each modality. To improve scalability under the stringent energy constraints of aerial platforms, we further develop a sparse MoE variant that selectively activates only a subset of experts, thereby reducing computation overhead while preserving the benefits of adaptive fusion. Comprehensive simulations on three typical ISAC tasks in LAWNs demonstrate that the proposed frameworks consistently outperform conventional multimodal fusion baselines in terms of learning performance and training sample efficiency.
Authors: Xiaochuan Li, Ke Wang, Girija Gouda, Shubham Choudhary, Yaqun Wang, Linwei Hu, Joel Vaughan, Freddy Lecue
Abstract: As Large Language Models (LLMs) become integrated into high-stakes domains, there is a growing need for evaluation methods that are both scalable for real-time deployment and reliable for critical decision-making. While human evaluation is reliable, it is slow and costly. Single LLM judges are biased, and static juries lack adaptability. To overcome these limitations, we propose LLM Jury-on-Demand - a dynamic, learning-based framework for scalable and context-aware evaluation. Our method trains a set of reliability predictors to assess when LLM judges will agree with human experts, leveraging token distributions, embeddings, and structural input features. This enables a fully adaptive evaluation where, for each data point, an optimal jury of the most reliable judges is dynamically selected, and their scores are aggregated using their reliability as weights. Experiments on summarization and RAG benchmarks show that our dynamic jury system achieves significantly higher correlation with human judgment than both single-judge and static-jury baselines. These results highlight the promise of adaptive, learning-based juries for building scalable, more reliable and trustworthy evaluation systems for modern LLMs in high-stakes domains.
Authors: Yunfei Li, Xiao Ma, Jiafeng Xu, Yu Cui, Zhongren Cui, Zhigang Han, Liqun Huang, Tao Kong, Yuxiao Liu, Hao Niu, Wanli Peng, Jingchao Qiao, Zeyu Ren, Haixin Shi, Zhi Su, Jiawen Tian, Yuyang Xiao, Shenyu Zhang, Liwei Zheng, Hang Li, Yonghui Wu
Abstract: We present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation. Assuming the optimality of human demonstrations is core to existing VLA policies. However, we claim that in highly dexterous and precise manipulation tasks, human demonstrations are noisy and suboptimal. GR-RL proposes a multi-stage training pipeline that filters, augments, and reinforces the demonstrations by reinforcement learning. First, GR-RL learns a vision-language-conditioned task progress, filters the demonstration trajectories, and only keeps the transitions that contribute positively to the progress. Specifically, we show that by directly applying offline RL with sparse reward, the resulting $Q$-values can be treated as a robust progress function. Next, we introduce morphological symmetry augmentation that greatly improves the generalization and performance of GR-RL. Lastly, to better align the VLA policy with its deployment behaviors for high-precision control, we perform online RL by learning a latent space noise predictor. With this pipeline, GR-RL is, to our knowledge, the first learning-based policy that can autonomously lace up a shoe by threading shoelaces through multiple eyelets with an 83.3% success rate, a task requiring long-horizon reasoning, millimeter-level precision, and compliant soft-body interaction. We hope GR-RL provides a step toward enabling generalist robot foundations models to specialize into reliable real-world experts.
Authors: Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang, Claire Jin, Daniel Pfrommer, Chenyang Yuan, Frank Permenter, Guannan Qu, Nicholas Boffi, Guanya Shi, Max Simchowitz
Abstract: Generative models, like flows and diffusions, have recently emerged as popular and efficacious policy parameterizations in robotics. There has been much speculation as to the factors underlying their successes, ranging from capturing multi-modal action distribution to expressing more complex behaviors. In this work, we perform a comprehensive evaluation of popular generative control policies (GCPs) on common behavior cloning (BC) benchmarks. We find that GCPs do not owe their success to their ability to capture multi-modality or to express more complex observation-to-action mappings. Instead, we find that their advantage stems from iterative computation, as long as intermediate steps are supervised during training and this supervision is paired with a suitable level of stochasticity. As a validation of our findings, we show that a minimum iterative policy (MIP), a lightweight two-step regression-based policy, essentially matches the performance of flow GCPs, and often outperforms distilled shortcut models. Our results suggest that the distribution-fitting component of GCPs is less salient than commonly believed, and point toward new design spaces focusing solely on control performance. Project page: https://simchowitzlabpublic.github.io/much-ado-about-noising-project/
URLs: https://simchowitzlabpublic.github.io/much-ado-about-noising-project/
Authors: Cencheng Shen, Yuexiao Dong, Carey E. Priebe
Abstract: Decision trees and random forest remain highly competitive for classification on medium-sized, standard datasets due to their robustness, minimal preprocessing requirements, and interpretability. However, a single tree suffers from high estimation variance, while large ensembles reduce this variance at the cost of substantial computational overhead and diminished interpretability. In this paper, we propose Decision Tree Embedding (DTE), a fast and effective method that leverages the leaf partitions of a trained classification tree to construct an interpretable feature representation. By using the sample means within each leaf region as anchor points, DTE maps inputs into an embedding space defined by the tree's partition structure, effectively circumventing the high variance inherent in decision-tree splitting rules. We further introduce an ensemble extension based on additional bootstrap trees, and pair the resulting embedding with linear discriminant analysis for classification. We establish several population-level theoretical properties of DTE, including its preservation of conditional density under mild conditions and a characterization of the resulting classification error. Empirical studies on synthetic and real datasets demonstrate that DTE strikes a strong balance between accuracy and computational efficiency, outperforming or matching random forest and shallow neural networks while requiring only a fraction of their training time in most cases. Overall, the proposed DTE method can be viewed either as a scalable decision tree classifier that improves upon standard split rules, or as a neural network model whose weights are learned from tree-derived anchor points, achieving an intriguing integration of both paradigms.
Authors: Valentin de Bortoli, Romuald Elie, Anna Kazeykina, Zhenjie Ren, Jiacheng Zhang
Abstract: Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution. A common approach involves simulating the time-reversal of an Ornstein-Uhlenbeck (OU) process initialized at the true data distribution. Since the score function associated with the OU process is typically unknown, it is approximated using a trained neural network. This approximation, along with finite time simulation, time discretization and statistical approximation, introduce several sources of error whose impact on the generated samples must be carefully understood. Previous analyses have quantified the error between the generated and the true data distributions in terms of Wasserstein distance or Kullback-Leibler (KL) divergence. However, both metrics present limitations: KL divergence requires absolute continuity between distributions, while Wasserstein distance, though more general, leads to error bounds that scale poorly with dimension, rendering them impractical in high-dimensional settings. In this work, we derive an explicit, dimension-free bound on the discrepancy between the generated and the true data distributions. The bound is expressed in terms of a smooth test functional with bounded first and second derivatives. The key novelty lies in the use of this weaker, functional metric to obtain dimension-independent guarantees, at the cost of higher regularity on the test functions. As an application, we formulate and solve a variational problem to minimize the time-discretization error, leading to the derivation of an optimal time-scheduling strategy for the reverse-time diffusion. Interestingly, this scheduler has appeared previously in the literature in a different context; our analysis provides a new justification for its optimality, now grounded in minimizing the discretization bias in generative sampling.
Authors: Jintian Zhang, Kewei Xu, Jingsheng Zheng, Zhuoyun Yu, Yuqi Zhu, Yujie Luo, Lanning Wei, Shuofei Qiao, Lun Du, Da Zheng, Shumin Deng, Huajun Chen, Ningyu Zhang
Abstract: LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True innovation depends not only on producing correct answers but also on the originality of the approach. We present InnoGym, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches. The benchmark includes 18 carefully curated tasks from real-world engineering and scientific domains, each standardized through resource filtering, evaluator validation, and solution collection. In addition, we provide iGym, a unified execution environment for reproducible and long-horizon evaluations. Extensive experiments show that while some agents produce novel approaches, their lack of robustness limits performance gains. These results highlight a key gap between creativity and effectiveness, underscoring the need for benchmarks that evaluate both.
Authors: Miguel A. Mendez
Abstract: This chapter opens with a review of classic tools for regression, a subset of machine learning that seeks to find relationships between variables. With the advent of scientific machine learning this field has moved from a purely data-driven (statistical) formalism to a constrained or ``physics-informed'' formalism, which integrates physical knowledge and methods from traditional computational engineering. In the first part, we introduce the general concepts and the statistical flavor of regression versus other forms of curve fitting. We then move to an overview of traditional methods from machine learning and their classification and ways to link these to traditional computational science. Finally, we close with a note on methods to combine machine learning and numerical methods for physics
Authors: Kentaro Fujii, Shingo Murata
Abstract: Robots in uncertain real-world environments must perform both goal-directed and exploratory actions. However, most deep learning-based control methods neglect exploration and struggle under uncertainty. To address this, we adopt deep active inference, a framework that accounts for human goal-directed and exploratory actions. Yet, conventional deep active inference approaches face challenges due to limited environmental representation capacity and high computational cost in action selection. We propose a novel deep active inference framework that consists of a world model, an action model, and an abstract world model. The world model encodes environmental dynamics into hidden state representations at slow and fast timescales. The action model compresses action sequences into abstract actions using vector quantization, and the abstract world model predicts future slow states conditioned on the abstract action, enabling low-cost action selection. We evaluate the framework on object-manipulation tasks with a real-world robot. Results show that it achieves high success rates across diverse manipulation tasks and switches between goal-directed and exploratory actions in uncertain settings, while making action selection computationally tractable. These findings highlight the importance of modeling multiple timescale dynamics and abstracting actions and state transitions.
Authors: Haoyang He, Jay Patrikar, Dong-Ki Kim, Max Smith, Daniel McGann, Ali-akbar Agha-mohammadi, Shayegan Omidshafiei, Sebastian Scherer
Abstract: Recent advances in video world modeling have enabled large-scale generative models to simulate embodied environments with high visual fidelity, providing strong priors for prediction, planning, and control. Yet, despite their realism, these models often lack geometric grounding, limiting their use in navigation tasks that require spatial coherence and long-horizon stability. We introduce Reinforcement Learning with World Grounding (RLWG), a self-supervised post-training framework that aligns pretrained world models with a physically verifiable structure through geometric and perceptual rewards. Analogous to reinforcement learning from verifiable feedback (RLVR) in language models, RLWG can use multiple rewards that measure pose cycle-consistency, depth reprojection, and temporal coherence. We instantiate this framework with GrndCtrl, a reward-aligned adaptation method based on Group Relative Policy Optimization (GRPO), yielding world models that maintain stable trajectories, consistent geometry, and reliable rollouts for embodied navigation. Like post-training alignment in large language models, GrndCtrl leverages verifiable rewards to bridge generative pretraining and grounded behavior, achieving superior spatial coherence and navigation stability over supervised fine-tuning in outdoor environments.
Authors: Andrea Goertzen, Sunbochen Tang, Navid Azizan
Abstract: Chaos is a fundamental feature of many complex dynamical systems, including weather systems and fluid turbulence. These systems are inherently difficult to predict due to their extreme sensitivity to initial conditions. Many chaotic systems are dissipative and ergodic, motivating data-driven models that aim to learn invariant statistical properties over long time horizons. While recent models have shown empirical success in preserving invariant statistics, they are prone to generating unbounded predictions, which prevent meaningful statistics evaluation. To overcome this, we introduce the Energy-Constrained Operator (ECO) that simultaneously learns the system dynamics while enforcing boundedness in predictions. We leverage concepts from control theory to develop algebraic conditions based on a learnable energy function, ensuring the learned dynamics is dissipative. ECO enforces these algebraic conditions through an efficient closed-form quadratic projection layer, which provides provable trajectory boundedness. To our knowledge, this is the first work establishing such formal guarantees for data-driven chaotic dynamics models. Additionally, the learned invariant level set provides an outer estimate for the strange attractor, a complex structure that is computationally intractable to characterize. We demonstrate empirical success in ECO's ability to generate stable long-horizon forecasts, capturing invariant statistics on systems governed by chaotic PDEs, including the Kuramoto--Sivashinsky and the Navier--Stokes equations.
Authors: Nasim Montazeri, Stone Yang, Dominik Luszczynski, John Zhang, Dharmendra Gurve, Andrew Centen, Maged Goubran, Andrew Lim
Abstract: Study Objectives: Wrist accelerometry is widely used for inferring sleep-wake state. Previous works demonstrated poor wake detection, without cross-device generalizability and validation in different age range and sleep disorders. We developed a robust deep learning model for to detect sleep-wakefulness from triaxial accelerometry and evaluated its validity across three devices and in a large adult population spanning a wide range of ages with and without sleep disorders. Methods: We collected wrist accelerometry simultaneous to polysomnography (PSG) in 453 adults undergoing clinical sleep testing at a tertiary care sleep laboratory, using three devices. We extracted features in 30-second epochs and trained a 3-class model to detect wake, sleep, and sleep with arousals, which was then collapsed into wake vs. sleep using a decision tree. To enhance wake detection, the model was specifically trained on randomly selected subjects with low sleep efficiency and/or high arousal index from one device recording and then tested on the remaining recordings. Results: The model showed high performance with F1 Score of 0.86, sensitivity (sleep) of 0.87, and specificity (wakefulness) of 0.78, and significant and moderate correlation to PSG in predicting total sleep time (R=0.69) and sleep efficiency (R=0.63). Model performance was robust to the presence of sleep disorders, including sleep apnea and periodic limb movements in sleep, and was consistent across all three models of accelerometer. Conclusions: We present a deep model to detect sleep-wakefulness from actigraphy in adults with relative robustness to the presence of sleep disorders and generalizability across diverse commonly used wrist accelerometers.
Authors: Guillermo Garcia-Cobo, Maximilian Igl, Peter Karkus, Zhejun Zhang, Michael Watson, Yuxiao Chen, Boris Ivanovic, Marco Pavone
Abstract: Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift when deployed in closed loop, leading to compounding errors. We introduce Rollouts as Demonstrations (RoaD), a simple and efficient method to mitigate covariate shift by leveraging the policy's own closed-loop rollouts as additional training data. During rollout generation, RoaD incorporates expert guidance to bias trajectories toward high-quality behavior, producing informative yet realistic demonstrations for fine-tuning. This approach enables robust closed-loop adaptation with orders of magnitude less data than reinforcement learning, and avoids restrictive assumptions of prior closed-loop supervised fine-tuning (CL-SFT) methods, allowing broader applications domains including end-to-end driving. We demonstrate the effectiveness of RoaD on WOSAC, a large-scale traffic simulation benchmark, where it performs similar or better than the prior CL-SFT method; and in AlpaSim, a high-fidelity neural reconstruction-based simulator for end-to-end driving, where it improves driving score by 41\% and reduces collisions by 54\%.
Authors: Younggyo Seo, Carmelo Sferrazza, Juyue Chen, Guanya Shi, Rocky Duan, Pieter Abbeel
Abstract: Massively parallel simulation has reduced reinforcement learning (RL) training time for robots from days to minutes. However, achieving fast and reliable sim-to-real RL for humanoid control remains difficult due to the challenges introduced by factors such as high dimensionality and domain randomization. In this work, we introduce a simple and practical recipe based on off-policy RL algorithms, i.e., FastSAC and FastTD3, that enables rapid training of humanoid locomotion policies in just 15 minutes with a single RTX 4090 GPU. Our simple recipe stabilizes off-policy RL algorithms at massive scale with thousands of parallel environments through carefully tuned design choices and minimalist reward functions. We demonstrate rapid end-to-end learning of humanoid locomotion controllers on Unitree G1 and Booster T1 robots under strong domain randomization, e.g., randomized dynamics, rough terrain, and push perturbations, as well as fast training of whole-body human-motion tracking policies. We provide videos and open-source implementation at: https://younggyo.me/fastsac-humanoid.
Authors: Jack Cook, Junxian Guo, Guangxuan Xiao, Yujun Lin, Song Han
Abstract: As large language models have grown larger, low-precision numerical formats such as NVFP4 have become increasingly popular due to the speed and memory benefits they provide. However, to accelerate computation with NVFP4, all matrix multiplication operands--weights and activations in the forward pass, and weights, activations, and gradients in the backward pass--must be quantized to NVFP4, often leading to divergence during training and performance degradation during inference. NVFP4 by evaluating multiple potential scale factors for each block of values. To address this issue, in this work we introduce Four Over Six (4/6), a modification to the NVFP4 quantization algorithm that evaluates two potential scale factors for each block of values. Unlike integer formats, floating-point formats such as FP4 have the most quantization error on near-maximal values in each block, which we find to be primarily responsible for downstream performance degradation. We find that for some blocks, scaling to smaller FP4 values makes the distribution of representable values more uniform, improving representation of near-maximal values. Importantly, 4/6 can be implemented efficiently on NVIDIA Blackwell GPUs, making it viable to use while training LLMs with NVFP4. In pre-training experiments with transformer and hybrid model architectures, we find that 4/6 prevents divergence in several cases, bringing training loss significantly closer to BF16 compared to models trained with current state-of-the-art NVFP4 training recipes. We also find that 4/6 can be easily incorporated into many different post-training quantization methods and generally improves downstream accuracy. We hope this inspires future work in training and deploying models with NVFP4.
Authors: Zhengyang Geng, Yiyang Lu, Zongze Wu, Eli Shechtman, J. Zico Kolter, Kaiming He
Abstract: MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's training target depends not only on the underlying ground-truth fields but also on the network itself. To address this issue, we recast the objective as a loss on the instantaneous velocity $v$, re-parameterized by a network that predicts the average velocity $u$. Our reformulation yields a more standard regression problem and improves the training stability. Second, the original MF fixes the classifier-free guidance scale during training, which sacrifices flexibility. We tackle this issue by formulating guidance as explicit conditioning variables, thereby retaining flexibility at test time. The diverse conditions are processed through in-context conditioning, which reduces model size and benefits performance. Overall, our $\textbf{improved MeanFlow}$ ($\textbf{iMF}$) method, trained entirely from scratch, achieves $\textbf{1.72}$ FID with a single function evaluation (1-NFE) on ImageNet 256$\times$256. iMF substantially outperforms prior methods of this kind and closes the gap with multi-step methods while using no distillation. We hope our work will further advance fastforward generative modeling as a stand-alone paradigm.
Authors: Shaowei Liu, David Yifan Yao, Saurabh Gupta, Shenlong Wang
Abstract: Today, people can easily record memorable moments, ranging from concerts, sports events, lectures, family gatherings, and birthday parties with multiple consumer cameras. However, synchronizing these cross-camera streams remains challenging. Existing methods assume controlled settings, specific targets, manual correction, or costly hardware. We present VisualSync, an optimization framework based on multi-view dynamics that aligns unposed, unsynchronized videos at millisecond accuracy. Our key insight is that any moving 3D point, when co-visible in two cameras, obeys epipolar constraints once properly synchronized. To exploit this, VisualSync leverages off-the-shelf 3D reconstruction, feature matching, and dense tracking to extract tracklets, relative poses, and cross-view correspondences. It then jointly minimizes the epipolar error to estimate each camera's time offset. Experiments on four diverse, challenging datasets show that VisualSync outperforms baseline methods, achieving an median synchronization error below 50 ms.
Authors: Jianlei Chang, Ruofeng Mei, Wei Ke, Xiangyu Xu
Abstract: Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data inefficiency, requiring large-scale demonstrations, and sampling inefficiency, incurring slow action generation during inference. We introduce EfficientFlow, a unified framework for efficient embodied AI with flow-based policy learning. To enhance data efficiency, we bring equivariance into flow matching. We theoretically prove that when using an isotropic Gaussian prior and an equivariant velocity prediction network, the resulting action distribution remains equivariant, leading to improved generalization and substantially reduced data demands. To accelerate sampling, we propose a novel acceleration regularization strategy. As direct computation of acceleration is intractable for marginal flow trajectories, we derive a novel surrogate loss that enables stable and scalable training using only conditional trajectories. Across a wide range of robotic manipulation benchmarks, the proposed algorithm achieves competitive or superior performance under limited data while offering dramatically faster inference. These results highlight EfficientFlow as a powerful and efficient paradigm for high-performance embodied AI.
Authors: Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson
Abstract: Federated Learning (FL) is a collaborative machine learning (ML) framework that combines on-device training and server-based aggregation to train a common ML model among distributed agents. In this work, we propose an asynchronous FL design with periodic aggregation to tackle the straggler issue in FL systems. Considering limited wireless communication resources, we investigate the effect of different scheduling policies and aggregation designs on the convergence performance. Driven by the importance of reducing the bias and variance of the aggregated model updates, we propose a scheduling policy that jointly considers the channel quality and training data representation of user devices. The effectiveness of our channel-aware data-importance-based scheduling policy, compared with state-of-the-art methods proposed for synchronous FL, is validated through simulations. Moreover, we show that an ``age-aware'' aggregation weighting design can significantly improve the learning performance in an asynchronous FL setting.
Authors: Shubhajit Roy, Shrutimoy Das, Binita Maity, Anant Kumar, Anirban Dasgupta
Abstract: Subgraph counting is a fundamental task for analyzing structural patterns in graph-structured data, with important applications in domains such as computational biology and social network analysis, where recurring motifs reveal functional and organizational properties. In this paper, we propose localized versions of the Weisfeiler-Leman (WL) algorithms to improve both expressivity and computational efficiency for this task. We introduce Local $k$-WL, which we prove to be more expressive than $k$-WL and at most as expressive as $(k+1)$-WL, and provide a characterization of patterns whose subgraph and induced subgraph counts are invariant under Local $k$-WL equivalence. To enhance scalability, we present two variants -- Layer $k$-WL and Recursive $k$-WL -- that achieve greater time and space efficiency compared to applying $k$-WL on the entire graph. Additionally, we propose a novel fragmentation technique that decomposes complex subgraphs into simpler subpatterns, enabling the exact count of all induced subgraphs of size at most $4$ using only $1$-WL, with extensions possible for larger patterns when $k>1$. Building on these ideas, we develop a three-stage differentiable learning framework that combines subpattern counts to compute counts of more complex motifs, bridging combinatorial algorithm design with machine learning approaches. We also compare the expressive power of Local $k$-WL with existing GNN hierarchies and demonstrate that, under bounded time complexity, our methods are more expressive than prior approaches.
Authors: Petr Philonenko, Vladimir Kokh, Pavel Blinov
Abstract: Conventional medical cancer screening methods are costly, labor-intensive, and extremely difficult to scale. Although AI can improve cancer detection, most systems rely on complex or specialized medical data, making them impractical for large-scale screening. We introduce Can-SAVE, a lightweight AI system that ranks population-wide cancer risks solely based on medical history events. By integrating survival model outputs into a gradient-boosting framework, our approach detects subtle, long-term patient risk patterns - often well before clinical symptoms manifest. Can-SAVE was rigorously evaluated on a real-world dataset of 2.5 million adults spanning five Russian regions, marking the study as one of the largest and most comprehensive deployments of AI-driven cancer risk assessment. In a retrospective oncologist-supervised study over 1.9M patients, Can-SAVE achieves a 4-10x higher detection rate at identical screening volumes and an Average Precision (AP) of 0.228 vs. 0.193 for the best baseline (LoRA-tuned Qwen3-Embeddings via DeepSeek-R1 summarization). In a year-long prospective pilot (426K patients), our method almost doubled the cancer detection rate (+91%) and increased population coverage by 36% over the national screening protocol. The system demonstrates practical scalability: a city-wide population of 1 million patients can be processed in under three hours using standard hardware, enabling seamless clinical integration. This work proves that Can-SAVE achieves nationally significant cancer detection improvements while adhering to real-world public healthcare constraints, offering immediate clinical utility and a replicable framework for population-wide screening. Code for training and feature engineering is available at https://github.com/sb-ai-lab/Can-SAVE.
Authors: Luyao Guo, Sulaiman A. Alghunaim, Kun Yuan, Laurent Condat, Jinde Cao
Abstract: The ProxSkip algorithm for distributed optimization is gaining increasing attention due to its effectiveness in reducing communication. However, existing analyses of ProxSkip are limited to the strongly convex setting and fail to achieve linear speedup with respect to the number of nodes. Key questions regarding its behavior in the non-convex setting and the achievability of linear speedup remain open. In this paper, we revisit ProxSkip and address both questions. We provide a comprehensive analysis for stochastic non-convex, convex, and strongly convex problems, revealing the effects of gradient noise, local updates, network connectivity, and data heterogeneity on its convergence. We prove that ProxSkip achieves linear speedup across all three settings, and can further achieve linear speedup with network-independent stepsizes in the strongly convex setting. Moreover, we show that properly increasing local updates effectively reduces communication complexity.
Authors: Ying Liu, Peng Cui, Wenbo Hu, Richang Hong
Abstract: Real-world time series data often exhibits substantial missing values, posing challenges for advanced analysis. A common approach to addressing this issue is imputation, where the primary challenge lies in determining the appropriate values to fill in. While previous deep learning methods have proven effective for time series imputation, they often produce overconfident imputations, which poses a potentially overlooked risk to the reliability of the intelligent system. Diffusion methods are proficient in estimating probability distributions but face challenges under a high missing rate and are, moreover, computationally expensive due to the nature of the generative model framework. In this paper, we propose Quantile Sub-Ensembles, a novel method that estimates uncertainty with ensembles of quantile-regression-based task networks and incorporate Quantile Sub-Ensembles into a non-generative time series imputation method. Our method not only produces accurate and reliable imputations, but also remains computationally efficient due to its non-generative framework. We conduct extensive experiments on five real-world datasets, and the results demonstrates superior performance in both deterministic and probabilistic imputation compared to baselines across most experimental settings. The code is available at https://github.com/yingliu-coder/QSE.
Authors: Ye Lin Tun, Chu Myaet Thwal, Huy Q. Le, Minh N. H. Nguyen, Eui-Nam Huh, Choong Seon Hong
Abstract: Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw data distributed across edge devices. However, edge devices often struggle with high computational and communication costs imposed by SSL and FL algorithms. With the deployment of more complex and large-scale models, these challenges are exacerbated. To tackle this, we propose Layer-Wise Federated Self-Supervised Learning (LW-FedSSL), which allows edge devices to incrementally train a small part of the model at a time. Specifically, in LW-FedSSL, training is decomposed into multiple stages, with each stage responsible for only a specific layer of the model. Since only a portion of the model is active for training at any given time, LW-FedSSL significantly reduces computational requirements. Additionally, only the active model portion needs to be exchanged between the FL server and clients, reducing communication overhead. This enables LW-FedSSL to jointly address both computational and communication challenges of FL client devices. It can achieve up to a $3.34 \times$ reduction in memory usage, $4.20 \times$ fewer computational operations (giga floating point operations, GFLOPs), and a $5.07 \times$ lower communication cost while maintaining performance comparable to its end-to-end training counterpart. Furthermore, we explore a progressive training strategy called Progressive Federated Self-Supervised Learning (Prog-FedSSL), which offers a $1.84\times$ reduction in GFLOPs and a $1.67\times$ reduction in communication costs while maintaining the same memory requirements as end-to-end training. Although the resource efficiency of Prog-FedSSL is lower than that of LW-FedSSL, its performance improvements make it a viable candidate for FL environments with more lenient resource constraints.
Authors: Vaggos Chatziafratis, Ishani Karmarkar, Yingxi Li, Ellen Vitercik
Abstract: In clustering algorithm selection, we are given a massive dataset and must efficiently select which clustering algorithm to use. We study this problem in a semi-supervised setting, with an unknown ground-truth clustering that we can only access through expensive oracle queries. Ideally, the clustering algorithm's output will be structurally close to the ground truth. We approach this problem by introducing a notion of size generalization for clustering algorithm accuracy. We identify conditions under which we can (1) subsample the massive clustering instance, (2) evaluate a set of candidate algorithms on the smaller instance, and (3) guarantee that the algorithm with the best accuracy on the small instance will have the best accuracy on the original big instance. We provide theoretical size generalization guarantees for three classic clustering algorithms: single-linkage, k-means++, and (a smoothed variant of) Gonzalez's k-centers heuristic. We validate our theoretical analysis with empirical results, observing that on real-world clustering instances, we can use a subsample of as little as 5% of the data to identify which algorithm is best on the full dataset.
Authors: Pedro Seber, Richard D. Braatz
Abstract: Interpretable models can have advantages over black-box models, and interpretability is essential for the application of machine learning in critical settings, such as aviation or medicine. This article introduces the LASSO-Clip-EN (LCEN) algorithm for nonlinear, interpretable feature selection and machine learning modeling. In a wide variety of artificial and empirical datasets, LCEN constructed sparse and frequently more accurate models than other methods, including sparse, nonlinear methods, on tested datasets. LCEN was empirically observed to be robust against many issues typically present in datasets and modeling, including noise, multicollinearity, and data scarcity. As a feature selection algorithm, LCEN matched or surpassed the thresholded elastic net but was, on average, 10.3-fold faster based on our experiments. LCEN for feature selection can also rediscover multiple physical laws from empirical data. As a machine learning algorithm, when tested on processes with no known physical laws, LCEN achieved better results than many other dense and sparse methods -- including being comparable to or better than ANNs on multiple datasets.
Authors: Hira Saleem, Flora Salim, Cormac Purcell
Abstract: Operational Numerical Weather Prediction (NWP) system relies on computationally expensive physics-based models. Recently, transformer models have shown remarkable potential in weather forecasting achieving state-of-the-art results. However, traditional transformers discretize spatio-temporal dimensions, limiting their ability to model continuous dynamical weather processes. Moreover, their reliance on increased depth to capture complex dependencies results in higher computational cost and parameter redundancy. We address these issues with STC-ViT, a Spatio-Temporal Continuous Vision Transformer for weather forecasting. STC-ViT integrates a Fourier Neural Operator (FNO) for global spatial operators with a transformer parameterised Neural ODE for continuous-time dynamics, yielding a space-time continuous model for weather forecasting. Our proposed method achieves competitive forecasting performance even with a shallow, single-layer transformer encoder mitigating the reliance on deeper networks. STC-ViT generates complete forecast trajectories with an inference speed of only 0.125 seconds and achieves strong medium-range forecasting skill on 1.5-degree WeatherBench 2 as compared to state-of-the-art data-driven and NWP models trained on higher-resolution data, with substantially lower data and compute costs. We also provide detailed empirical analysis on model's performance with respect to denser time grids, higher-accuracy ODE solvers, and deeper transformer stacks.
Authors: Peiman Mohseni, Nick Duffield
Abstract: Neural processes (NPs) are probabilistic meta-learning models that map sets of observations to posterior predictive distributions, enabling inference at arbitrary domain points. Their capacity to handle variable-sized collections of unstructured observations, combined with simple maximum-likelihood training and uncertainty-aware predictions, makes them well-suited for modeling data over continuous domains. Since their introduction, several variants have been proposed. Early approaches typically represented observed data using finite-dimensional summary embeddings obtained through aggregation schemes such as mean pooling. However, this strategy fundamentally mismatches the infinite-dimensional nature of the generative processes that NPs aim to capture. Convolutional conditional neural processes (ConvCNPs) address this limitation by constructing infinite-dimensional functional embeddings processed through convolutional neural networks (CNNs) to enforce translation equivariance. Yet CNNs with local spatial kernels struggle to capture long-range dependencies without resorting to large kernels, which impose significant computational costs. To overcome this limitation, we propose the Spectral ConvCNP (SConvCNP), which performs global convolution in the frequency domain. Inspired by Fourier neural operators (FNOs) for learning solution operators of partial differential equations (PDEs), our approach directly parameterizes convolution kernels in the frequency domain, leveraging the relatively compact yet global Fourier representation of many natural signals. We validate the effectiveness of SConvCNP on both synthetic and real-world datasets, demonstrating how ideas from operator learning can advance the capabilities of NPs.
Authors: Abdallah Alabdallah, Omar Hamed, Mattias Ohlsson, Thorsteinn R\"ognvaldsson, Sepideh Pashami
Abstract: The Cox Proportional Hazards (CPH) model has long been the preferred survival model for its explainability. However, to increase its predictive power beyond its linear log-risk, it was extended to utilize deep neural networks, sacrificing its explainability. In this work, we explore the potential of self-explaining neural networks (SENN) for survival analysis. We propose a new locally explainable Cox proportional hazards model, named CoxSE, by estimating a locally-linear log-hazard function using the SENN. We also propose a modification to the Neural additive (NAM) model, hybrid with SENN, named CoxSENAM, which enables the control of the stability and consistency of the generated explanations. Several experiments using synthetic and real datasets are presented, benchmarking CoxSE and CoxSENAM against a NAM-based model, a DeepSurv model explained with SHAP, and a linear CPH model. The results show that, unlike the NAM-based model, the SENN-based model can provide more stable and consistent explanations while maintaining the predictive power of the black-box model. The results also show that, due to their structural design, NAM-based models demonstrate better robustness to non-informative features. Among the models, the hybrid model exhibits the best robustness.
Authors: Zhenyu Zhao, Yexi Jiang
Abstract: Effective feature selection is essential for optimizing contextual multi-armed bandits (CMABs) in large-scale online systems, where suboptimal features can degrade rewards, interpretability, and efficiency. Traditional feature selection often prioritizes outcome correlation, neglecting the crucial role of heterogeneous treatment effects (HTE) across arms in CMAB decision-making. This paper introduces two novel, model-free filter methods, Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD), specifically designed to identify features driving HTE. HIE quantifies a feature's value based on its ability to induce changes in the optimal arm, while HDD measures its impact on reward distribution divergence across arms. These methods are computationally efficient, robust to model mis-specification, and adaptable to various feature types, making them suitable for rapid screening in dynamic environments where retraining complex models is infeasible. We validate HIE and HDD on synthetic data with known ground truth and in a large-scale commercial recommender system, demonstrating their consistent ability to identify influential HTE features and thereby enhance CMAB performance.
Authors: Zhiming Xu, Suorong Yang, Baile Xu, Furao Shen, Jian Zhao
Abstract: Class-incremental learning (CIL) aims to learn new classes while retaining previous knowledge. Although pre-trained model (PTM) based approaches show strong performance, directly fine-tuning PTMs on incremental task streams often causes renewed catastrophic forgetting. This paper proposes a Dual-Prototype Network with Task-wise Adaptation (DPTA) for PTM-based CIL. For each incremental learning task, an adapter module is built to fine-tune the PTM, where the center-adapt loss forces the representation to be more centrally clustered and class separable. The dual prototype network improves the prediction process by enabling test-time adapter selection, where the raw prototypes deduce several possible task indexes of test samples to select suitable adapter modules for PTM, and the augmented prototypes that could separate confusable classes are utilized to determine the final result. Experiments on multiple benchmarks show that DPTA consistently surpasses recent methods by 1\% - 5\%. Notably, on the VTAB dataset, it achieves approximately 3\% improvement over state-of-the-art methods. The code is open-sourced in https://github.com/Yorkxzm/DPTA}
Authors: Youssef Mansour, Reinhard Heckel
Abstract: We investigate fingerprints in pretraining datasets for large language models (LLMs) through dataset classification experiments. Building on prior work demonstrating the existence of fingerprints or biases in popular computer vision datasets, we analyze popular open-source pretraining datasets for LLMs derived from CommonCrawl including C4, RefinedWeb, DolmaCC, RedPajama-V2, FineWeb, and DCLM-Baseline. Despite those datasets being obtained with similar curation steps, neural networks can classify surprisingly well which dataset a single text sequence belongs to, significantly better than a human can. This indicates that small differences in filtering and processing pipelines induce fingerprints. Those fingerprints are evident in formatting, vocabulary, and content distributions, and can negatively impact cross-dataset generalization. Additionally, we show that these fingerprints propagate through training: sequences generated by models trained on those datasets can be accurately classified by a classifier trained on the original datasets. This can offer insights into data characteristics that are typically undisclosed by LLM developers, including pretraining mixture proportions and finetuning data sources.
Authors: Arash Golmohammadi, Jannik Luboeinski, Christian Tetzlaff
Abstract: Heterogeneity is a ubiquitous property of many biological systems and has profound implications for computation. While it is conceivable to optimize neuronal and synaptic heterogeneity for a specific task, such top-down optimization is biologically implausible, prone to catastrophic forgetting, and both data- and energy-intensive. In contrast, biological organisms, with remarkable capacity to perform numerous tasks with minimal metabolic cost, exhibit a heterogeneity that is inherent, stable during adulthood, and task-unspecific. Inspired by this intrinsic form of heterogeneity, we investigate the utility of variations in neuronal time constants for solving hundreds of distinct temporal tasks of varying complexity. Our results show that intrinsic heterogeneity significantly enhances performance and robustness in an implementation-independent manner, indicating its usefulness for both (rate-based) machine learning and (spike-coded) neuromorphic applications. Importantly, only skewed heterogeneity profiles-reminiscent of those found in biology-produce such performance gains. We further demonstrate that this computational advantage eliminates the need for large networks, allowing comparable performance with substantially lower operational, metabolic, and energetic costs, respectively in silico, in vivo, and on neuromorphic hardware. Finally, we discuss the implications of intrinsic (rather than task-induced) heterogeneity for the design of efficient artificial systems, particularly novel neuromorphic devices that exhibit similar device-to-device variability.
Authors: Dylan Sam, Marc Finzi, J. Zico Kolter
Abstract: Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language models are offered only through closed-source APIs, providing only black-box access. In this paper, we predict the behavior of black-box language models by asking follow-up questions and taking the probabilities of responses \emph{as} representations to train reliable predictors. We first demonstrate that training a linear model on these responses reliably and accurately predicts model correctness on question-answering and reasoning benchmarks. Surprisingly, this can \textit{even outperform white-box linear predictors} that operate over model internals or activations. Furthermore, we demonstrate that these follow-up question responses can reliably distinguish between a clean version of an LLM and one that has been adversarially influenced via a system prompt to answer questions incorrectly or to introduce bugs into generated code. Finally, we show that they can also be used to differentiate between black-box LLMs, enabling the detection of misrepresented models provided through an API. Overall, our work shows promise in monitoring black-box language model behavior, supporting their deployment in larger, autonomous systems.
Authors: Zechen Wu, Amy Greenwald, Ronald Parr
Abstract: In off-policy policy evaluation (OPE) tasks within reinforcement learning, Temporal Difference Learning(TD) and Fitted Q-Iteration (FQI) have traditionally been viewed as differing in the number of updates toward the target value function: TD makes one update, FQI makes an infinite number, and Partial Fitted Q-Iteration (PFQI) performs a finite number. We show that this view is not accurate, and provide a new mathematical perspective under linear value function approximation that unifies these methods as a single iterative method solving the same linear system, but using different matrix splitting schemes and preconditioners. We show that increasing the number of updates under the same target value function, i.e., the target network technique, is a transition from using a constant preconditioner to using a data-feature adaptive preconditioner. This elucidates, for the first time, why TD convergence does not necessarily imply FQI convergence, and establishes tight convergence connections among TD, PFQI, and FQI. Our framework enables sharper theoretical results than previous work and characterization of the convergence conditions for each algorithm, without relying on assumptions about the features (e.g., linear independence). We also provide an encoder-decoder perspective to better understand the convergence conditions of TD, and prove, for the first time, that when a large learning rate doesn't work, trying a smaller one may help. Our framework also leads to the discovery of new crucial conditions on features for convergence, and shows how common assumptions about features influence convergence, e.g., the assumption of linearly independent features can be dropped without compromising the convergence guarantees of stochastic TD in the on-policy setting. This paper is also the first to introduce matrix splitting into the convergence analysis of these algorithms.
Authors: Mathias Bellat, Jordy D. Orellana Figueroa, Jonathan S. Reeves, Ruhollah Taghizadeh-Mehrjardi, Claudio Tennie, Thomas Scholten
Abstract: Artificial intelligence and machine learning applications in archaeology have increased significantly in recent years, and these now span all subfields, geographical regions, and time periods. The prevalence and success of these applications have remained largely unexamined, as recent reviews on the use of machine learning in archaeology have only focused only on specific subfields of archaeology. Our review examined an exhaustive corpus of 135 articles published between 1997 and 2022. We observed a significant increase in the number of publications from 2019 onwards. Automatic structure detection and artefact classification were the most represented tasks in the articles reviewed, followed by taphonomy, and archaeological predictive modelling. From the review, clustering and unsupervised methods were underrepresented compared to supervised models. Artificial neural networks and ensemble learning account for two thirds of the total number of models used. However, if machine learning models are gaining in popularity they remain subject to misunderstanding. We observed, in some cases, poorly defined requirements and caveats of the machine learning methods used. Furthermore, the goals and the needs of machine learning applications for archaeological purposes are in some cases unclear or poorly expressed. To address this, we proposed a workflow guide for archaeologists to develop coherent and consistent methodologies adapted to their research questions, project scale and data. As in many other areas, machine learning is rapidly becoming an important tool in archaeological research and practice, useful for the analyses of large and multivariate data, although not without limitations. This review highlights the importance of well-defined and well-reported structured methodologies and collaborative practices to maximise the potential of applications of machine learning methods in archaeology.
Authors: Surbhi Goel, Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
Abstract: We pose a fundamental question in computational learning theory: can we efficiently test whether a training set satisfies the assumptions of a given noise model? This question has remained unaddressed despite decades of research on learning in the presence of noise. In this work, we show that this task is tractable and present the first efficient algorithm to test various noise assumptions on the training data. To model this question, we extend the recently proposed testable learning framework of Rubinfeld and Vasilyan (2023) and require a learner to run an associated test that satisfies the following two conditions: (1) whenever the test accepts, the learner outputs a classifier along with a certificate of optimality, and (2) the test must pass for any dataset drawn according to a specified modeling assumption on both the marginal distribution and the noise model. We then consider the problem of learning halfspaces over Gaussian marginals with Massart noise (where each label can be flipped with probability less than $1/2$ depending on the input features), and give a fully-polynomial time testable learning algorithm. We also show a separation between the classical setting of learning in the presence of structured noise and testable learning. In fact, for the simple case of random classification noise (where each label is flipped with fixed probability $\eta = 1/2$), we show that testable learning requires super-polynomial time while classical learning is trivial.
Authors: Zhihui Xie, Jie Chen, Liyu Chen, Weichao Mao, Jingjing Xu, Lingpeng Kong
Abstract: Teaching large language models (LLMs) to critique and refine their outputs is crucial for building systems that can iteratively improve, yet it is fundamentally limited by the ability to provide accurate judgments and actionable suggestions. In this work, we study LLM critics for code generation and propose $\texttt{CTRL}$, a framework for $\texttt{C}$ritic $\texttt{T}$raining via $\texttt{R}$einforcement $\texttt{L}$earning, which trains a critic model to generate feedback that maximizes correction performance for a fixed generator model without human supervision. Our results demonstrate that critics trained with $\texttt{CTRL}$ significantly enhance pass rates and mitigate compounding errors across both base and stronger generator models. Furthermore, we show that these critic models act as accurate generative reward models and enable test-time scaling through iterative critique-revision, achieving up to 106.1% relative improvements across challenging code generation benchmarks.
Authors: Zicheng Liu, Siyuan Li, Zhiyuan Chen, Chang Yu, Qirong Yang, Yucheng Guo, Yujie Yang, Xiaoming Zhang, Stan Z. Li
Abstract: The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. Although modern biological pre-trained models have achieved great success in analyzing these macromolecules individually, their interconnected nature remains underexplored. This paper follows the guidance of the central dogma to redesign both the data and model pipeline and offers a comprehensive framework, Life-Code, that spans different biological functions. As for data flow, we propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences. As for the model, we design a codon tokenizer and a hybrid long-sequence architecture to encode the interactions between coding and non-coding regions through masked modeling pre-training. To model the translation and folding process with coding sequences, Life-Code learns protein structures of the corresponding amino acids by knowledge distillation from off-the-shelf protein language models. Such designs enable Life-Code to capture complex interactions within genetic sequences, providing a more comprehensive understanding of multi-omics with the central dogma. Extensive experiments show that Life-Code achieves state-of-the-art results on various tasks across three omics, highlighting its potential for advancing multi-omics analysis and interpretation.
Authors: Kareem Amin, Sara Babakniya, Alex Bie, Weiwei Kong, Umar Syed, Sergei Vassilvitskii
Abstract: Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance to plateau, or even "collapse", after many training iterations. In this paper, we formalize this question and develop a theoretical framework to investigate how much curation is needed in order to ensure that LLM performance continually improves. Our analysis is inspired by boosting, a classic machine learning technique that leverages a very weak learning algorithm to produce an arbitrarily good classifier. The approach we analyze subsumes many recently proposed methods for training LLMs on synthetic data, and thus our analysis sheds light on why they are successful, and also suggests opportunities for future improvement. We present experiments that validate our theory, and show that dynamically focusing labeling resources on the most challenging examples -- in much the same way that boosting focuses the efforts of the weak learner -- leads to improved performance.
Authors: Juntong Ni, Zewen Liu, Shiyu Wang, Ming Jin, Wei Jin
Abstract: Transformer-based and CNN-based methods demonstrate strong performance in long-term time series forecasting. However, their high computational and storage requirements can hinder large-scale deployment. To address this limitation, we propose integrating lightweight MLP with advanced architectures using knowledge distillation (KD). Our preliminary study reveals different models can capture complementary patterns, particularly multi-scale and multi-period patterns in the temporal and frequency domains. Based on this observation, we introduce TimeDistill, a cross-architecture KD framework that transfers these patterns from teacher models (e.g., Transformers, CNNs) to MLP. Additionally, we provide a theoretical analysis, demonstrating that our KD approach can be interpreted as a specialized form of mixup data augmentation. TimeDistill improves MLP performance by up to 18.6%, surpassing teacher models on eight datasets. It also achieves up to 7X faster inference and requires 130X fewer parameters. Furthermore, we conduct extensive evaluations to highlight the versatility and effectiveness of TimeDistill.
Authors: Maximilian Forstenh\"ausler, Daniel K\"ulzer, Christos Anagnostopoulos, Shameem Puthiya Parambath, Natascha Weber
Abstract: Understanding user intent is essential for situational and context-aware decision-making. Motivated by a real-world scenario, this work addresses intent predictions of smart device users in the vicinity of vehicles by modeling sequential spatiotemporal data. However, in real-world scenarios, environmental factors and sensor limitations can result in non-stationary and irregularly sampled data, posing significant challenges. To address these issues, we propose STaRFormer, a Transformer-based approach that can serve as a universal framework for sequential modeling. STaRFormer utilizes a new dynamic attention-based regional masking scheme combined with a novel semi-supervised contrastive learning paradigm to enhance task-specific latent representations. Comprehensive experiments on 56 datasets varying in types (including non-stationary and irregularly sampled), tasks, domains, sequence lengths, training samples, and applications demonstrate the efficacy of STaRFormer, achieving notable improvements over state-of-the-art approaches.
Authors: Miaoyun Zhao, Chenrong Li, Qiang Zhang
Abstract: Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. Existing research attributes this issue to group imbalance and addresses it by maximizing group-balanced or worst-group accuracy, which heavily relies on expensive bias annotations. A compromise approach involves predicting bias information using extensively pretrained foundation models, which requires large-scale data and becomes impractical for resource-limited rare domains. To address these challenges, we offer a novel perspective by reframing the spurious correlations as imbalances or mismatches in class-conditional distributions, and propose a simple yet effective robust learning method that eliminates the need for both bias annotations and predictions. With the goal of maximizing the conditional entropy (uncertainty) of the label given spurious factors, our method leverages a sample reweighting strategy to achieve class-conditional distribution balancing, which automatically highlights minority groups and classes, effectively dismantling spurious correlations and producing a debiased data distribution for classification. Extensive experiments and analysis demonstrate that our approach consistently delivers state-of-the-art performance, rivaling methods that rely on bias supervision.
Authors: Zihao An, Huajun Bai, Ziqiong Liu, Dong Li, Emad Barsoum
Abstract: The autoregressive nature of large language models (LLMs) fundamentally limits inference speed, as each forward pass generates only a single token and is often bottlenecked by memory bandwidth. Speculative decoding has emerged as a promising solution, adopting a draft-then-verify strategy to accelerate token generation. While the EAGLE series achieves strong acceleration, its requirement of training a separate draft head for each target model introduces substantial adaptation costs. In this work, we propose \textbf{PARD (PARallel Draft)}, a novel speculative decoding method featuring \textit{target-independence} and \textit{parallel token prediction}. Specifically, PARD enables a single draft model to be applied across an entire family of target models without requiring separate training for each variant, thereby minimizing adaptation costs. Meanwhile, PARD substantially accelerates inference by predicting multiple future tokens within a single forward pass of the draft phase. To further reduce the training adaptation cost of PARD, we propose a COnditional Drop-token (COD) mechanism based on the integrity of prefix key-value states, enabling autoregressive draft models to be adapted into parallel draft models at low-cost. Our experiments show that the proposed COD method improves draft model training efficiency by \textbf{3$\times$} compared with traditional masked prediction training. On the \texttt{vLLM} inference framework, PARD achieves up to \textbf{3.67$\times$} speedup on LLaMA3.1-8B, reaching \textbf{264.88} tokens per second, which is \textbf{1.15$\times$} faster than EAGLE-3. Our code is available at https://github.com/AMD-AIG-AIMA/PARD.
Authors: Tanvir Islam
Abstract: We propose TLoRA, a novel tri-matrix low-rank adaptation method that decomposes weight updates into three matrices: two fixed random matrices and one trainable matrix, combined with a learnable, layer-wise scaling factor. This tri-matrix design enables TLoRA to achieve highly efficient parameter adaptation while introducing minimal additional computational overhead. Through extensive experiments on the GLUE benchmark, we demonstrate that TLoRA achieves comparable performance to existing low-rank methods such as LoRA and Adapter-based techniques, while requiring significantly fewer trainable parameters. Analyzing the adaptation dynamics, we observe that TLoRA exhibits Gaussian-like weight distributions, stable parameter norms, and scaling factor variability across layers, further highlighting its expressive power and adaptability. Additionally, we show that TLoRA closely resembles LoRA in its eigenvalue distributions, parameter norms, and cosine similarity of updates, underscoring its ability to effectively approximate LoRA's adaptation behavior. Our results establish TLoRA as a highly efficient and effective fine-tuning method for LLMs, offering a significant step forward in resource-efficient model adaptation.
Authors: Julen Erzibengoa, Meritxell G\'omez-Omella, Izaro Goienetxea
Abstract: Wildfires pose a threat to ecosystems, economies and public safety, particularly in Mediterranean regions such as Spain. Accurate predictive models require high-resolution spatio-temporal data to capture complex dynamics of environmental and human factors. To address the scarcity of fine-grained wildfire datasets in Spain, we introduce IberFire: a spatio-temporal dataset with 1 km x 1 km x 1-day resolution, covering mainland Spain and the Balearic Islands from December 2007 to December 2024. IberFire integrates 120 features across eight categories: auxiliary data, fire history, geography, topography, meteorology, vegetation indices, human activity and land cover. All features and processing rely on open-access data and tools, with a publicly available codebase ensuring transparency and applicability. IberFire offers enhanced spatial granularity and feature diversity compared to existing European datasets, and provides a reproducible framework. It supports advanced wildfire risk modelling via Machine Learning and Deep Learning, facilitates climate trend analysis, and informs fire prevention and land management strategies. The dataset is freely available on Zenodo to promote open research and collaboration.
Authors: Palok Biswas, Zuzanna Osika, Isidoro Tamassia, Adit Whorra, Jazmin Zatarain-Salazar, Jan Kwakkel, Frans A. Oliehoek, Pradeep K. Murukannaiah
Abstract: Addressing climate change requires coordinated policy efforts of nations worldwide. These efforts are informed by scientific reports, which rely in part on Integrated Assessment Models (IAMs), prominent tools used to assess the economic impacts of climate policies. However, traditional IAMs optimize policies based on a single objective, limiting their ability to capture the trade-offs among economic growth, temperature goals, and climate justice. As a result, policy recommendations have been criticized for perpetuating inequalities, fueling disagreements during policy negotiations. We introduce Justice, the first framework integrating IAM with Multi-Objective Multi-Agent Reinforcement Learning (MOMARL). By incorporating multiple objectives, Justice generates policy recommendations that shed light on equity while balancing climate and economic goals. Further, using multiple agents can provide a realistic representation of the interactions among the diverse policy actors. We identify equitable Pareto-optimal policies using our framework, which facilitates deliberative decision-making by presenting policymakers with the inherent trade-offs in climate and economic policy.
Authors: Yizhou Liu, Ziming Liu, Jeff Gore
Abstract: The success of today's large language models (LLMs) depends on the observation that larger models perform better. However, the origin of this neural scaling law, that loss decreases as a power law with model size, remains unclear. We propose that representation superposition, meaning that LLMs represent more features than they have dimensions, can be a key contributor to loss and cause neural scaling. Based on Anthropic's toy model, we use weight decay to control the degree of superposition, allowing us to systematically study how loss scales with model size. When superposition is weak, the loss follows a power law only if data feature frequencies are power-law distributed. In contrast, under strong superposition, the loss generically scales inversely with model dimension across a broad class of frequency distributions, due to geometric overlaps between representation vectors. We confirmed that open-sourced LLMs operate in the strong superposition regime and have loss scaling inversely with model dimension, and that the Chinchilla scaling laws are also consistent with this behavior. Our results identify representation superposition as a central driver of neural scaling laws, providing insights into questions like when neural scaling laws can be improved and when they will break down.
Authors: Ben Adcock, Nick Huang
Abstract: We study the sample complexity of Bayesian recovery for solving inverse problems with general prior, forward operator and noise distributions. We consider posterior sampling according to an approximate prior $\mathcal{P}$, and establish sufficient conditions for stable and accurate recovery with high probability. Our main result is a non-asymptotic bound that shows that the sample complexity depends on (i) the intrinsic complexity of $\mathcal{P}$, quantified by its so-called approximate covering number, and (ii) concentration bounds for the forward operator and noise distributions. As a key application, we specialize to generative priors, where $\mathcal{P}$ is the pushforward of a latent distribution via a Deep Neural Network (DNN). We show that the sample complexity scales log-linearly with the latent dimension $k$, thus establishing the efficacy of DNN-based priors. Generalizing existing results on deterministic (i.e., non-Bayesian) recovery for the important problem of random sampling with an orthogonal matrix $U$, we show how the sample complexity is determined by the coherence of $U$ with respect to the support of $\mathcal{P}$. Hence, we establish that coherence plays a fundamental role in Bayesian recovery as well. Overall, our framework unifies and extends prior work, providing rigorous guarantees for the sample complexity of solving Bayesian inverse problems with arbitrary distributions.
Authors: Francesco Marchetti, Edoardo Legnaro, Sabrina Guastavino
Abstract: In this paper, we introduce a threshold-based framework for multiclass classification that generalizes the standard argmax rule. This is done by replacing the probabilistic interpretation of softmax outputs with a geometric one on the multidimensional simplex, where the classification depends on a multidimensional threshold. This change of perspective enables for any trained classification network an a posteriori optimization of the classification score by means of threshold tuning, as usually carried out in the binary setting. This allows a further refinement of the prediction capability of any network. Moreover, this multidimensional threshold-based setting makes it possible to define score-oriented losses, which are based on the interpretation of the threshold as a random variable. Our experiments show that the multidimensional threshold tuning yields consistent performance improvements across various networks and datasets, and that the proposed multiclass score-oriented losses are competitive with standard loss functions, resembling the advantages observed in the binary case.
Authors: Anqiao Ouyang, Hongyi Ke, Qi Wang
Abstract: We present the Fourier-Invertible Neural Encoder (FINE), a compact and interpretable architecture for dimension reduction in translation-equivariant datasets. FINE integrates reversible filters and monotonic activation functions with a Fourier truncation bottleneck, achieving information-preserving compression that respects translational symmetry. This design offers a new perspective on symmetry-aware learning, linking spectral truncation to group-equivariant representations. The proposed FINE architecture is tested on one-dimensional nonlinear wave interaction, one-dimensional Kuramoto-Sivashinsky turbulence dataset, and a two-dimensional turbulence dataset. FINE achieves an overall 4.9-9.1 times lower reconstruction error than convolutional autoencoders while using only 13-21% of their parameters. The results highlight FINE's effectiveness in representing complex physical systems with minimal dimension in the latent space. The proposed framework provides a principled framework for interpretable, low-parameter, and symmetry-preserving dimensional reduction, bridging the gap between Fourier representations and modern neural architectures for scientific and physics-informed learning.
Authors: Benjamin Turtel, Danny Franklin, Kris Skotheim, Luke Hewitt, Philipp Schoenegger
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been an effective approach for improving Large Language Models' reasoning in domains such as coding and mathematics. Here, we apply RLVR methods towards forecasting future real-world events - a challenging task for RL due to the very noisy (and delayed) outcomes involved. Using a novel dataset of recent questions from a prediction market, and accompanying relevant news headlines, we show that a compact (14B) reasoning model can be trained to match or surpass the predictive accuracy of frontier models like o1, while greatly improving probabilistic calibration. The model's performance is also practically meaningful: in a Polymarket trading simulation, we estimate that its bets would have yielded a return on investment of over 10% across all questions in the test set. We detail and compare approaches used in training our model, including augmenting our training-data with synthetic prediction questions, guardrails for learning stability, and median prediction sampling at inference-time.
Authors: David Koplow, Tomaso Poggio, Liu Ziyin
Abstract: Hebbian and anti-Hebbian plasticity are widely observed in the biological brain, yet their theoretical understanding remains limited. In this work, we find that when a learning method is regularized with L2 weight decay, its learning signal will gradually align with the direction of the Hebbian learning signal as it approaches stationarity. This Hebbian-like behavior is not unique to SGD: almost any learning rule, including random ones, can exhibit the same signature long before learning has ceased. We also provide a theoretical explanation for anti-Hebbian plasticity in regression tasks, demonstrating how it can arise naturally from gradient or input noise, and offering a potential reason for the observed anti-Hebbian effects in the brain. Certainly, our proposed mechanisms do not rule out any conventionally established forms of Hebbian plasticity and could coexist with them extensively in the brain. A key insight for neurophysiology is the need to develop ways to experimentally distinguish these two types of Hebbian observations.
Authors: Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, Sanjay Lall, Sajjad Amini, Seyed-Mohsen Moosavi-Dezfooli
Abstract: Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge. Recent efforts have explored both supervised and unsupervised adversarial fine-tuning strategies. We identify two key limitations in these approaches: (i) they often suffer from instability, especially during the early stages of fine-tuning, resulting in suboptimal convergence and degraded performance on clean data, and (ii) they exhibit a suboptimal trade-off between robustness and clean data accuracy, hindering the simultaneous optimization of both objectives. To overcome these challenges, we propose Lagrangian-Optimized Robust Embeddings (LORE), a novel unsupervised adversarial fine-tuning framework. LORE utilizes constrained optimization, which offers a principled approach to balancing competing goals, such as improving robustness while preserving nominal performance. By enforcing embedding-space proximity constraints, LORE effectively maintains clean data performance throughout adversarial fine-tuning. Extensive experiments show that LORE significantly improves zero-shot adversarial robustness with minimal degradation in clean data accuracy. Furthermore, we demonstrate the effectiveness of the adversarially fine-tuned CLIP image encoder in out-of-distribution generalization and enhancing the interpretability of image embeddings.
Authors: Xichen Ye, Yifan Wu, Weizhong Zhang, Cheng Jin, Yifan Chen
Abstract: The Influence Function (IF) is a widely used technique for assessing the impact of individual training samples on model predictions. However, existing IF methods often fail to provide reliable influence estimates in deep neural networks, particularly when applied to noisy training data. This issue does not stem from inaccuracies in parameter change estimation, which has been the primary focus of prior research, but rather from deficiencies in loss change estimation, specifically due to the sharpness of validation risk. In this work, we establish a theoretical connection between influence estimation error, validation set risk, and its sharpness, underscoring the importance of flat validation minima for accurate influence estimation. Furthermore, we introduce a novel estimation form of Influence Function specifically designed for flat validation minima. Experimental results across various tasks validate the superiority of our approach.
Authors: Antonio Orvieto, Robert M. Gower
Abstract: Understanding the remarkable efficacy of Adam when training transformer-based language models has become a central research topic within the optimization community. To gain deeper insights, several simplifications of Adam have been proposed, such as the signed gradient and signed momentum methods. In this work, we conduct an extensive empirical study - training over 1500 language models across different data configurations and scales - comparing Adam to several known simplified variants. We find that signed momentum methods are faster than SGD, but consistently underperform relative to Adam, even after careful tuning of momentum, clipping setting and learning rates. However, our analysis reveals a compelling option that preserves near-optimal performance while allowing for new insightful reformulations: constraining the Adam momentum parameters to be equal, beta1 = beta2. Beyond robust performance, this choice affords new theoretical insights, highlights the "secret sauce" on top of signed momentum, and grants a precise statistical interpretation: we show that Adam in this setting implements a natural online algorithm for estimating the mean and variance of gradients-one that arises from a mean-field Gaussian variational inference perspective.
Authors: An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri, Vy Tuong Dang, Anh Totti Nguyen, Daeyoung Kim
Abstract: Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may notoriously sway their outputs towards wrong or biased answers. In this work, we test how the knowledge about popular subjects hurt the accuracy of vision language models (VLMs) on standard, objective visual tasks of counting and identification. We find that state-of-the-art VLMs are strongly biased (e.g., unable to recognize the 4th stripe has been added to a 3-stripe Adidas logo) scoring an average of 17.05% accuracy in counting (e.g., counting stripes in an Adidas-like logo) across 7 diverse domains from animals, logos, chess, board games, optical illusions, to patterned grids. Removing image backgrounds nearly doubles accuracy (21.09 percentage points), revealing that contextual visual cues trigger these biased responses. Further analysis of VLMs' reasoning patterns shows that counting accuracy initially rises with thinking tokens, reaching ~40%, before declining with excessive reasoning. Our work presents an interesting failure mode in VLMs and a human-supervised automated framework for testing VLM biases. Code and data are available at: vlmsarebiased.github.io.
Authors: Javier Bisbal, Julio Sotelo, Maria I Vald\'es, Pablo Irarrazaval, Marcelo E Andia, Julio Garc\'ia, Jos\'e Rodriguez-Palomarez, Francesca Raimondi, Cristi\'an Tejos, Sergio Uribe
Abstract: Background and Objective: Plane reformatting for four-dimensional phase contrast MRI (4D flow MRI) is time-consuming and prone to inter-observer variability, which limits fast cardiovascular flow assessment. Deep reinforcement learning (DRL) trains agents to iteratively adjust plane position and orientation, enabling accurate plane reformatting without the need for detailed landmarks, making it suitable for images with limited contrast and resolution such as 4D flow MRI. However, current DRL methods assume that test volumes share the same spatial alignment as the training data, limiting generalization across scanners and institutions. To address this limitation, we introduce AdaPR (Adaptive Plane Reformatting), a DRL framework that uses a local coordinate system to navigate volumes with arbitrary positions and orientations. Methods: We implemented AdaPR using the Asynchronous Advantage Actor-Critic (A3C) algorithm and validated it on 88 4D flow MRI datasets acquired from multiple vendors, including patients with congenital heart disease. Results: AdaPR achieved a mean angular error of 6.32 +/- 4.15 degrees and a distance error of 3.40 +/- 2.75 mm, outperforming global-coordinate DRL methods and alternative non-DRL methods. AdaPR maintained consistent accuracy under different volume orientations and positions. Flow measurements from AdaPR planes showed no significant differences compared to two manual observers, with excellent correlation (R^2 = 0.972 and R^2 = 0.968), comparable to inter-observer agreement (R^2 = 0.969). Conclusion: AdaPR provides robust, orientation-independent plane reformatting for 4D flow MRI, achieving flow quantification comparable to expert observers. Its adaptability across datasets and scanners makes it a promising candidate for medical imaging applications beyond 4D flow MRI.
Authors: Yanjun Fu, Faisal Hamman, Sanghamitra Dutta
Abstract: Instruction tuning is essential for Large Language Models (LLMs) to effectively follow user instructions. To improve training efficiency and reduce data redundancy, recent works use LLM-based scoring functions, e.g., Instruction-Following Difficulty (IFD), to select high-quality instruction-tuning data with scores above a threshold. While these data selection methods often lead to models that can match or even exceed the performance of models trained on the full datasets, we identify two key limitations: (i) they assess quality at the sample level, ignoring token-level informativeness; and (ii) they overlook the robustness of the scoring method, often selecting a sample due to superficial lexical features instead of its true quality. In this work, we propose Token-Selective HIeRarchical Data Selection for Instruction Tuning (T-SHIRT), a novel data selection framework that introduces a new scoring method to include only informative tokens in quality evaluation and also promotes robust and reliable samples whose neighbors also show high quality with less local inconsistencies. We demonstrate that models instruction-tuned on a curated dataset (only 5% of the original size) using T-SHIRT can outperform those trained on the entire large-scale dataset by up to 5.48 points on average across eight benchmarks. Across various LLMs and training set scales, our method consistently surpasses existing state-of-the-art data selection techniques, while also remaining both cost-effective and highly efficient. For instance, by using GPT-2 for score computation, we are able to process a dataset of 52k samples in 40 minutes on a single GPU. Our code is available at https://github.com/Dynamite321/T-SHIRT.
Authors: Annabelle Sujun Tang, Christopher Priebe, Rohan Mahapatra, Lianhui Qin, Hadi Esmaeilzadeh
Abstract: While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven substantial performance improvements, but existing compilers struggle with neural workloads due to the exponentially large and highly interdependent space of possible transformations. Although existing stochastic search techniques can be effective, they are often sample-inefficient and fail to leverage the structural context underlying compilation decisions. We set out to investigate the research question of whether reasoning with large language models (LLMs), without any retraining, can leverage the context-aware decision space of compiler optimizations to significantly improve sample efficiency. To that end, we introduce a novel compilation framework (dubbed Reasoning Compiler) that formulates optimization as a sequential, context-aware decision process guided by a large language model and structured Monte Carlo tree search (MCTS). The LLM acts as a proposal mechanism, suggesting hardware-informed transformations that reflect the current program state and accumulated performance feedback. MCTS incorporates the LLM-generated proposals to balance exploration and exploitation, facilitating structured, context-sensitive traversal of the expansive compiler optimization space. By achieving substantial speedups with markedly fewer samples than leading neural compilers, our approach demonstrates the potential of LLM-guided reasoning to transform the landscape of compiler optimization.
Authors: Hanlin Yu, Berfin Inal, Georgios Arvanitidis, Soren Hauberg, Francesco Locatello, Marco Fumero
Abstract: Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different representations, even when learning the same task on the same data. However, it has recently been shown that when a latent structure is shared between distinct latent spaces, relative distances between representations can be preserved, up to distortions. Building on this idea, we demonstrate that exploiting the differential-geometric structure of latent spaces of neural models, it is possible to capture precisely the transformations between representational spaces trained on similar data distributions. Specifically, we assume that distinct neural models parametrize approximately the same underlying manifold, and introduce a representation based on the pullback metric that captures the intrinsic structure of the latent space, while scaling efficiently to large models. We validate experimentally our method on model stitching and retrieval tasks, covering autoencoders and vision foundation discriminative models, across diverse architectures, datasets, and pretraining schemes.
Authors: Rishwanth Raghu, Axel Levy, Gordon Wetzstein, Ellen D. Zhong
Abstract: Protein structure prediction models are now capable of generating accurate 3D structural hypotheses from sequence alone. However, they routinely fail to capture the conformational diversity of dynamic biomolecular complexes, often requiring heuristic MSA subsampling approaches for generating alternative states. In parallel, cryo-electron microscopy (cryo-EM) has emerged as a powerful tool for imaging near-native structural heterogeneity, but is challenged by arduous pipelines to transform raw experimental data into atomic models. Here, we bridge the gap between these modalities, combining cryo-EM density maps with the rich sequence and biophysical priors learned by protein structure prediction models. Our method, CryoBoltz, guides the sampling trajectory of a pretrained biomolecular structure prediction model using both global and local structural constraints derived from density maps, driving predictions towards conformational states consistent with the experimental data. We demonstrate that this flexible yet powerful inference-time approach allows us to build atomic models into heterogeneous cryo-EM maps across a variety of dynamic biomolecular systems including transporters and antibodies. Code is available at https://github.com/ml-struct-bio/cryoboltz .
Authors: Mattie Ji, Amauri H. Souza, Vikas Garg
Abstract: Including intricate topological information (e.g., cycles) provably enhances the expressivity of message-passing graph neural networks (GNNs) beyond the Weisfeiler-Leman (WL) hierarchy. Consequently, Persistent Homology (PH) methods are increasingly employed for graph representation learning. In this context, recent works have proposed decorating classical PH diagrams with vertex and edge features for improved expressivity. However, these methods still fail to capture basic graph structural information. In this paper, we propose SpectRe -- a new topological descriptor for graphs that integrates spectral information into PH diagrams. Notably, SpectRe is strictly more expressive than existing descriptors on graphs. We also introduce notions of global and local stability to analyze existing descriptors and establish that SpectRe is locally stable. Finally, experiments on synthetic and real-world datasets demonstrate the effectiveness of SpectRe and its potential to enhance the capabilities of graph models in relevant learning tasks. Code is available at https://github.com/Aalto-QuML/SpectRe/.
Authors: Yonatan Ashlag, Uri Koren, Mirco Mutti, Esther Derman, Pierre-Luc Bacon, Shie Mannor
Abstract: State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization improves robustness to structured and spatially correlated perturbations. These types of variation are common in transfer learning but often overlooked by standard robust RL methods, which typically focus on small, uncorrelated changes. We provide a comprehensive characterization of these robustness properties, including formal guarantees under reward and transition uncertainty, as well as settings where the method performs poorly. Much of our analysis contrasts state entropy with the widely used policy entropy regularization, highlighting their different benefits. Finally, from a practical standpoint, we illustrate that compared with policy entropy, the robustness advantages of state entropy are more sensitive to the number of rollouts used for policy evaluation.
Authors: Jing Liu, Toshiaki Koike-Akino, Ye Wang, Hassan Mansour, Matthew Brand
Abstract: To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-training quantization and pruning. Drawing connections between activation-aware weight pruning and sparse approximation problems, and motivated by the success of Iterative Hard Thresholding (IHT), we propose a unified method for Activation-aware Weight pruning and quantization via Projected gradient descent (AWP). Our experiments demonstrate that AWP outperforms state-of-the-art LLM pruning and quantization methods. Theoretical convergence guarantees of the proposed method for pruning are also provided.
Authors: Esther Rodriguez, Monica Welfert, Samuel McDowell, Nathan Stromberg, Julian Antolin Camarena, Lalitha Sankar
Abstract: Diffusion models have achieved impressive performance in generating high-quality and diverse synthetic data. However, their success typically assumes a class-balanced training distribution. In real-world settings, multi-class data often follow a long-tailed distribution, where standard diffusion models struggle -- producing low-diversity and lower-quality samples for tail classes. While this degradation is well-documented, its underlying cause remains poorly understood. In this work, we investigate the behavior of diffusion models trained on long-tailed datasets and identify a key issue: the latent representations (from the bottleneck layer of the U-Net) for tail class subspaces exhibit significant overlap with those of head classes, leading to feature borrowing and poor generation quality. Importantly, we show that this is not merely due to limited data per class, but that the relative class imbalance significantly contributes to this phenomenon. To address this, we propose COntrastive Regularization for Aligning Latents (CORAL), a contrastive latent alignment framework that leverages supervised contrastive losses to encourage well-separated latent class representations. Experiments demonstrate that CORAL significantly improves both the diversity and visual quality of samples generated for tail classes relative to state-of-the-art methods.
Authors: Itay Lamprecht, Asaf Karnieli, Yair Hanani, Niv Giladi, Daniel Soudry
Abstract: Training and inference of Large Language Models (LLMs) with tensor-parallelism requires substantial communication to synchronize activations. Our findings suggest that with a few minor adjustments to current practices, LLMs can be trained without fully synchronizing activations, reducing bandwidth demands. We name this "Communication-Aware Architecture for Tensor-parallelism" (CAAT-Net). We train a 7B parameter CAAT-Net model and show that tensor-parallel communication can be reduced by up to 50% with no significant drop in pretraining accuracy across nearly all evaluated benchmarks. We also experiment with smaller 130M and 1.1B models to show the robustness and scalability of our method. We find that, in some scenarios, validation loss can even improve when reducing communication. Finally, we demonstrate how CAAT-Net accelerates both training and inference workloads across various settings and model sizes.
Authors: Vishnu Vinod, Krishna Pillutla, Abhradeep Guha Thakurta
Abstract: As major progress in LLM-based long-form text generation enables paradigms such as retrieval-augmented generation (RAG) and inference-time scaling, safely incorporating private information into the generation remains a critical open question. We present InvisibleInk, a highly scalable long-form text generation framework satisfying rigorous differential privacy guarantees with respect to the sensitive reference texts. It interprets sampling from the LLM's next-token-distribution as the exponential mechanism over the LLM logits with two innovations. First, we reduce the privacy cost by isolating and clipping only the sensitive information in the model logits (relative to the public logits). Second, we improve text quality by sampling without any privacy cost from a small superset of the top-$k$ private tokens. Empirical evaluations demonstrate a consistent $8\times$ (or more) reduction in computation cost over state-of-the-art baselines to generate long-form private text of the same utility across privacy levels. InvisibleInk is able to generate, for the first time, high-quality private long-form text at less than $4$-$8\times$ times the computation cost of non-private generation, paving the way for its practical use. We open-source a pip-installable Python package (invink) for InvisibleInk at https://github.com/cerai-iitm/invisibleink.
Authors: Lydia T. Liu, Inioluwa Deborah Raji, Angela Zhou, Luke Guerdan, Jessica Hullman, Daniel Malinsky, Bryan Wilder, Simone Zhang, Hammaad Adam, Amanda Coston, Ben Laufer, Ezinne Nwankwo, Michael Zanger-Tishler, Eli Ben-Michael, Solon Barocas, Avi Feller, Marissa Gerchick, Talia Gillis, Shion Guha, Daniel Ho, Lily Hu, Kosuke Imai, Sayash Kapoor, Joshua Loftus, Razieh Nabi, Arvind Narayanan, Ben Recht, Juan Carlos Perdomo, Matthew Salganik, Mark Sendak, Alexander Tolbert, Berk Ustun, Suresh Venkatasubramanian, Angelina Wang, Ashia Wilson
Abstract: Many automated decision systems (ADS) are designed to solve prediction problems -- where the goal is to learn patterns from a sample of the population and apply them to individuals from the same population. In reality, these prediction systems operationalize holistic policy interventions in deployment. Once deployed, ADS can shape impacted population outcomes through an effective policy change in how decision-makers operate, while also being defined by past and present interactions between stakeholders and the limitations of existing organizational, as well as societal, infrastructure and context. In this work, we consider the ways in which we must shift from a prediction-focused paradigm to an interventionist paradigm when considering the impact of ADS within social systems. We argue this requires a new default problem setup for ADS beyond prediction, to instead consider predictions as decision support, final decisions, and outcomes. We highlight how this perspective unifies modern statistical frameworks and other tools to study the design, implementation, and evaluation of ADS systems, and point to the research directions necessary to operationalize this paradigm shift. Using these tools, we characterize the limitations of focusing on isolated prediction tasks, and lay the foundation for a more intervention-oriented approach to developing and deploying ADS.
Authors: Simon Matrenok, Skander Moalla, Caglar Gulcehre
Abstract: Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage offline or off-policy data, such as DPO and REBEL, are limited to learning from preference pairs or relative signals. To bridge this gap, we introduce Quantile Reward Policy Optimization (QRPO), which learns from pointwise absolute rewards while preserving the simplicity and offline applicability of DPO-like methods. QRPO uses quantile rewards to enable regression to the closed-form solution of the KL-regularized RL objective. This reward yields an analytically tractable partition function, removing the need for relative signals to cancel this term. Moreover, QRPO scales with increased compute to estimate quantile rewards, opening a new dimension for pre-computation scaling. Empirically, QRPO consistently achieves top performance on chat and coding evaluations--reward model scores, AlpacaEval 2, and LeetCode--compared to DPO, REBEL, and SimPO across diverse datasets and 8B-scale models. Finally, we find that training with robust rewards instead of converting them to preferences induces less length bias.
Authors: Azimov Sherkhon, Susana Lopez-Moreno, Eric Dolores-Cuenca, Sieun Lee, Sangil Kim
Abstract: Nonlinear vector autoregression (NVAR) and reservoir computing (RC) have shown promise in forecasting chaotic dynamical systems, such as the Lorenz-63 model and El Nino-Southern Oscillation. However, their reliance on fixed nonlinear transformations - polynomial expansions in NVAR or random feature maps in RC - limits their adaptability to high noise or complex real-world data. Furthermore, these methods also exhibit poor scalability in high-dimensional settings due to costly matrix inversion during optimization. We propose a data-adaptive NVAR model that combines delay-embedded linear inputs with features generated by a shallow, trainable multilayer perceptron (MLP). Unlike standard NVAR and RC models, the MLP and linear readout are jointly trained using gradient-based optimization, enabling the model to learn data-driven nonlinearities, while preserving a simple readout structure and improving scalability. Initial experiments across multiple chaotic systems, tested under noise-free and synthetically noisy conditions, showed that the adaptive model outperformed in predictive accuracy the standard NVAR, a leaky echo state network (ESN) - the most common RC model - and a hybrid ESN, thereby showing robust forecasting under noisy conditions.
Authors: T. Anderson Keller
Abstract: Data arrives at our senses as a continuous stream, smoothly transforming from one instant to the next. These smooth transformations can be viewed as continuous symmetries of the environment that we inhabit, defining equivalence relations between stimuli over time. In machine learning, neural network architectures that respect symmetries of their data are called equivariant and have provable benefits in terms of generalization ability and sample efficiency. To date, however, equivariance has been considered only for static transformations and feed-forward networks, limiting its applicability to sequence models, such as recurrent neural networks (RNNs), and corresponding time-parameterized sequence transformations. In this work, we extend equivariant network theory to this regime of 'flows' -- one-parameter Lie subgroups capturing natural transformations over time, such as visual motion. We begin by showing that standard RNNs are generally not flow equivariant: their hidden states fail to transform in a geometrically structured manner for moving stimuli. We then show how flow equivariance can be introduced, and demonstrate that these models significantly outperform their non-equivariant counterparts in terms of training speed, length generalization, and velocity generalization, on both next step prediction and sequence classification. We present this work as a first step towards building sequence models that respect the time-parameterized symmetries which govern the world around us.
Authors: Datta Nimmaturi, Vaishnavi Bhargava, Rajat Ghosh, Johnu George, Debojyoti Dutta
Abstract: Fine-tuning large language models (LLMs) for reasoning tasks using reinforcement learning methods like Group Relative Policy Optimization (GRPO) is computationally expensive. To address this, we propose a predictive framework that models training dynamics and helps optimize resource usage. Through experiments on Llama and Qwen models (3B 8B), we derive an empirical scaling law based on model size, initial performance, and training progress. This law predicts reward trajectories and identifies three consistent training phases: slow start, rapid improvement, and plateau. We find that training beyond certain number of an epoch offers little gain, suggesting earlier stopping can significantly reduce compute without sacrificing performance. Our approach generalizes across model types, providing a practical guide for efficient GRPO-based fine-tuning.
Authors: Agrim Bari, Parikshit Hegde, Gustavo de Veciana
Abstract: With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase computation structure: a prefill-phase that processes the full input prompt and a decode-phase that autoregressively generates tokens one at a time. This structure calls for new strategies for routing and scheduling requests. In this paper, we take a comprehensive approach to this challenge by developing a theoretical framework that models routing and scheduling in LLM inference systems. We identify two key design principles-optimal tiling and dynamic resource allocation-that are essential for achieving high throughput. Guided by these principles, we propose the Resource-Aware Dynamic (RAD) scheduler and prove that it achieves throughput optimality under mild conditions. To address practical Service Level Objectives (SLOs) such as serving requests with different Time Between Token (TBT) constraints, we design the SLO-Aware LLM Inference (SLAI) scheduler. SLAI uses real-time measurements to prioritize decode requests that are close to missing their TBT deadlines and reorders prefill requests based on known prompt lengths to further reduce the Time To First Token (TTFT) delays. We evaluate SLAI on the Openchat ShareGPT4 dataset using the Mistral-7B model on an NVIDIA RTX ADA 6000 GPU. Compared to Sarathi-Serve, SLAI reduces the median TTFT by 53% and increases the maximum serving capacity by 26% such that median TTFT is below 0.5 seconds, while meeting tail TBT latency constraints.
Authors: Hongwei Ma, Junbin Gao, Minh-Ngoc Tran
Abstract: Accurate, explainable and physically credible forecasting remains a persistent challenge for multivariate time-series whose statistical properties vary across domains. We propose DORIC, a Domain-Universal, ODE-Regularized, Interpretable-Concept Transformer for Time-Series Forecasting that generates predictions through five self-supervised, domain-agnostic concepts while enforcing differentiable residuals grounded in first-principles constraints.
Authors: Ziyu Zhou, Yiming Huang, Yanyun Wang, Yuankai Wu, James Kwok, Yuxuan Liang
Abstract: Irregular multivariate time series (IMTS), characterized by uneven sampling and inter-variate asynchrony, fuel many forecasting applications yet remain challenging to model efficiently. Canonical Pre-Alignment (CPA) has been widely adopted in IMTS modeling by padding zeros at every global timestamp, thereby alleviating inter-variate asynchrony and unifying the series length, but its dense zero-padding inflates the pre-aligned series length, especially when numerous variates are present, causing prohibitive compute overhead. Recent graph-based models with patching strategies sidestep CPA, but their local message passing struggles to capture global inter-variate correlations. Therefore, we posit that CPA should be retained, with the pre-aligned series properly handled by the model, enabling it to outperform state-of-the-art graph-based baselines that sidestep CPA. Technically, we propose KAFNet, a compact architecture grounded in CPA for IMTS forecasting that couples (1) Pre-Convolution module for sequence smoothing and sparsity mitigation, (2) Temporal Kernel Aggregation module for learnable compression and modeling of intra-series irregularity, and (3) Frequency Linear Attention blocks for the low-cost inter-series correlations modeling in the frequency domain. Experiments on multiple IMTS datasets show that KAFNet achieves state-of-the-art forecasting performance, with a 7.2$\times$ parameter reduction and a 8.4$\times$ training-inference acceleration.
Authors: Ngoc-Bao Nguyen, Sy-Tuyen Ho, Koh Jun Hao, Ngai-Man Cheung
Abstract: Model inversion (MI) attacks pose significant privacy risks by reconstructing private training data from trained neural networks. While prior studies have primarily examined unimodal deep networks, the vulnerability of vision-language models (VLMs) remains largely unexplored. In this work, we present the first systematic study of MI attacks on VLMs to understand their susceptibility to leaking private visual training data. Our work makes two main contributions. First, tailored to the token-generative nature of VLMs, we introduce a suite of token-based and sequence-based model inversion strategies, providing a comprehensive analysis of VLMs' vulnerability under different attack formulations. Second, based on the observation that tokens vary in their visual grounding, and hence their gradients differ in informativeness for image reconstruction, we propose Sequence-based Model Inversion with Adaptive Token Weighting (SMI-AW) as a novel MI for VLMs. SMI-AW dynamically reweights each token's loss gradient according to its visual grounding, enabling the optimization to focus on visually informative tokens and more effectively guide the reconstruction of private images. Through extensive experiments and human evaluations on a range of state-of-the-art VLMs across multiple datasets, we show that VLMs are susceptible to training data leakage. Human evaluation of the reconstructed images yields an attack accuracy of 61.21%, underscoring the severity of these privacy risks. Notably, we demonstrate that publicly released VLMs are vulnerable to such attacks. Our study highlights the urgent need for privacy safeguards as VLMs become increasingly deployed in sensitive domains such as healthcare and finance. Additional experiments are provided in Supp.
Authors: Lingwei Zhu, Haseeb Shah, Zheng Chen, Yukie Nagai, Martha White
Abstract: Behavior Regularized Policy Optimization (BRPO) leverages asymmetric (divergence) regularization to mitigate the distribution shift in offline Reinforcement Learning. This paper is the first to study the open question of symmetric regularization. We show that symmetric regularization does not permit an analytic optimal policy $\pi^*$, posing a challenge to practical utility of symmetric BRPO. We approximate $\pi^*$ by the Taylor series of Pearson-Vajda $\chi^n$ divergences and show that an analytic policy expression exists only when the series is capped at $n=5$. To compute the solution in a numerically stable manner, we propose to Taylor expand the conditional symmetry term of the symmetric divergence loss, leading to a novel algorithm: Symmetric $f$-Actor Critic (S$f$-AC). S$f$-AC achieves consistently strong results across various D4RL MuJoCo tasks. Additionally, S$f$-AC avoids per-environment failures observed in IQL, SQL, XQL and AWAC, opening up possibilities for more diverse and effective regularization choices for offline RL.
Authors: Huan Ma, Jiadong Pan, Jing Liu, Yan Chen, Joey Tianyi Zhou, Guangyu Wang, Qinghua Hu, Hua Wu, Changqing Zhang, Haifeng Wang
Abstract: Large Language Models (LLMs) are being increasingly deployed in real-world applications, but they remain susceptible to hallucinations, which produce fluent yet incorrect responses and lead to erroneous decision-making. Uncertainty estimation is a feasible approach to detect such hallucinations. For example, semantic entropy estimates uncertainty by considering the semantic diversity across multiple sampled responses, thus identifying hallucinations. However, semantic entropy relies on post-softmax probabilities and fails to capture the model's inherent uncertainty, causing it to be ineffective in certain scenarios. To address this issue, we introduce Semantic Energy, a novel uncertainty estimation framework that leverages the inherent confidence of LLMs by operating directly on logits of penultimate layer. By combining semantic clustering with a Boltzmann-inspired energy distribution, our method better captures uncertainty in cases where semantic entropy fails. Experiments across multiple benchmarks show that Semantic Energy significantly improves hallucination detection and uncertainty estimation, offering more reliable signals for downstream applications such as hallucination detection.
Authors: G. Charbel N. Kindji (MALT), Elisa Fromont (MALT), Lina Maria Rojas-Barahona, Tanguy Urvoy
Abstract: The rise of powerful generative models has sparked concerns over data authenticity. While detection methods have been extensively developed for images and text, the case of tabular data, despite its ubiquity, has been largely overlooked. Yet, detecting synthetic tabular data is especially challenging due to its heterogeneous structure and unseen formats at test time. We address the underexplored task of detecting synthetic tabular data ''in the wild'', i.e. when the detector is deployed on tables with variable and previously unseen schemas. We introduce a novel datum-wise transformer architecture that significantly outperforms the only previously published baseline, improving both AUC and accuracy by 7 points. By incorporating a table-adaptation component, our model gains an additional 7 accuracy points, demonstrating enhanced robustness. This work provides the first strong evidence that detecting synthetic tabular data in real-world conditions is feasible, and demonstrates substantial improvements over previous approaches. Following acceptance of the paper, we are finalizing the administrative and licensing procedures necessary for releasing the source code. This extended version will be updated as soon as the release is complete.
Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh
Abstract: The success of federated learning (FL) ultimately depends on how strategic participants behave under partial observability, yet most formulations still treat FL as a static optimization problem. We instead view FL deployments as governed strategic systems and develop an analytical framework that separates welfare-improving behavior from metric gaming. Within this framework, we introduce indices that quantify manipulability, the price of gaming, and the price of cooperation, and we use them to study how rules, information disclosure, evaluation metrics, and aggregator-switching policies reshape incentives and cooperation patterns. We derive threshold conditions for deterring harmful gaming while preserving benign cooperation, and for triggering auto-switch rules when early-warning indicators become critical. Building on these results, we construct a design toolkit including a governance checklist and a simple audit-budget allocation algorithm with a provable performance guarantee. Simulations across diverse stylized environments and a federated learning case study consistently match the qualitative and quantitative patterns predicted by our framework. Taken together, our results provide design principles and operational guidelines for reducing metric gaming while sustaining stable, high-welfare cooperation in FL platforms.
Authors: Syed Zain Abbas, Ehimare Okoyomon
Abstract: To address the lack of public power system data for machine learning research in energy networks, we investigate the use of variational graph autoencoders (VGAEs) for synthetic distribution grid generation. Using two open-source datasets, ENGAGE and DINGO, we evaluate four decoder variants and compare generated networks against the original grids using structural and spectral metrics. Results indicate that simple decoders fail to capture realistic topologies, while GCN-based approaches achieve strong fidelity on ENGAGE but struggle on the more complex DINGO dataset, producing artifacts such as disconnected components and repeated motifs. These findings highlight both the promise and limitations of VGAEs for grid synthesis, underscoring the need for more expressive generative models and robust evaluation. We release our models and analysis as open source to support benchmarking and accelerate progress in ML-driven power system research.
Authors: Sophia Sun, Rose Yu
Abstract: Conformal prediction has been explored as a general and efficient way to provide uncertainty quantification for time series. However, current methods struggle to handle time series data with change points - sudden shifts in the underlying data-generating process. In this paper, we propose a novel Conformal Prediction for Time-series with Change points (CPTC) algorithm, addressing this gap by integrating a model to predict the underlying state with online conformal prediction to model uncertainties in non-stationary time series. We prove CPTC's validity and improved adaptivity in the time series setting under minimum assumptions, and demonstrate CPTC's practical effectiveness on 6 synthetic and real-world datasets, showing improved validity and adaptivity compared to state-of-the-art baselines.
Authors: Yuqi Pan, Yupeng Feng, Jinghao Zhuang, Siyu Ding, Han Xu, Zehao Liu, Bohan Sun, Yuhong Chou, Xuerui Qiu, Anlin Deng, Anjie Hu, Shurong Wang, Peng Zhou, Man Yao, Jibin Wu, Jian Yang, Guoliang Sun, Bo Xu, Guoqi Li
Abstract: Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large models on non-NVIDIA platforms also poses challenges for stable and efficient training. To address this, we introduce SpikingBrain, a family of brain-inspired models designed for efficient long-context training and inference. SpikingBrain leverages the MetaX GPU cluster and focuses on three aspects: (1) Model Architecture: linear and hybrid-linear attention architectures with adaptive spiking neurons; (2) Algorithmic Optimizations: an efficient, conversion-based training pipeline and a dedicated spike coding framework; (3) System Engineering: customized training frameworks, operator libraries, and parallelism strategies tailored to MetaX hardware. Using these techniques, we develop two models: SpikingBrain-7B, a linear LLM, and SpikingBrain-76B, a hybrid-linear MoE LLM. These models demonstrate the feasibility of large-scale LLM development on non-NVIDIA platforms, and training remains stable for weeks on hundreds of MetaX GPUs with Model FLOPs Utilization at expected levels. SpikingBrain achieves performance comparable to open-source Transformer baselines while using only about 150B tokens for continual pre-training. Our models also significantly improve long-context efficiency and deliver inference with (partially) constant memory and event-driven spiking behavior. For example, SpikingBrain-7B attains over 100x speedup in Time to First Token for 4M-token sequences. Furthermore, the proposed spiking scheme achieves 69.15 percent sparsity, enabling low-power operation. Overall, this work demonstrates the potential of brain-inspired mechanisms to drive the next generation of efficient and scalable large model design.
Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh
Abstract: We introduce ORACLE, a framework that explains neural networks on tabular and scientific design data. It fits ANOVA-style main and pairwise interaction effects to a model's prediction surface. ORACLE treats a trained network as a black-box response, learns an orthogonal factorial surrogate on a discretized input grid, and uses simple centering and $\mu$-rebalancing steps to obtain main- and interaction-effect tables that remain $L^2$-consistent with the original model. The resulting grid-based interaction maps are easy to visualize, comparable across backbones, and directly connected to classical design-of-experiments analyses. On synthetic factorial and low- to medium-dimensional tabular regression benchmarks, ORACLE more accurately recovers ground-truth ANOVA interactions and hotspot structure than Monte Carlo SHAP-family interaction methods, as measured by ranking, localization, and cross-backbone stability metrics. In latent image and text settings, ORACLE instead delineates its natural scope, and our results indicate that grid-based ANOVA surrogates are most effective when features admit interpretable factorial structure, making ORACLE particularly well-suited to scientific and engineering tabular workflows that require stable, DoE-style interaction summaries.
Authors: Wenbo Lu, Shaoyi Zheng, Yuxuan Xia, Shengjie Wang
Abstract: Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in generated images but rely on GPU-inefficient operations (e.g., sorting, scattered writes), introducing overheads that negate theoretical speedups when paired with optimized attention implementations (e.g., FlashAttention). To bridge this gap, we propose Token Merge with Attention (ToMA), an off-the-shelf method that redesigns token reduction for GPU-aligned efficiency, with three key contributions: 1) a reformulation of token merge as a submodular optimization problem to select diverse tokens; 2) merge/unmerge as an attention-like linear transformation via GPU-friendly matrix operations; and 3) exploiting latent locality and sequential redundancy (pattern reuse) to minimize overhead. ToMA reduces SDXL/Flux generation latency by 24%/23%, respectively (with DINO $\Delta < 0.07$), outperforming prior methods. This work bridges the gap between theoretical and practical efficiency for transformers in diffusion. Code available at https://github.com/WenboLuu/ToMA.
Authors: Antonin Sulc
Abstract: The study of neural representations, both in biological and artificial systems, is increasingly revealing the importance of geometric and topological structures. Inspired by this, we introduce Event2Vec, a novel framework for learning representations of discrete event sequences. Our model leverages a simple, additive recurrent structure to learn composable, interpretable embeddings. We provide a theoretical analysis demonstrating that, under specific training objectives, our model's learned representations in a Euclidean space converge to an ideal additive structure. This ensures that the representation of a sequence is the vector sum of its constituent events, a property we term the linear additive hypothesis. To address the limitations of Euclidean geometry for hierarchical data, we also introduce a variant of our model in hyperbolic space, which is naturally suited to embedding tree-like structures with low distortion. We present experiments to validate our hypothesis. Quantitative evaluation on the Brown Corpus yields a Silhouette score of 0.0564, outperforming a Word2Vec baseline (0.0215), demonstrating the model's ability to capture structural dependencies without supervision.
Authors: Kristina P. Sinaga
Abstract: In the realm of distributed artificial intelligence (AI) and privacy-focused medical applications, this paper proposes a multi-view clustering framework that links quantum field theory with federated healthcare analytics. The method uses heat kernel coefficients from spectral analysis to convert Euclidean distances into geometry-aware similarity measures that capture the structure of diverse medical data. The framework is presented through the heat kernel distance (HKD) transformation, which has convergence guarantees. Two algorithms have been developed: The first, Heat Kernel-Enhanced Multi-View Fuzzy Clustering (HK-MVFC), is used for central analysis. The second, Federated Heat Kernel Multi-View Fuzzy Clustering (FedHK-MVFC), is used for secure, privacy-preserving learning across hospitals. FedHK-MVFC uses differential privacy and secure aggregation to enable HIPAA-compliant collaboration. Tests on synthetic cardiovascular patient datasets demonstrate increased clustering accuracy, reduced communication, and retained efficiency compared to centralized methods. After being validated on 10,000 synthetic patient records across two hospitals, the methods proved useful for collaborative phenotyping involving electrocardiogram (ECG) data, cardiac imaging data, and behavioral data. The proposed methods' theoretical contributions include update rules with proven convergence, adaptive view weighting, and privacy-preserving protocols. These contributions establish a new standard for geometry-aware federated learning in healthcare, translating advanced mathematics into practical solutions for analyzing sensitive medical data while ensuring rigor and clinical relevance.
Authors: Yuxi Lu, Biao Wu, Zhidong Li, Kunqi Li, Chenya Huang, Huacan Wang, Qizhen Lan, Ronghao Chen, Ling Chen, Bin Liang
Abstract: World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene settings, limiting their validation in real-world contexts with broad spatial coverage and complex semantics. Meanwhile, remote sensing applications urgently require spatial reasoning capabilities for disaster response and urban planning. This paper bridges these gaps by introducing the first framework for world modeling in remote sensing. We formulate remote sensing world modeling as direction-conditioned spatial extrapolation, where models generate semantically consistent adjacent image tiles given a central observation and directional instruction. To enable rigorous evaluation, we develop RSWISE (Remote Sensing World-Image Spatial Evaluation), a benchmark containing 1,600 evaluation tasks across four scenarios: general, flood, urban, and rural. RSWISE combines visual fidelity assessment with instruction compliance evaluation using GPT-4o as a semantic judge, ensuring models genuinely perform spatial reasoning rather than simple replication. Afterwards, we present RemoteBAGEL, a unified multimodal model fine-tuned on remote sensing data for spatial extrapolation tasks. Extensive experiments demonstrate that RemoteBAGEL consistently outperforms state-of-the-art baselines on RSWISE.
Authors: Kaustubh Sharma, Simardeep Singh, Parikshit Pareek
Abstract: Prior-data fitted networks (PFNs) are a promising alternative to time-consuming Gaussian process (GP) inference for creating fast surrogates of physical systems. PFN reduces the computational burden of GP-training by replacing Bayesian inference in GP with a single forward pass of a learned prediction model. However, with standard Transformer attention, PFNs show limited effectiveness on high-dimensional regression tasks. We introduce Decoupled-Value Attention (DVA)-- motivated by the GP property that the function space is fully characterized by the kernel over inputs and the predictive mean is a weighted sum of training targets. DVA computes similarities from inputs only and propagates labels solely through values. Thus, the proposed DVA mirrors the GP update while remaining kernel-free. We demonstrate that PFNs are backbone architecture invariant and the crucial factor for scaling PFNs is the attention rule rather than the architecture itself. Specifically, our results demonstrate that (a) localized attention consistently reduces out-of-sample validation loss in PFNs across different dimensional settings, with validation loss reduced by more than 50% in five- and ten-dimensional cases, and (b) the role of attention is more decisive than the choice of backbone architecture, showing that CNN, RNN and LSTM-based PFNs can perform at par with their Transformer-based counterparts. The proposed PFNs provide 64-dimensional power flow equation approximations with a mean absolute error of the order of E-03, while being over 80x faster than exact GP inference.
Authors: Hongyang He, Xinyuan Song, Yangfan He, Zeyu Zhang, Yanshu Li, Haochen You, Lifan Sun, Wenqiao Zhang
Abstract: We introduce TRiCo, a novel triadic game-theoretic co-training framework that rethinks the structure of semi-supervised learning by incorporating a teacher, two students, and an adversarial generator into a unified training paradigm. Unlike existing co-training or teacher-student approaches, TRiCo formulates SSL as a structured interaction among three roles: (i) two student classifiers trained on frozen, complementary representations, (ii) a meta-learned teacher that adaptively regulates pseudo-label selection and loss balancing via validation-based feedback, and (iii) a non-parametric generator that perturbs embeddings to uncover decision boundary weaknesses. Pseudo-labels are selected based on mutual information rather than confidence, providing a more robust measure of epistemic uncertainty. This triadic interaction is formalized as a Stackelberg game, where the teacher leads strategy optimization and students follow under adversarial perturbations. By addressing key limitations in existing SSL frameworks, such as static view interactions, unreliable pseudo-labels, and lack of hard sample modeling, TRiCo provides a principled and generalizable solution. Extensive experiments on CIFAR-10, SVHN, STL-10, and ImageNet demonstrate that TRiCo consistently achieves state-of-the-art performance in low-label regimes, while remaining architecture-agnostic and compatible with frozen vision backbones.Code:https://github.com/HoHongYeung/NeurIPS25-TRiCo.
Authors: Hugh Xuechen Liu, K{\i}van\c{c} Tatar
Abstract: Bipartite knowledge graphs in niche domains are typically data-poor and edge-sparse, which hinders link prediction. We introduce AEGIS (Authentic Edge Growth In Sparsity), an edge-only augmentation framework that resamples existing training edges -either uniformly simple or with inverse-degree bias degree-aware -thereby preserving the original node set and sidestepping fabricated endpoints. To probe authenticity across regimes, we consider naturally sparse graphs (game design pattern's game-pattern network) and induce sparsity in denser benchmarks (Amazon, MovieLens) via high-rate bond percolation. We evaluate augmentations on two complementary metrics: AUC-ROC (higher is better) and the Brier score (lower is better), using two-tailed paired t-tests against sparse baselines. On Amazon and MovieLens, copy-based AEGIS variants match the baseline while the semantic KNN augmentation is the only method that restores AUC and calibration; random and synthetic edges remain detrimental. On the text-rich GDP graph, semantic KNN achieves the largest AUC improvement and Brier score reduction, and simple also lowers the Brier score relative to the sparse control. These findings position authenticity-constrained resampling as a data-efficient strategy for sparse bipartite link prediction, with semantic augmentation providing an additional boost when informative node descriptions are available.
Authors: David Benfield, Phan Tu Vuong, Alain Zemkoho
Abstract: Adversarial machine learning challenges the assumption that the underlying distribution remains consistent throughout the training and implementation of a prediction model. In particular, adversarial evasion considers scenarios where adversaries adapt their data to influence particular outcomes from established prediction models, such scenarios arise in applications such as spam email filtering, malware detection and fake-image generation, where security methods must be actively updated to keep up with the ever-improving generation of malicious data. Game theoretic models have been shown to be effective at modelling these scenarios and hence training resilient predictors against such adversaries. Recent advancements in the use of pessimistic bilevel optimsiation which remove assumptions about the convexity and uniqueness of the adversary's optimal strategy have proved to be particularly effective at mitigating threats to classifiers due to its ability to capture the antagonistic nature of the adversary. However, this formulation has not yet been adapted to regression scenarios. This article serves to propose a pessimistic bilevel optimisation program for regression scenarios which makes no assumptions on the convexity or uniqueness of the adversary's solutions.
Authors: Yaswanth Chittepu, Prasann Singhal, Greg Durrett, Scott Niekum
Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinforcement Learning from Human Feedback (RLHF), existing methods typically rely on no margins, fixed margins, or margins that are simplistic functions of preference ratings. However, such formulations often fail to account for the varying strengths of different preferences, for example some preferences are associated with larger margins between responses, or they rely on noisy margin information derived from ratings. We argue that modeling the strength of preferences can lead to better generalization and more faithful alignment. Furthermore, many existing methods that use adaptive margins assume access to accurate preference scores, which can be difficult for humans to provide reliably. We propose an approach that leverages preferences over preferences, that is annotations indicating which of two preferences reflects a stronger distinction. We use this ordinal signal to infer adaptive margins on a per-datapoint basis. We introduce an extension to Direct Preference Optimization (DPO), DPO-PoP, that incorporates adaptive margins from preference-over-preference supervision, enabling improved discriminative and generative performance. Empirically, our method outperforms vanilla DPO, DPO with fixed margins, and DPO with ground-truth margins on the UltraFeedback dataset. Additionally, we show that there is a tradeoff between discriminative and generative performance: improving test classification accuracy, particularly by correctly labeling weaker preferences at the expense of stronger ones, can lead to a decline in generative quality. To navigate this tradeoff, we propose two sampling strategies to gather preference-over-preference labels: one favoring discriminative performance and one favoring generative performance.
Authors: Ziheng Peng, Shijie Ren, Xinyue Gu, Linxiao Yang, Xiting Wang, Liang Sun
Abstract: While deep learning has achieved impressive performance in time series forecasting, it becomes increasingly crucial to understand its decision-making process for building trust in high-stakes scenarios. Existing interpretable models often provide only local and partial explanations, lacking the capability to reveal how heterogeneous and interacting input variables jointly shape the overall temporal patterns in the forecast curve. We propose ProtoTS, a novel interpretable forecasting framework that achieves both high accuracy and transparent decision-making through modeling prototypical temporal patterns. ProtoTS computes instance-prototype similarity based on a denoised representation that preserves abundant heterogeneous information. The prototypes are organized hierarchically to capture global temporal patterns with coarse prototypes while capturing finer-grained local variations with detailed prototypes, enabling expert steering and multi-level interpretability. Experiments on multiple realistic benchmarks, including a newly released LOF dataset, show that ProtoTS not only exceeds existing methods in forecast accuracy but also delivers expert-steerable interpretations for better model understanding and decision support.
Authors: Akhil Premkumar
Abstract: We draw a connection between diffusion models and the Kelly criterion for maximizing returns in betting games. A signal that is correlated with the outcome of such a game can be used to focus the bets on a narrow range of high probability predictions. Diffusion models share the same paradigm in that they gradually concentrate the probability mass to fit the training data. We show that the information stored in an unconditional diffusion model captures, in part, the joint correlation between the components of the data variable $X$. Conditional diffusion models store additional information to bind the signal $X$ with the conditioning information $Y$, equal to the mutual information between them. The latter is only a small fraction of the total information in the neural network if the data is low-dimensional. We examine why this does not hinder conditional generation.
Authors: Ya-Wei Eileen Lin, Ron Levie
Abstract: Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural networks by mapping each input to a standard form. Yet, it often introduces discontinuities that can affect stability during training, limit generalization, and complicate universal approximation theorems. In this paper, we address this by introducing adaptive canonicalization, a general framework in which the canonicalization depends both on the input and the network. Specifically, we present the adaptive canonicalization based on prior maximization, where the standard form of the input is chosen to maximize the predictive confidence of the network. We prove that this construction yields continuous and symmetry-respecting models that admit universal approximation properties. We propose two applications of our setting: (i) resolving eigenbasis ambiguities in spectral graph neural networks, and (ii) handling rotational symmetries in point clouds. We empirically validate our methods on molecular and protein classification, as well as point cloud classification tasks. Our adaptive canonicalization outperforms the three other common solutions to equivariant machine learning: data augmentation, standard canonicalization, and equivariant architectures.
Authors: Pirzada Suhail, Aditya Anand, Amit Sethi
Abstract: Machine learning models, by virtue of training, learn a large repertoire of decision rules for any given input, and any one of these may suffice to justify a prediction. However, in high-dimensional input spaces, such rules are difficult to identify and interpret. In this paper, we introduce EXP-CAM: an explanation generation and circuit discovery approach using Classifier Activation Matching. EXP-CAM can generate minimal and faithful explanations for the decisions of pre-trained image classifiers that not only preserve the model's decision but are also concise and human-readable. We aim to identify minimal explanations that not only preserve the model's decision but are also concise and human-readable. To achieve this, we train a lightweight auto-encoder to produce binary masks that learns to highlight the decision-wise critical regions of an image while discarding irrelevant background. The training objective integrates activation alignment across multiple layers, consistency at the output label, priors that encourage sparsity, and compactness, along with a robustness constraint that enforces faithfulness. The minimal explanations so generated also lead us to mechanistically interpreting the model internals. In this regard we also introduce a circuit readout procedure wherein using the explanation's forward pass and gradients, we identify active channels and construct a channel-level graph, scoring inter-layer edges by ingress weight magnitude times source activation and feature-to-class links by classifier weight magnitude times feature activation. Together, these contributions provide a practical bridge between minimal input-level explanations and a mechanistic understanding of the internal computations driving model decisions.
Authors: Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma, Wee Peng Tay
Abstract: Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic graphs, where connected nodes often belong to different classes, remains limited. Most existing methods rely on complex augmentation schemes, intricate encoders, or negative sampling, which raises the question of whether such complexity is truly necessary in this challenging setting. In this work, we revisit the foundations of supervised and unsupervised learning on graphs and uncover a simple yet effective principle for GCL: mitigating node feature noise by aggregating it with structural features derived from the graph topology. This observation suggests that the original node features and the graph structure naturally provide two complementary views for contrastive learning. Building on this insight, we propose an embarrassingly simple GCL model that uses a GCN encoder to capture structural features and an MLP encoder to isolate node feature noise. Our design requires neither data augmentation nor negative sampling, yet achieves state-of-the-art results on heterophilic benchmarks with minimal computational and memory overhead, while also offering advantages in homophilic graphs in terms of complexity, scalability, and robustness. We provide theoretical justification for our approach and validate its effectiveness through extensive experiments, including robustness evaluations against both black-box and white-box adversarial attacks.
Authors: Julian Coda-Forno, Zhuokai Zhao, Qiang Zhang, Dipesh Tamboli, Weiwei Li, Xiangjun Fan, Lizhu Zhang, Eric Schulz, Hsiao-Ping Tseng
Abstract: Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two hypotheses aimed at improving latent communication over Liu et al. (2024): (H1) increase channel capacity; (H2) learn communication via joint finetuning. Under matched latent-token budgets on GPT-2 and Qwen-3, H2 is consistently strongest while H1 yields modest gains. A unified soft-embedding baseline, a single model with the same forward pass and shared representations, using the same latent-token budget, nearly matches H2 and surpasses H1, suggesting current dual designs mostly add compute rather than qualitatively improving reasoning. Across GSM8K, ProsQA, and a Countdown stress test with increasing branching factor, scaling the latent-token budget beyond small values fails to improve robustness. Latent analyses show overlapping subspaces with limited specialization, consistent with weak reasoning gains. We conclude dual-model latent reasoning remains promising in principle, but likely requires objectives and training schedules that explicitly shape latent spaces for algorithmic planning.
Authors: Jialin Liu, Lisang Ding, Stanley Osher, Wotao Yin
Abstract: Implicit models, an emerging model class, compute outputs by iterating a single parameter block to a fixed point. This architecture realizes an infinite-depth, weight-tied network that trains with constant memory, significantly reducing memory needs for the same level of performance compared to explicit models. While it is empirically known that these compact models can often match or even exceed the accuracy of larger explicit networks by allocating more test-time compute, the underlying mechanism remains poorly understood. We study this gap through a nonparametric analysis of expressive power. We provide a strict mathematical characterization, showing that a simple and regular implicit operator can, through iteration, progressively express more complex mappings. We prove that for a broad class of implicit models, this process lets the model's expressive power scale with test-time compute, ultimately matching a much richer function class. The theory is validated across four domains: image reconstruction, scientific computing, operations research, and LLM reasoning, demonstrating that as test-time iterations increase, the complexity of the learned mapping rises, while the solution quality simultaneously improves and stabilizes.
Authors: Armin Gerami, Ramani Duraiswami
Abstract: Transformer models have become increasingly popular in financial applications, yet their potential risk making and biases remain under-explored. The purpose of this work is to audit the reliance of the model on volatile data for decision-making, and quantify how the frequency of price movements affects the model's prediction confidence. We employ a transformer model for prediction, and introduce a metric based on Partial Information Decomposition (PID) to measure the influence of each asset on the model's decision making. Our analysis reveals two key observations: first, the model disregards data volatility entirely, and second, it is biased toward data with lower-frequency price movements.
Authors: Prateek Humane, Paolo Cudrano, Daniel Z. Kaplan, Matteo Matteucci, Supriyo Chakraborty, Irina Rish
Abstract: Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on indirect heuristics such as problem difficulty or trace length, while instruction-tuning has explored a broader range of automated selection strategies, but rarely in the context of reasoning. We propose to define reasoning data quality using influence functions, which measure the causal effect of individual CoT examples on downstream accuracy, and introduce influence-based pruning, which consistently outperforms perplexity and embedding-based baselines on math reasoning within a model family.
Authors: Moein E. Samadi, Andreas Schuppert
Abstract: Foundation models have rapidly advanced AI, raising the question of whether their decisions will ultimately surpass human strategies in real-world domains. The exponential, and possibly super-exponential, pace of AI development makes such analysis elusive. Nevertheless, many application areas that matter for daily life and society show only modest gains so far; a prominent case is diagnosing and treating dynamically evolving disease in intensive care. The common challenge is adapting complex systems to dynamic environments. Effective strategies must optimize outcomes in systems composed of strongly interacting functions while avoiding shared side effects; this requires reliable, self-adaptive modeling. These tasks align with building digital twins of highly complex systems whose mechanisms are not fully or quantitatively understood. It is therefore essential to develop methods for self-adapting AI models with minimal data and limited mechanistic knowledge. As this challenge extends beyond medicine, AI should demonstrate clear superiority in these settings before assuming broader decision-making roles. We identify the curse of dimensionality as a fundamental barrier to efficient self-adaptation and argue that monolithic foundation models face conceptual limits in overcoming it. As an alternative, we propose a decentralized architecture of interacting small agent networks (SANs). We focus on agents representing the specialized substructure of the system, where each agent covers only a subset of the full system functions. Drawing on mathematical results on the learning behavior of SANs and evidence from existing applications, we argue that swarm-learning in diverse swarms can enable self-adaptive SANs to deliver superior decision-making in dynamic environments compared with monolithic foundation models, though at the cost of reduced reproducibility in detail.
Authors: Tavish McDonald, Bo Lei, Stanislav Fort, Bhavya Kailkhura, Brian Bartoldson
Abstract: Models are susceptible to adversarially out-of-distribution (OOD) data despite large training-compute investments into their robustification. Zaremba et al. (2025) make progress on this problem at test time, showing LLM reasoning improves satisfaction of model specifications designed to thwart attacks, resulting in a correlation between reasoning effort and robustness to jailbreaks. However, this benefit of test compute fades when attackers are given access to gradients or multimodal inputs. We address this gap, clarifying that inference-compute offers benefits even in such cases. Our approach argues that compositional generalization, through which OOD data is understandable via its in-distribution (ID) components, enables adherence to defensive specifications on adversarially OOD inputs. Namely, we posit the Robustness from Inference Compute Hypothesis (RICH): inference-compute defenses profit as the model's training data better reflects the attacked data's components. We empirically support this hypothesis across vision language model and attack types, finding robustness gains from test-time compute if specification following on OOD data is unlocked by compositional generalization. For example, InternVL 3.5 gpt-oss 20B gains little robustness when its test compute is scaled, but such scaling adds significant robustness if we first robustify its vision encoder. This correlation of inference-compute's robustness benefit with base model robustness is the rich-get-richer dynamic of the RICH: attacked data components are more ID for robustified models, aiding compositional generalization to OOD data. Thus, we advise layering train-time and test-time defenses to obtain their synergistic benefit.
Authors: Chen Wang, Zhaochun Li, Jionghao Bai, Yuzhi Zhang, Shisheng Cui, Zhou Zhao, Yue Wang
Abstract: Reinforcement Learning (RL) is essential for enhancing the reasoning capabilities of large language models (LLMs), yet the widely adopted Group Relative Policy Optimization (GRPO) suffers from entropy collapse, causing exploration to vanish and policies to converge prematurely. As a result, RL is widely believed to be incapable of expanding the reasoning frontier of LLMs. Existing entropy-regularized methods introduce an inevitable trade-off between reward and entropy, leading to exploration accompanied by non-negligible optimization bias. In this work, we prove that temperature-guided REINFORCE can modulate policy entropy, and propose Arbitrary Entropy Policy Optimization (AEPO), which reformulates entropy regularization as a policy-gradient optimization problem. Rather than manipulating entropy directly, AEPO implicitly regulates it by applying a REINFORCE regularization term on temperature-adjusted samples, ensuring that entropy is controlled but never dominates optimization, thereby enabling arbitrary and principled entropy regulation. Experiments show that AEPO outperforms RL baselines on both pass@1 and pass@$k$, and even surpasses the base model on pass@1024. By modulating entropy precisely, AEPO achieves more effective optimization dynamics and provides direct empirical evidence that entropy, exploration, and performance are intrinsically linked.
Authors: Shiyu Chen, Ningyuan Huang, Soledad Villar
Abstract: Graph Neural Networks (GNNs) typically scale with the number of graph edges, making them well suited for sparse graphs but less efficient on dense graphs, such as point clouds or molecular interactions. A common remedy is to sparsify the graph via similarity thresholding or distance pruning, but this forces an arbitrary choice of a single interaction scale and discards crucial information from other scales. To overcome this limitation, we introduce a multi-view graph-tuple framework. Instead of a single graph, our graph-tuple framework partitions the graph into disjoint subgraphs, capturing primary local interactions and weaker, long-range connections. We then learn multi-view representations from the graph-tuple via a heterogeneous message-passing architecture inspired by the theory of non-commuting operators, which we formally prove is strictly more expressive and guarantees a lower oracle risk compared to single-graph message-passing models. We instantiate our framework on two scientific domains: molecular property prediction from feature-scarce Coulomb matrices and cosmological parameter inference from geometric point clouds. On both applications, our multi-view graph-tuple models demonstrate better performance than single-graph baselines, highlighting the power and versatility of our multi-view approach.
Authors: Konstantinos Barmpas, Na Lee, Alexandros Koliousis, Yannis Panagakis, Dimitrios A. Adamos, Nikolaos Laskaris, Stefanos Zafeiriou
Abstract: Electroencephalography (EEG) captures neural activity across multiple temporal and spectral scales, yielding signals that are rich but complex for representation learning. Recently, EEG foundation models trained to predict masked signal-tokens have shown promise for learning generalizable representations. However, their performance is hindered by their signal tokenization modules. Existing neural tokenizers fail to preserve high-frequency dynamics, limiting their ability to reconstruct EEG signals with high fidelity. We introduce NeuroRVQ, a scalable Large Brainwave Model (LBM) centered on a codebook-based tokenizer. Our tokenizer integrates: (i) multi-scale feature extraction modules that capture the full frequency neural spectrum; (ii) hierarchical residual vector quantization (RVQ) codebooks for high-resolution encoding; and, (iii) an EEG signal phase- and amplitude-aware loss function for efficient training. This design enables efficient EEG compression while supporting accurate reconstruction across all frequency bands, leading to robust generative masked modeling. Our empirical results demonstrate that NeuroRVQ achieves lower reconstruction error and outperforms existing LBMs on a variety of downstream tasks. More broadly, NeuroRVQ tokenizer establishes a strong prior for codebook-based general-purpose brainwave models, enabling advances in neural decoding, generative modeling and multimodal biosignal integration.
Authors: Xingjian Wu, Xiangfei Qiu, Hanyin Cheng, Zhengyu Li, Jilin Hu, Chenjuan Guo, Bin Yang
Abstract: Time Series Forecasting has made significant progress with the help of Patching technique, which partitions time series into multiple patches to effectively retain contextual semantic information into a representation space beneficial for modeling long-term dependencies. However, conventional patching partitions a time series into adjacent patches, which causes a fixed representation space, thus resulting in insufficiently expressful representations. In this paper, we pioneer the exploration of constructing a selective representation space to flexibly include the most informative patches for forecasting. Specifically, we propose the Selective Representation Space (SRS) module, which utilizes the learnable Selective Patching and Dynamic Reassembly techniques to adaptively select and shuffle the patches from the contextual time series, aiming at fully exploiting the information of contextual time series to enhance the forecasting performance of patch-based models. To demonstrate the effectiveness of SRS module, we propose a simple yet effective SRSNet consisting of SRS and an MLP head, which achieves state-of-the-art performance on real-world datasets from multiple domains. Furthermore, as a novel plug-and-play module, SRS can also enhance the performance of existing patch-based models. The resources are available at https://github.com/decisionintelligence/SRSNet.
Authors: Hongwei Ma, Junbin Gao, Minh-ngoc Tran
Abstract: Long-horizon multivariate time-series forecasting is challenging because realistic predictions must (i) denoise heterogeneous signals, (ii) track time-varying cross-series dependencies, and (iii) remain stable and physically plausible over long rollout horizons. We present PRISM, which couples a score-based diffusion preconditioner with a dynamic, correlation-thresholded graph encoder and a forecast head regularized by generic physics penalties. We prove contraction of the induced horizon dynamics under mild conditions and derive Lipschitz bounds for graph blocks, explaining the model's robustness. On six standard benchmarks , PRISM achieves consistent SOTA with strong MSE and MAE gains.
Authors: Peng Wang, Minghao Gu, Qiang Huang
Abstract: Catastrophic forgetting is a well-documented challenge in model fine-tuning, particularly when the downstream domain has limited labeled data or differs substantially from the pre-training distribution. Existing parameter-efficient fine-tuning methods largely operate in the weight space by modifying or augmenting the parameters of the pre-trained model, which can lead to models that are overly specialized to the observed downstream data. Recent studies suggest that one mechanism underlying such forgetting is the introduction of intruder dimensions into the representation space during fine-tuning. To mitigate the risk of overwriting pre-trained knowledge and to enhance robustness, we propose Vector-based Feature Adaptation (VeFA), a new fine-tuning method that operates directly in the feature space, which naturally avoids generating intruder dimensions. VeFA performs element-wise adaptation on individual features, thereby ensuring that the effective fine-tuned weights always remain within the column space of the pre-trained weight matrix. This feature-space adaptation perspective is inspired by the idea of effect equivalence modeling (EEM) of downstream lurking variables that induce distribution shifts, which posits that the influence of unobserved factors can be represented as an equivalent aggregate effect on observed features. By compensating for the effects of downstream lurking variables via a lightweight feature-level transformation, VeFA preserves the pre-trained representations and improves model generalization under distribution shift. We evaluate VeFA against LoRA on image classification, NLU, and NLG benchmarks, considering both standard fine-tuning performance and robustness; across these tasks, VeFA achieves comparable fine-tuning performance while consistently exhibiting stronger robustness.
Authors: Bhavya Vasudeva, Puneesh Deora, Yize Zhao, Vatsal Sharan, Christos Thrampoulidis
Abstract: The growing adoption of spectrum-aware matrix-valued optimizers such as Muon and Shampoo in deep learning motivates a systematic study of their generalization properties and, in particular, when they might outperform competitive algorithms. We approach this question by introducing appropriate simplifying abstractions as follows: First, we use imbalanced data as a testbed. Second, we study the canonical form of such optimizers, which is Spectral Gradient Descent (SpecGD) -- each update step is $UV^T$ where $U\Sigma V^T$ is the truncated SVD of the gradient. Third, within this framework we identify a canonical setting for which we precisely quantify when SpecGD outperforms vanilla Euclidean GD. For a Gaussian mixture data model and both linear and bilinear models, we show that unlike GD, which prioritizes learning dominant principal components of the data first, SpecGD learns all principal components of the data at equal rates. We demonstrate how this translates to a growing gap in balanced accuracy favoring SpecGD early in training and further show that the gap remains consistent even when the GD counterpart uses adaptive step-sizes via normalization. By extending the analysis to deep linear models, we show that depth amplifies these effects. We empirically verify our theoretical findings on a variety of imbalanced datasets. Our experiments compare practical variants of spectral methods, like Muon and Shampoo, against their Euclidean counterparts and Adam. The results validate our findings that these spectral optimizers achieve superior generalization by promoting a more balanced learning of the data's underlying components.
Authors: Job Petrov\v{c}i\v{c}, David Eliecer Narvaez Denis, Ljup\v{c}o Todorovski
Abstract: Premise selection is a key bottleneck for scaling theorem proving in large formal libraries. Yet existing language-based methods often treat premises in isolation, ignoring the web of dependencies that connects them. We present a graph-augmented approach that combines dense text embeddings of Lean formalizations with graph neural networks over a heterogeneous dependency graph capturing both state-premise and premise-premise relations. On the LeanDojo Benchmark, our method outperforms the ReProver language-based baseline by over 25\% across standard retrieval metrics. These results suggest that relational information is beneficial for premise selection.
Authors: Tenghui Li, Guoxu Zhou, Xuyang Zhao, Yuning Qiu, Qibin Zhao
Abstract: As the length of input text grows, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce memory usage but suffer from numerical precision loss or suboptimal retention of key-value pairs. We introduce Low Rank Query and Key attention (LRQK), a two-stage framework that jointly decomposes the full-precision query and key matrices into compact rank-\(r\) factors during the prefill stage, and then uses these low-dimensional projections to compute proxy attention scores in \(\mathcal{O}(lr)\) time at each decode step. By selecting only the top-\(k\) tokens and a small fixed set of recent tokens, LRQK employs a mixed GPU-CPU cache with a hit-and-miss mechanism that transfers only missing full-precision KV pairs, thereby preserving exact attention outputs while reducing CPU-GPU data movement. Extensive experiments on the RULER and LongBench benchmarks with LLaMA-3-8B and Qwen2.5-7B demonstrate that LRQK matches or surpasses leading sparse-attention methods in long context settings, while delivering significant memory savings with minimal loss in accuracy. Our code is available at https://github.com/tenghuilee/LRQK.
Authors: Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Fernando Maia, Adeylson Guimar\~aes Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Vanderlei Cunha Parro, Fl\'avio Almeida de Magalh\~aes Cipparrone, Alexandre Dias Porto Chiavegatto Filho, Victor W\"unsch Filho, Tatiana Natasha Toporcov
Abstract: This study presents a comparative methodological analysis of six machine learning models for survival analysis (MLSA). Using data from nearly 45,000 colorectal cancer patients in the Hospital-Based Cancer Registries of S\~ao Paulo, we evaluated Random Survival Forest (RSF), Gradient Boosting for Survival Analysis (GBSA), Survival SVM (SSVM), XGBoost-Cox (XGB-Cox), XGBoost-AFT (XGB-AFT), and LightGBM (LGBM), capable of predicting survival considering censored data. Hyperparameter optimization was performed with different samplers, and model performance was assessed using the Concordance Index (C-Index), C-Index IPCW, time-dependent AUC, and Integrated Brier Score (IBS). Survival curves produced by the models were compared with predictions from classification algorithms, and predictor interpretation was conducted using SHAP and permutation importance. XGB-AFT achieved the best performance (C-Index = 0.7618; IPCW = 0.7532), followed by GBSA and RSF. The results highlight the potential and applicability of MLSA to improve survival prediction and support decision making.
Authors: Md Tanvirul Alam, Nidhi Rastogi
Abstract: Mathematical reasoning is a central challenge for large language models (LLMs), requiring not only correct answers but also faithful reasoning processes. Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising approach for enhancing such capabilities; however, its ability to foster genuine reasoning remains unclear. We investigate RLVR on two combinatorial problems with fully verifiable solutions: \emph{Activity Scheduling} and the \emph{Longest Increasing Subsequence}, using carefully curated datasets with unique optima. Across multiple reward designs, we find that RLVR improves evaluation metrics but often by reinforcing superficial heuristics rather than acquiring new reasoning strategies. These findings highlight the limits of RLVR generalization, emphasizing the importance of benchmarks that disentangle genuine mathematical reasoning from shortcut exploitation and provide faithful measures of progress. Code available at https://github.com/xashru/rlvr-seq-generalization.
Authors: Austin Meek, Eitan Sprejer, Iv\'an Arcuschin, Austin J. Brockmeier, Steven Basart
Abstract: Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This visibility could help us spot unsafe or misaligned behavior (monitorability), but only if the CoT is transparent about its internal reasoning (faithfulness). Fully measuring faithfulness is difficult, so researchers often focus on examining the CoT in cases where the model changes its answer after adding a cue to the input. This proxy finds some instances of unfaithfulness but loses information when the model maintains its answer, and does not investigate aspects of reasoning not tied to the cue. We extend these results to a more holistic sense of monitorability by introducing verbosity: whether the CoT lists every factor needed to solve the task. We combine faithfulness and verbosity into a single monitorability score that shows how well the CoT serves as the model's external `working memory', a property that many safety schemes based on CoT monitoring depend on. We evaluate instruction-tuned and reasoning models on BBH, GPQA, and MMLU. Our results show that models can appear faithful yet remain hard to monitor when they leave out key factors, and that monitorability differs sharply across model families. We release our evaluation code using the Inspect library to support reproducible future work.
Authors: Satchel Grant, Simon Jerome Han, Alexa R. Tartaglini, Christopher Potts
Abstract: A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create out-of-distribution (divergent) representations, and whether this raises concerns about how faithful their resulting explanations are to the target model in its natural state. First, we demonstrate theoretically and empirically that common causal intervention techniques often do shift internal representations away from the natural distribution of the target model. Then, we provide a theoretical analysis of two cases of such divergences: "harmless" divergences that occur in the behavioral null-space of the layer(s) of interest, and "pernicious" divergences that activate hidden network pathways and cause dormant behavioral changes. Finally, in an effort to mitigate the pernicious cases, we apply and modify the Counterfactual Latent (CL) loss from Grant (2025) allowing representations from causal interventions to remain closer to the natural distribution, reducing the likelihood of harmful divergences while preserving the interpretive power of the interventions. Together, these results highlight a path towards more reliable interpretability methods.
Authors: Ragini Gupta, Naman Raina, Bo Chen, Li Chen, Claudiu Danilov, Josh Eckhardt, Keyshla Bernard, Klara Nahrstedt
Abstract: Modern IoT deployments for environmental sensing produce high volume spatiotemporal data to support downstream tasks such as forecasting, typically powered by machine learning models. While existing filtering and strategic deployment techniques optimize collected data volume at the edge, they overlook how variations in sampling frequencies and spatial coverage affect downstream model performance. In many forecasting models, incorporating data from additional sensors denoise predictions by providing broader spatial contexts. This interplay between sampling frequency, spatial coverage and different forecasting model architectures remain underexplored. This work presents a systematic study of forecasting models - classical models (VAR), neural networks (GRU, Transformer), spatio-temporal graph neural networks (STGNNs), and time series foundation models (TSFMs: Chronos Moirai, TimesFM) under varying spatial sensor nodes density and sampling intervals using real-world temperature data in a wireless sensor network. Our results show that STGNNs are effective when sensor deployments are sparse and sampling rate is moderate, leveraging spatial correlations via encoded graph structure to compensate for limited coverage. In contrast, TSFMs perform competitively at high frequencies but degrade when spatial coverage from neighboring sensors is reduced. Crucially, the multivariate TSFM Moirai outperforms all models by natively learning cross-sensor dependencies. These findings offer actionable insights for building efficient forecasting pipelines in spatio-temporal systems. All code for model configurations, training, dataset, and logs are open-sourced for reproducibility: https://github.com/UIUC-MONET-Projects/Benchmarking-Spatiotemporal-Forecast-Models
URLs: https://github.com/UIUC-MONET-Projects/Benchmarking-Spatiotemporal-Forecast-Models
Authors: Tzu-Yuan Huang, Armin Lederer, Dai-Jie Wu, Xiaobing Dai, Sihua Zhang, Stefan Sosnowski, Shao-Hua Sun, Sandra Hirche
Abstract: Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. Moreover, existing FM planners do not ensure the dynamical consistency, which potentially renders trajectories inexecutable. We address these shortcomings by proposing SAD-Flower, a novel framework for generating Safe, Admissible, and Dynamically consistent trajectories. Our approach relies on an augmentation of the flow with a virtual control input. Thereby, principled guidance can be derived using techniques from nonlinear control theory, providing formal guarantees for state constraints, action constraints, and dynamic consistency. Crucially, SAD-Flower operates without retraining, enabling test-time satisfaction of unseen constraints. Through extensive experiments across several tasks, we demonstrate that SAD-Flower outperforms various generative-model-based baselines in ensuring constraint satisfaction.
Authors: Mehmet Can Yavuz
Abstract: Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian posterior, which simplifies optimization but rules out correlated uncertainty and often yields entangled or redundant latent dimensions. We introduce the Multivariate Variational Autoencoder (MVAE), a tractable full-covariance extension of the VAE that augments the encoder with sample-specific diagonal scales and a global coupling matrix. This induces a multivariate Gaussian posterior of the form $N(\mu_\phi(x), C \operatorname{diag}(\sigma_\phi^2(x)) C^\top)$, enabling correlated latent factors while preserving a closed-form KL divergence and a simple reparameterization path. Beyond likelihood, we propose a multi-criterion evaluation protocol that jointly assesses reconstruction quality (MSE, ELBO), downstream discrimination (linear probes), probabilistic calibration (NLL, Brier, ECE), and unsupervised structure (NMI, ARI). Across Larochelle-style MNIST variants, Fashion-MNIST, and CIFAR-10/100, MVAE consistently matches or outperforms diagonal-covariance VAEs of comparable capacity, with particularly notable gains in calibration and clustering metrics at both low and high latent dimensions. Qualitative analyses further show smoother, more semantically coherent latent traversals and sharper reconstructions. All code, dataset splits, and evaluation utilities are released to facilitate reproducible comparison and future extensions of multivariate posterior models.
Authors: Brian B. Moser, Shalini Sarode, Federico Raue, Stanislav Frolov, Krzysztof Adamkiewicz, Arundhati Shanbhag, Joachim Folz, Tobias C. Nauen, Andreas Dengel
Abstract: Dataset distillation (DD) promises compact yet faithful synthetic data, but existing approaches often inherit the inductive bias of a single teacher model. As dataset size increases, this bias drives generation toward overly smooth, homogeneous samples, reducing intra-class diversity and limiting generalization. We present PRISM (PRIors from diverse Source Models), a framework that disentangles architectural priors during synthesis. PRISM decouples the logit-matching and regularization objectives, supervising them with different teacher architectures: a primary model for logits and a stochastic subset for batch-normalization (BN) alignment. On ImageNet-1K, PRISM consistently and reproducibly outperforms single-teacher methods (e.g., SRe2L) and recent multi-teacher variants (e.g., G-VBSM) at low- and mid-IPC regimes. The generated data also show significantly richer intra-class diversity, as reflected by a notable drop in cosine similarity between features. We further analyze teacher selection strategies (pre- vs. intra-distillation) and introduce a scalable cross-class batch formation scheme for fast parallel synthesis. Code will be released after the review period.
Authors: Federico Maddanu, Tommaso Proietti, Riccardo Crupi
Abstract: Detecting point anomalies in bank account balances is essential for financial institutions, as it enables the identification of potential fraud, operational issues, or other irregularities. Robust statistics is useful for flagging outliers and for providing estimates of the data distribution parameters that are not affected by contaminated observations. However, such a strategy is often less efficient and computationally expensive under high dimensional setting. In this paper, we propose and evaluate empirically several robust approaches that may be computationally efficient in medium and high dimensional datasets, with high breakdown points and low computational time. Our application deals with around 2.6 million daily records of anonymous users' bank account balances.
Authors: Vishal Joshua Meesala
Abstract: Modern deep learning systems are typically deployed as open-loop function approximators: they map inputs to outputs in a single pass, without regulating how much computation or explanatory effort is spent on a given case. In safety-critical settings, this is brittle: easy and ambiguous inputs receive identical processing, and uncertainty is only read off retrospectively from raw probabilities. We introduce the Surgical Cognitive Interpreter (SCI), a lightweight closed-loop metacognitive control layer that wraps an existing stochastic model and turns prediction into an iterative process. SCI monitors a scalar interpretive state SP(t), here instantiated as a normalized entropy-based confidence signal, and adaptively decides whether to stop, continue sampling, or abstain. The goal is not to improve accuracy per se, but to regulate interpretive error {\Delta}SP and expose a safety signal that tracks when the underlying model is likely to fail. We instantiate SCI around Monte Carlo dropout classifiers in three domains: vision (MNIST digits), medical time series (MIT-BIH arrhythmia), and industrial condition monitoring (rolling-element bearings). In all cases, the controller allocates more inference steps to misclassified inputs than to correct ones (up to about 3-4x on MNIST and bearings, and 1.4x on MIT-BIH). The resulting {\Delta}SP acts as a usable safety signal for detecting misclassifications (AUROC 0.63 on MNIST, 0.70 on MIT-BIH, 0.86 on bearings). Code and reproducibility: https://github.com/vishal-1344/sci
Authors: Han Meng, Gang Mei, Hong Tian, Nengxiong Xu, Jianbing Peng
Abstract: Rock discontinuities critically govern the mechanical behavior and stability of rock masses. Their internal distributions remain largely unobservable and are typically inferred from surface-exposed discontinuities using generative prediction approaches. However, surface-exposed observations are inherently sparse, and existing generative prediction approaches either fail to capture the underlying complex distribution patterns or lack robustness under data-sparse conditions. Here, we proposed a simple yet robust approach for statistically accurate generative prediction of rock discontinuities by utilizing a tabular foundation model. By leveraging the powerful sample learning capability of the foundation model specifically designed for small data, our approach can effectively capture the underlying complex distribution patterns within limited measured discontinuities. Comparative experiments on ten datasets with diverse scales and distribution patterns of discontinuities demonstrate superior accuracy and robustness over conventional statistical models and deep generative approaches. This work advances quantitative characterization of rock mass structures, supporting safer and more reliable data-driven geotechnical design.
Authors: Meng Zhu, Quan Xiao, Weidong Min
Abstract: Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to local and even global minima. Entering the era of large language models, although the scale of model parameters and data has increased, Adam remains the mainstream optimization algorithm. However, compared with stochastic gradient descent (SGD) based optimization algorithms, Adam is more likely to converge to non-flat minima. To address this issue, the AdamNX algorithm is proposed. Its core innovation lies in the proposition of a novel type of second-order moment estimation exponential decay rate, which gradually weakens the learning step correction strength as training progresses, and degrades to momentum SGD in the stable training period, thereby improving the stability of training in the stable period and possibly enhancing generalization ability. Experimental results show that our second-order moment estimation exponential decay rate is better than the current second-order moment estimation exponential decay rate, and AdamNX can stably outperform Adam and its variants in terms of performance. Our code is open-sourced at https://github.com/mengzhu0308/AdamNX.
Authors: Saif Ur Rehman, Wajid Yousuf
Abstract: The accurate solution of nonlinear hyperbolic partial differential equations (PDEs) remains challenging due to steep gradients, discontinuities, and multiscale structures that make conventional solvers computationally demanding. Physics-Informed Neural Networks (PINNs) embed the governing equations into the learning process, enabling mesh-free solution of PDEs, yet they often struggle to capture steep gradients, discontinuities, and complex nonlinear wave interactions. To address these limitations, we employ the Extended Physics-Informed Neural Network (XPINN) framework to solve the nonlinear Buckley-Leverett equation with a nonconvex flux, modeling immiscible two-phase flow in porous media. The computational domain is dynamically decomposed in space and time into evolving pre-shock and post-shock subdomains, allowing localized subnetworks to efficiently learn distinct flow behaviors, with coupling enforced via the Rankine-Hugoniot jump condition to ensure physically consistent flux continuity. We compare XPINN with standard PINNs and its variants, including PINN with artificial viscosity, PINN with Welge construction, and PINN with the Oleinik entropy condition, and across all cases, XPINN consistently outperforms the other methods, accurately resolving sharp fronts and capturing the correct physical behavior. Importantly, XPINN achieves this using the simpler Adam optimizer, whereas some PINN variants require more complex or higher-order strategies such as L-BFGS to reach comparable accuracy, demonstrating that XPINN is a robust and scalable approach for challenging hyperbolic PDEs without artificial diffusion or entropy corrections. The code is available at github.com/saifkhanengr/XPINN-for-Buckley-Leverett.
Authors: Jian Lu
Abstract: Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention, with growing efforts to reproduce and apply it. However, training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training are typically deployed on the same devices. While this approach reduces costs through resource consolidation, its synchronous execution imposes a computational coupling that prevents concurrent inference and training. In this study, we are returning to the strategy of separating inference and training deployment, and by introducing improvements in the data loader, we transform the conventional synchronous architecture into a periodically asynchronous framework, which allows for demand-driven, independent, and elastic scaling of each component, while the accuracy of the algorithm remains completely equivalent to the synchronization method, with both belonging to the on-policy strategy. It is worth emphasizing that we apply a unified tri-model architecture in the training phase, and we also proposed a shared-prompt attention mask to reduce repetitive computation. In practice, these works have achieved at least a threefold overall performance improvement in RL training on NPU platforms, indicating its potential for widespread application.
Authors: Dereck Piche, Mohammed Muqeeth, Milad Aghajohari, Juan Duque, Michael Noukhovitch, Aaron Courville
Abstract: As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual incentives can undermine collective welfare. While reinforcement learning (RL) has been effective for aligning large language models (LLMs) in the single-agent regime, prior small-network results suggest that standard RL in multi-agent settings often converges to defecting, self-interested policies. We show the same effect in LLMs: despite cooperative priors, RL-trained LLM agents develop opportunistic behavior that can exploit even advanced closed-source models. To address this tendency of RL to converge to poor equilibria, we adapt a recent opponent-learning awareness algorithm, Advantage Alignment, to fine-tune LLMs toward multi-agent cooperation and non-exploitability. We then introduce a group-relative baseline that simplifies advantage computation in iterated games, enabling multi-agent training at LLM scale. We also contribute a novel social dilemma environment, Trust-and-Split, which requires natural language communication to achieve high collective welfare. Across a wide range of social dilemmas, policies learned with Advantage Alignment achieve higher collective payoffs while remaining robust against exploitation by greedy agents. We release all of our code to support future work on multi-agent RL training for LLMs.
Authors: Chang Gao, Chujie Zheng, Xiong-Hui Chen, Kai Dang, Shixuan Liu, Bowen Yu, An Yang, Shuai Bai, Jingren Zhou, Junyang Lin
Abstract: Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often exhibit high variance-a phenomenon exacerbated in Mixture-of-Experts models-leading to unstable updates. Existing group-based policy optimization methods, such as GSPO and GRPO, alleviate this problem via hard clipping, making it difficult to maintain both stability and effective learning. We propose Soft Adaptive Policy Optimization (SAPO), which replaces hard clipping with a smooth, temperature-controlled gate that adaptively attenuates off-policy updates while preserving useful learning signals. Compared with GSPO and GRPO, SAPO is both sequence-coherent and token-adaptive. Like GSPO, SAPO maintains sequence-level coherence, but its soft gating forms a continuous trust region that avoids the brittle hard clipping band used in GSPO. When a sequence contains a few highly off-policy tokens, GSPO suppresses all gradients for that sequence, whereas SAPO selectively down-weights only the offending tokens and preserves the learning signal from the near-on-policy ones, improving sample efficiency. Relative to GRPO, SAPO replaces hard token-level clipping with smooth, temperature-controlled scaling, enabling more informative and stable updates. Empirical results on mathematical reasoning benchmarks indicate that SAPO exhibits improved training stability and higher Pass@1 performance under comparable training budgets. Moreover, we employ SAPO to train the Qwen3-VL model series, demonstrating that SAPO yields consistent performance gains across diverse tasks and different model sizes. Overall, SAPO provides a more reliable, scalable, and effective optimization strategy for RL training of LLMs.
Authors: Aodong Li, Abishek Sankararaman, Balakrishnan Narayanaswamy
Abstract: We study streaming data with categorical features where the vocabulary of categorical feature values is changing and can even grow unboundedly over time. Feature hashing is commonly used as a pre-processing step to map these categorical values into a feature space of fixed size before learning their embeddings. While these methods have been developed and evaluated for offline or batch settings, in this paper we consider online settings. We show that deterministic embeddings are sensitive to the arrival order of categories and suffer from forgetting in online learning, leading to performance deterioration. To mitigate this issue, we propose a probabilistic hash embedding (PHE) model that treats hash embeddings as stochastic and applies Bayesian online learning to learn incrementally from data. Based on the structure of PHE, we derive a scalable inference algorithm to learn model parameters and infer/update the posteriors of hash embeddings and other latent variables. Our algorithm (i) can handle an evolving vocabulary of categorical items, (ii) is adaptive to new items without forgetting old items, (iii) is implementable with a bounded set of parameters that does not grow with the number of distinct observed values on the stream, and (iv) is invariant to the item arrival order. Experiments in classification, sequence modeling, and recommendation systems in online learning setups demonstrate the superior performance of PHE while maintaining high memory efficiency (consumes as low as 2~4 memory of a one-hot embedding table). Supplementary materials are at https://github.com/aodongli/probabilistic-hash-embeddings
URLs: https://github.com/aodongli/probabilistic-hash-embeddings
Authors: Yaw Osei Adjei (Kwame Nkrumah University of Science,Technology), Frederick Ayivor (Independent Researcher, Fishers, Indiana, USA)
Abstract: Business Email Compromise (BEC) is a sophisticated social engineering threat that manipulates organizational hierarchies, leading to significant financial damage. According to the 2024 FBI Internet Crime Report, BEC accounts for over $2.9 billion in annual losses, presenting a massive economic asymmetry: the financial cost of a False Negative (fraud loss) exceeds the operational cost of a False Positive (manual review) by a ratio of approximately 5,480:1. This paper contrasts two detection paradigms: a Forensic Psycholinguistic Stream (CatBoost), which analyzes linguistic cues like urgency and authority with high interpretability, and a Semantic Stream (DistilBERT), which utilizes deep learning for contextual understanding. We evaluated both streams on a hybrid dataset (N=7,990) containing human-legitimate and AI-synthesized adversarial fraud. Benchmarked on Tesla T4 infrastructure, DistilBERT achieved near-perfect detection on synthetic threats (AUC >0.99, F1 =0.998) with acceptable real-time latency (7.4 ms). CatBoost achieved competitive detection (AUC =0.991, F1 =0.949) at 8.4x lower latency (0.8 ms) with negligible resource consumption. We conclude that while DistilBERT offers maximum accuracy for GPU-equipped organizations, CatBoost provides a viable, cost-effective alternative for edge deployments. Both approaches demonstrate a theoretical ROI exceeding 99.9% when optimized via cost-sensitive learning.
Authors: Fengze Yu, Leshu Li, Brad McDanel, Sai Qian Zhang
Abstract: Large language model (LLM) inference often suffers from high decoding latency and limited scalability across heterogeneous edge-cloud environments. Existing speculative decoding (SD) techniques accelerate token generation but remain confined to single-node execution. We propose DSD, a distributed speculative decoding framework that extends SD to multi-device deployments through coordinated draft-target execution. Given the lack of prior work on simulating this paradigm, we first introduce DSD-Sim, a discrete-event simulator that captures network, batching, and scheduling dynamics. Building on insights from DSD-Sim, we further design an Adaptive Window Control (AWC) policy that dynamically adjusts speculation window size to optimize throughput. Experiments across diverse workloads show that DSD achieves up to 1.1x speedup and 9.7% higher throughput over existing SD baselines, enabling agile and scalable LLM serving across edge and cloud.
Authors: Florian Rottach, William Rudman, Bastian Rieck, Harrisen Scells, Carsten Eickhoff
Abstract: Studying how embeddings are organized in space not only enhances model interpretability but also uncovers factors that drive downstream task performance. In this paper, we present a comprehensive analysis of topological and geometric measures across a wide set of text embedding models and datasets. We find a high degree of redundancy among these measures and observe that individual metrics often fail to sufficiently differentiate embedding spaces. Building on these insights, we introduce Unified Topological Signatures (UTS), a holistic framework for characterizing embedding spaces. We show that UTS can predict model-specific properties and reveal similarities driven by model architecture. Further, we demonstrate the utility of our method by linking topological structure to ranking effectiveness and accurately predicting document retrievability. We find that a holistic, multi-attribute perspective is essential to understanding and leveraging the geometry of text embeddings.
Authors: Ryan Cory-Wright, Jean Pauphilet
Abstract: Sparse Principal Component Analysis (sPCA) is a cardinal technique for obtaining combinations of features, or principal components (PCs), that explain the variance of high-dimensional datasets in an interpretable manner. This involves solving a sparsity and orthogonality constrained convex maximization problem, which is extremely computationally challenging. Most existing works address sparse PCA via methods-such as iteratively computing one sparse PC and deflating the covariance matrix-that do not guarantee the orthogonality, let alone the optimality, of the resulting solution when we seek multiple mutually orthogonal PCs. We challenge this status by reformulating the orthogonality conditions as rank constraints and optimizing over the sparsity and rank constraints simultaneously. We design tight semidefinite relaxations to supply high-quality upper bounds, which we strengthen via additional second-order cone inequalities when each PC's individual sparsity is specified. Further, we derive a combinatorial upper bound on the maximum amount of variance explained as a function of the support. We exploit these relaxations and bounds to propose exact methods and rounding mechanisms that, together, obtain solutions with a bound gap on the order of 0%-15% for real-world datasets with p = 100s or 1000s of features and r \in {2, 3} components. Numerically, our algorithms match (and sometimes surpass) the best performing methods in terms of fraction of variance explained and systematically return PCs that are sparse and orthogonal. In contrast, we find that existing methods like deflation return solutions that violate the orthogonality constraints, even when the data is generated according to sparse orthogonal PCs. Altogether, our approach solves sparse PCA problems with multiple components to certifiable (near) optimality in a practically tractable fashion.
Authors: Benoit Boulet Huiliang Zhang, Di Wu, Arnaud Zinflou
Abstract: The building sector is one of the largest contributors to global energy consumption. Improving its energy efficiency is essential for reducing operational costs and greenhouse gas emissions. Energy management systems (EMS) play a key role in monitoring and controlling building appliances efficiently and reliably. With the increasing integration of renewable energy, intelligent EMS solutions have received growing attention. Reinforcement learning (RL) has recently been explored for this purpose and shows strong potential. However, most RL-based EMS methods require a large number of training steps to learn effective control policies, especially when adapting to unseen buildings, which limits their practical deployment. This paper introduces MetaEMS, a meta-reinforcement learning framework for EMS. MetaEMS improves learning efficiency by transferring knowledge from previously solved tasks to new ones through group-level and building-level adaptation, enabling fast adaptation and effective control across diverse building environments. Experimental results demonstrate that MetaEMS adapts more rapidly to unseen buildings and consistently outperforms baseline methods across various scenarios.
Authors: YongTaek Lim, Suho Kang, Yewon Kim, Dokyung Yoon, KyungWoo Song
Abstract: Large-scale pre-trained models such as CLIP excel in transferability and robust generalization across diverse datasets. However, adapting these models to new datasets or domains is computationally costly, especially in low-resource or few-shot settings, and existing prompt-learning methods often lack interpretability. We introduce Efficient Prompt Learning with Knowledge Graph (EPLKG), which uses a knowledge graph to curate diverse, interpretable prompts and, where KG coverage is limited, augments this bank with LLM-generated human-readable visual descriptions. EPLKG operates entirely on cached CLIP image and text embeddings and employs a lightweight Gumbel-Softmax module to select a single prompt per image-class pair, enabling low-memory, fast training. Across 11 benchmarks, EPLKG reduces per-image training time by up to 45 percent and peak GPU memory by around 30 to 40 percent compared to strong prompt-learning baselines, while keeping the average base-new harmonic-mean accuracy within 2 percentage points, thereby improving the efficiency of model adaptation without sacrificing competitive performance or interpretability.
Authors: Du Nguyen
Abstract: We study the information geometry of $\bcc$-divergences from families of costs of the form $\mathsf{c}(x, \barx) =\mathsf{u}(x^{\mathfrak{t}}\barx)$ through the optimal transport point of view. Here, $\mathsf{u}$ is a scalar function with inverse $\mathsf{s}$, $x^{\ft}\barx$ is a nondegenerate bilinear pairing of vectors $x, \barx$ belonging to an open subset of $\mathbb{R}^n$. We compute explicitly the MTW tensor (or cross curvature) for the optimal transport problem on $\mathbb{R}^n$ with this cost. The condition that the MTW-tensor vanishes on null vectors under the Kim-McCann metric is a fourth-order nonlinear ODE, which could be reduced to a linear ODE of the form $\mathsf{s}^{(2)} - S\mathsf{s}^{(1)} + P\mathsf{s} = 0$ with constant coefficients $P$ and $S$. The resulting inverse functions include {\it Lambert} and {\it generalized inverse hyperbolic\slash trigonometric} functions. The square Euclidean metric and $\log$-type costs are equivalent to instances of these solutions. The optimal map may be written explicitly in terms of the potential function. For cost functions of a similar form on a hyperboloid model of the hyperbolic space and unit sphere, we also express this tensor in terms of algebraic expressions in derivatives of $\mathsf{s}$ using the Gauss-Codazzi equation, obtaining new families of strictly regular costs for these manifolds, including new families of {\it power function costs}. We express the divergence geometry of the $\mathsf{c}$-divergence in terms of the Kim-McCann metric, including a $\mathsf{c}$-Crouzeix identity and a formula for the primal connection. We analyze the $\sinh$-type hyperbolic cost, providing examples of $\mathsf{c}$-convex functions, which are used to construct a new \emph{local form} of the $\alpha$-divergences on probability simplices. We apply the optimal maps to sample the multivariate $t$-distribution.
Authors: Isao Ishikawa, Yuka Hashimoto, Masahiro Ikeda, Yoshinobu Kawahara
Abstract: This paper presents a novel approach for estimating the Koopman operator defined on a reproducing kernel Hilbert space (RKHS) and its spectra. We propose an estimation method, what we call Jet Extended Dynamic Mode Decomposition (JetEDMD), leveraging the intrinsic structure of RKHS and the geometric notion known as jets to enhance the estimation of the Koopman operator. This method refines the traditional Extended Dynamic Mode Decomposition (EDMD) in accuracy, especially in the numerical estimation of eigenvalues. This paper proves JetEDMD's superiority through explicit error bounds and convergence rate for special positive definite kernels, offering a solid theoretical foundation for its performance. We also investigate the spectral analysis of the Koopman operator, proposing the notion of an extended Koopman operator within a framework of a rigged Hilbert space. This notion leads to a deeper understanding of estimated Koopman eigenfunctions and capturing them outside the original function space. Through the theory of rigged Hilbert space, our study provides a principled methodology to analyze the estimated spectrum and eigenfunctions of Koopman operators, and enables eigendecomposition within a rigged RKHS. We also propose a new effective method for reconstructing the dynamical system from temporally-sampled trajectory data of the dynamical system with solid theoretical guarantee. We conduct several numerical simulations using the van der Pol oscillator, the Duffing oscillator, the H\'enon map, and the Lorenz attractor, and illustrate the performance of JetEDMD with clear numerical computations of eigenvalues and accurate predictions of the dynamical systems.
Authors: Linrui Dai, Rongzhao Zhang, Yongrui Yu, Xiaofan Zhang
Abstract: The recently emerging conditional diffusion models seem promising for mitigating the labor and expenses in building large 3D medical imaging datasets. However, previous studies on 3D CT generation primarily focus on specific organs characterized by a local structure and fixed contrast and have yet to fully capitalize on the benefits of both semantic and textual conditions. In this paper, we present GuideGen, a controllable framework based on easily-acquired text prompts to generate anatomical masks and corresponding CT volumes for the entire torso-from chest to pelvis. Our approach includes three core components: a text-conditional semantic synthesizer for creating realistic full-torso anatomies; an anatomy-aware high-dynamic-range (HDR) autoencoder for high-fidelity feature extraction across varying intensity levels; and a latent feature generator that ensures alignment between CT images, anatomical semantics and input prompts. Combined, these components enable data synthesis for segmentation tasks from only textual instructions. To train and evaluate GuideGen, we compile a multi-modality cancer imaging dataset with paired CT and clinical descriptions from 12 public TCIA datasets and one private real-world dataset. Comprehensive evaluations across generation quality, cross-modality alignment, and data usability on multi-organ and tumor segmentation tasks demonstrate GuideGen's superiority over existing CT generation methods. Relevant materials are available at https://github.com/OvO1111/GuideGen.
Authors: Yajie Bao, Yuyang Huo, Haojie Ren, Changliang Zou
Abstract: We study the problem of post-selection predictive inference in an online fashion. To avoid devoting resources to unimportant units, a preliminary selection of the current individual before reporting its prediction interval is common and meaningful in online predictive tasks. Since the online selection causes a temporal multiplicity in the selected prediction intervals, it is important to control the real-time false coverage-statement rate (FCR) which measures the overall miscoverage level. We develop a general framework named CAP (Calibration after Adaptive Pick) that performs an adaptive pick rule on historical data to construct a calibration set if the current individual is selected and then outputs a conformal prediction interval for the unobserved label. We provide tractable procedures for constructing the calibration set for popular online selection rules. We proved that CAP can achieve an exact selection-conditional coverage guarantee in the finite-sample and distribution-free regimes. To account for the distribution shift in online data, we also embed CAP into some recent dynamic conformal prediction algorithms and show that the proposed method can deliver long-run FCR control. Numerical results on both synthetic and real data corroborate that CAP can effectively control FCR around the target level and yield more narrowed prediction intervals over existing baselines across various settings.
Authors: Ayan Banerjee, Nityanand Mathur, Josep Llados, Umapada Pal, Anjan Dutta
Abstract: Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research has been mostly limited to the generation of single objects, rather than comprehensive scenes comprising multiple elements. In response, this work introduces SVGCraft, a novel end-to-end framework for the creation of vector graphics depicting entire scenes from textual descriptions. Utilizing a pre-trained LLM for layout generation from text prompts, this framework introduces a technique for producing masked latents in specified bounding boxes for accurate object placement. It introduces a fusion mechanism for integrating attention maps and employs a diffusion U-Net for coherent composition, speeding up the drawing process. The resulting SVG is optimized using a pre-trained encoder and LPIPS loss with opacity modulation to maximize similarity. Additionally, this work explores the potential of primitive shapes in facilitating canvas completion in constrained environments. Through both qualitative and quantitative assessments, SVGCraft is demonstrated to surpass prior works in abstraction, recognizability, and detail, as evidenced by its performance metrics (CLIP-T: 0.4563, Cosine Similarity: 0.6342, Confusion: 0.66, Aesthetic: 6.7832). The code will be available at https://github.com/ayanban011/SVGCraft.
Authors: Shahed Rezaei, Reza Najian Asl, Kianoosh Taghikhani, Ahmad Moeineddin, Michael Kaliske, Markus Apel
Abstract: We introduce a method that combines neural operators, physics-informed machine learning, and standard numerical methods for solving PDEs. The proposed approach extends each of the aforementioned methods and unifies them within a single framework. We can parametrically solve partial differential equations in a data-free manner and provide accurate sensitivities, meaning the derivatives of the solution space with respect to the design space. These capabilities enable gradient-based optimization without the typical sensitivity analysis costs, unlike adjoint methods that scale directly with the number of response functions. Our Finite Operator Learning (FOL) approach uses an uncomplicated feed-forward neural network model to directly map the discrete design space (i.e. parametric input space) to the discrete solution space (i.e. finite number of sensor points in the arbitrary shape domain) ensuring compliance with physical laws by designing them into loss functions. The discretized governing equations, as well as the design and solution spaces, can be derived from any well-established numerical techniques. In this work, we employ the Finite Element Method (FEM) to approximate fields and their spatial derivatives. Subsequently, we conduct Sobolev training to minimize a multi-objective loss function, which includes the discretized weak form of the energy functional, boundary conditions violations, and the stationarity of the residuals with respect to the design variables. Our study focuses on the steady-state heat equation within heterogeneous materials that exhibits significant phase contrast and possibly temperature-dependent conductivity. The network's tangent matrix is directly used for gradient-based optimization to improve the microstructure's heat transfer characteristics. ...
Authors: Haoran Wang, Xinji Mai, Zeng Tao, Junxiong Lin, Xuan Tong, Ivy Pan, Shaoqi Yan, Yan Wang, Shuyong Gao
Abstract: Affective Forecasting is an psychology task that involves predicting an individual's future emotional responses, often hampered by reliance on external factors leading to inaccuracies, and typically remains at a qualitative analysis stage. To address these challenges, we narrows the scope of Affective Forecasting by introducing the concept of Human-interaction-based Emotion Forecasting (EF). This task is set within the context of a two-party interaction, positing that an individual's emotions are significantly influenced by their interaction partner's emotional expressions and informational cues. This dynamic provides a structured perspective for exploring the patterns of emotional change, thereby enhancing the feasibility of emotion forecasting.
Authors: Purba Mukherjee, Antara Dey, Supratik Pal
Abstract: Reionization is one of the least understood processes in the evolution history of the Universe, mostly because of the numerous astrophysical processes occurring simultaneously about which we do not have a very clear idea so far. In this article, we use the Gaussian Process Regression (GPR) method to learn the reionization history and infer the astrophysical parameters. We reconstruct the UV luminosity density function using the HFF and early JWST data. From the reconstructed history of reionization, the global differential brightness temperature fluctuation during this epoch has been computed. We perform MCMC analysis of the global 21-cm signal using the instrumental specifications of SARAS, in combination with Lyman-$\alpha$ ionization fraction data, Planck optical depth measurements and UV luminosity data. Our analysis reveals that GPR can help infer the astrophysical parameters in a model-agnostic way than conventional methods. Additionally, we analyze the 21-cm power spectrum using the reconstructed history of reionization and demonstrate how the future 21-cm mission SKA, in combination with Planck and Lyman-$\alpha$ forest data, improves the bounds on the reionization astrophysical parameters by doing a joint MCMC analysis for the astrophysical parameters plus 6 cosmological parameters for $\Lambda$CDM model. The results make the GPR-based reconstruction technique a robust learning process and the inferences on the astrophysical parameters obtained therefrom are quite reliable that can be used for future analysis.
Authors: Hongyao Yu, Yixiang Qiu, Hao Fang, Tianqu Zhuang, Bin Chen, Sijin Yu, Bin Wang, Shu-Tao Xia, Ke Xu
Abstract: Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of MIAs across diverse settings, defense strategies have lagged behind -- struggling to balance model utility with robustness against increasingly sophisticated attacks. In this work, we propose the ideal inversion error to measure the privacy leakage, and our theoretical and empirical investigations reveals that higher-rank features are inherently more prone to privacy leakage. Motivated by this insight, we propose a lightweight and effective defense strategy based on low-rank feature filtering, which explicitly reduces the attack surface by constraining the dimension of intermediate representations. Extensive experiments across various model architectures and datasets demonstrate that our method consistently outperforms existing defenses, achieving state-of-the-art performance against a wide range of MIAs. Notably, our approach remains effective even in challenging regimes involving high-resolution data and high-capacity models, where prior defenses fail to provide adequate protection.
Authors: Peng Jin, Bo Zhu, Li Yuan, Shuicheng Yan
Abstract: In this work, we upgrade the multi-head attention mechanism, the core of the Transformer model, to improve efficiency while maintaining or surpassing the previous accuracy level. We show that multi-head attention can be expressed in the summation form. Drawing on the insight that not all attention heads hold equal significance, we propose Mixture-of-Head attention (MoH), a new architecture that treats attention heads as experts in the Mixture-of-Experts (MoE) mechanism. MoH has two significant advantages: First, MoH enables each token to select the appropriate attention heads, enhancing inference efficiency without compromising accuracy or increasing the number of parameters. Second, MoH replaces the standard summation in multi-head attention with a weighted summation, introducing flexibility to the attention mechanism and unlocking extra performance potential. Extensive experiments on ViT, DiT, and LLMs demonstrate that MoH outperforms multi-head attention by using only 50%-90% of the attention heads. Moreover, we demonstrate that pre-trained multi-head attention models, such as LLaMA3-8B, can be further continue-tuned into our MoH models. Notably, MoH-LLaMA3-8B achieves an average accuracy of 64.0% across 14 benchmarks, outperforming LLaMA3-8B by 2.4% by utilizing only 75% of the attention heads. We believe the proposed MoH is a promising alternative to multi-head attention and provides a strong foundation for developing advanced and efficient attention-based models.
Authors: Melissa Adrian, Jake A. Soloff, Rebecca Willett
Abstract: Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data. However, absent strong assumptions, such methods are highly unstable: if a single data point is removed from the training set, a different model may be selected. In this paper, we present a new approach to stabilizing model selection with theoretical stability guarantees that leverages a combination of bagging and an ''inflated'' argmax operation. Our method selects a small collection of models that all fit the data, and it is stable in that, with high probability, the removal of any training point will result in a collection of selected models that overlaps with the original collection. We illustrate this method in (a) a simulation in which strongly correlated covariates make standard LASSO model selection highly unstable, (b) a Lotka-Volterra model selection problem focused on identifying how competition in an ecosystem influences species' abundances, (c) a graph subset selection problem using cell-signaling data from proteomics, and (d) unsupervised $\kappa$-means clustering. In these settings, the proposed method yields stable, compact, and accurate collections of selected models, outperforming a variety of benchmarks.
Authors: Yen-Ting Lin, Zhehuai Chen, Piotr Zelasko, Zhen Wan, Xuesong Yang, Zih-Ching Chen, Krishna C Puvvada, Szu-Wei Fu, Ke Hu, Jun Wei Chiu, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank Wang, Chao-Han Huck Yang
Abstract: Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative 5.0% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with 15.5% to 27.6% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.
Authors: Yuan Lu
Abstract: Standard conformal prediction methods guarantee marginal coverage but often produce inefficient intervals that fail to adapt to local heteroscedasticity, while recent localized approaches often struggle to maintain validity across distinct subpopulations with varying noise profiles. To address these challenges, we introduce Localized Conformal Multi-Quantile Regression (LCMQR), a novel framework that synergizes multi-quantile information with kernel-based localization to construct efficient and adaptive prediction intervals. Theoretically, we resolve an inconsistency in Conformalized Composite Quantile Regression (CCQR) by proving that our consistent Average-then-Max scoring mechanism systematically yields tighter intervals than the Max-then-Average approach used in prior work. For heterogeneous environments, we extend this framework to Group-Calibrated LCMQR (GC-LCMQR) via a stratified calibration step that guarantees finite-sample validity within distinct subgroups. Experiments on benchmark datasets and an Individual Treatment Effect (ITE) task demonstrate that LCMQR achieves superior efficiency on standard benchmarks, while GC-LCMQR uniquely achieves group-level coverage for target subgroups in mixture populations where baselines fail.
Authors: Sihang Li, Siqi Tan, Bowen Chang, Jing Zhang, Chen Feng, Yiming Li
Abstract: Visual localization, which estimates a camera's pose within a known scene, is a fundamental capability for autonomous systems. While absolute pose regression (APR) methods have shown promise for efficient inference, they often struggle with generalization. Recent approaches attempt to address this through data augmentation with varied viewpoints, yet they overlook a critical factor: appearance diversity. In this work, we identify appearance variation as the key to robust localization. Specifically, we first lift real 2D images into 3D Gaussian Splats with varying appearance and deblurring ability, enabling the synthesis of diverse training data that varies not just in poses but also in environmental conditions such as lighting and weather. To fully unleash the potential of the appearance-diverse data, we build a two-branch joint training pipeline with an adversarial discriminator to bridge the syn-to-real gap. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods, reducing translation and rotation errors by 50\% and 41\% on indoor datasets, and 38\% and 44\% on outdoor datasets. Most notably, our method shows remarkable robustness in dynamic driving scenarios under varying weather conditions and in day-to-night scenarios, where previous APR methods fail. Project Page: https://ai4ce.github.io/RAP/
Authors: Michail Dontas, Yutong He, Naoki Murata, Yuki Mitsufuji, J. Zico Kolter, Ruslan Salakhutdinov
Abstract: This paper considers blind inverse image restoration, the task of predicting a target image from a degraded source when the degradation (i.e. the forward operator) is unknown. Existing solutions typically rely on restrictive assumptions such as operator linearity, curated training data or narrow image distributions limiting their practicality. We introduce LADiBI, a training-free method leveraging large-scale text-to-image diffusion to solve diverse blind inverse problems with minimal assumptions. Within a Bayesian framework, LADiBI uses text prompts to jointly encode priors for both target images and operators, unlocking unprecedented flexibility compared to existing methods. Additionally, we propose a novel diffusion posterior sampling algorithm that combines strategic operator initialization with iterative refinement of image and operator parameters, eliminating the need for highly constrained operator forms. Experiments show that LADiBI effectively handles both linear and challenging nonlinear image restoration problems across various image distributions, all without task-specific assumptions or retraining.
Authors: Muntasir Wahed, Kiet A. Nguyen, Adheesh Sunil Juvekar, Xinzhuo Li, Xiaona Zhou, Vedant Shah, Tianjiao Yu, Pinar Yanardag, Ismini Lourentzou
Abstract: Despite significant advancements in Large Vision-Language Models (LVLMs)' capabilities, existing pixel-grounding models operate in single-image settings, limiting their ability to perform detailed, fine-grained comparisons across multiple images. Conversely, current multi-image understanding models lack pixel-level grounding. Our work addresses this gap by introducing the task of multi-image pixel-grounded reasoning alongside PRIMA, an LVLM that integrates pixel-level grounding with robust multi-image reasoning to produce contextually rich, pixel-grounded explanations. Central to PRIMA is SQuARE, a vision module that injects cross-image relational context into compact query-based visual tokens before fusing them with the language backbone. To support training and evaluation, we curate M4SEG, a new multi-image reasoning segmentation benchmark consisting of $\sim$744K question-answer pairs that require fine-grained visual understanding across multiple images. PRIMA outperforms state-of-the-art baselines with $7.83\%$ and $11.25\%$ improvements in Recall and S-IoU, respectively. Ablation studies further demonstrate the effectiveness of the proposed SQuARE module in capturing cross-image relationships.
Authors: Jae Ho Chang, Massimiliano Russo, Subhadeep Paul
Abstract: We consider Heterogeneous Transfer Learning (HTL) from a source to a new target domain for high-dimensional regression with differing feature sets. Most homogeneous TL methods assume that target and source domains share the same feature space, which limits their practical applicability. In applications, the target and source features are frequently different due to the inability to measure certain variables in data-poor target environments. Conversely, existing HTL methods do not provide statistical error guarantees, limiting their utility for scientific discovery. Our method first learns a feature map between the missing and observed features, leveraging the vast source data, and then imputes the missing features in the target. Using the combined matched and imputed features, we then perform a two-step transfer learning for penalized regression. We develop upper bounds on estimation and prediction errors, assuming that the source and target parameters differ sparsely but without assuming sparsity in the target model. We obtain results for both when the feature map is linear and when it is nonparametrically specified as unknown functions. Our results elucidate how estimation and prediction errors of HTL depend on the model's complexity, sample size, the quality and differences in feature maps, and differences in the models across domains.
Authors: Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez, Houbing Herbert Song
Abstract: In this paper, we propose an Adaptive Neuro-Symbolic Learning and Reasoning Framework for digital twin technology called "ANSR-DT." Digital twins in industrial environments often struggle with interpretability, real-time adaptation, and human input integration. Our approach addresses these challenges by combining CNN-LSTM dynamic event detection with reinforcement learning and symbolic reasoning to enable adaptive intelligence with interpretable decision processes. This integration enhances environmental understanding while promoting continuous learning, leading to more effective real-time decision-making in human-machine collaborative applications. We evaluated ANSR-DT on synthetic industrial data, observing significant improvements over traditional approaches, with up to 99.5% accuracy for dynamic pattern recognition. The framework demonstrated superior adaptability with extended reinforcement learning training, improving explained variance from 0.447 to 0.547. Future work aims at scaling to larger datasets to test rule management beyond the current 14 rules. Our open-source implementation promotes reproducibility and establishes a foundation for future research in adaptive, interpretable digital twins for industrial applications.
Authors: Honglin Wen, Pierre Pinson
Abstract: Forecast reconciliation is considered an effective method to achieve coherence (within a forecast hierarchy) and to improve forecast quality. However, the value of reconciled forecasts in downstream decision-making tasks has been mostly overlooked. In a multi-agent setup with heterogeneous loss functions, this oversight may lead to unfair outcomes, hence resulting in conflicts during the reconciliation process. To address this, we propose a value-oriented forecast reconciliation approach that focuses on the forecast value for all individual agents. Fairness is ensured through the use of a Nash bargaining framework. Specifically, we model this problem as a cooperative bargaining game, where each agent aims to optimize their own gain while contributing to the overall reconciliation process. We then present a primal-dual algorithm for parameter estimation based on empirical risk minimization. From an application perspective, we consider an aggregated wind energy trading problem, where profits are distributed using a weighted allocation rule. We demonstrate the effectiveness of our approach through several numerical experiments, showing that it consistently results in increased profits for all agents involved.
Authors: Hossein Aghagolzadeh, Mehdi Ezoji
Abstract: Although backpropagation is widely accepted as a training algorithm for artificial neural networks, researchers are always looking for inspiration from the brain to find ways with potentially better performance. Forward-Forward is a novel training algorithm that is more similar to what occurs in the brain, although there is a significant performance gap compared to backpropagation. In the Forward-Forward algorithm, the loss functions are placed after each layer, and the updating of a layer is done using two local forward passes and one local backward pass. Forward-Forward is in its early stages and has been designed and evaluated on simple multi-layer perceptron networks to solve image classification tasks. In this work, we have extended the use of this algorithm to a more complex and modern network, namely the Vision Transformer. Inspired by insights from contrastive learning, we have attempted to revise this algorithm, leading to the introduction of Contrastive Forward-Forward. Experimental results show that our proposed algorithm performs significantly better than the baseline Forward-Forward leading to an increase of up to 10% in accuracy and accelerating the convergence speed by 5 to 20 times. Furthermore, if we take Cross Entropy as the baseline loss function in backpropagation, it will be demonstrated that the proposed modifications to the baseline Forward-Forward reduce its performance gap compared to backpropagation on Vision Transformer, and even outperforms it in certain conditions, such as inaccurate supervision.
Authors: Afsara Benazir, Felix Xiaozhu Lin
Abstract: Robust speech recognition systems rely on cloud service providers for inference. It needs to ensure that an untrustworthy provider cannot deduce the sensitive content in speech. Sanitization can be done on speech content keeping in mind that it has to avoid compromising transcription accuracy. Realizing the under utilized capabilities of tiny speech foundation models (FMs), for the first time, we propose a novel use: enhancing speech privacy on resource-constrained devices. We introduce SpeechShield, an edge/cloud privacy preserving speech inference engine that can filter sensitive entities without compromising transcript accuracy. We utilize a timestamp based on-device masking approach that utilizes a token to entity prediction model to filter sensitive entities. Our choice of mask strategically conceals parts of the input and hides sensitive data. The masked input is sent to a trusted cloud service or to a local hub to generate the masked output. The effectiveness of SpeechShield hinges on how well the entity time segments are masked. Our recovery is a confidence score based approach that chooses the best prediction between cloud and on-device model. We implement SpeechShield on a 64 bit Raspberry Pi 4B. Experiments show that our solution leads to robust speech recognition without forsaking privacy. SpeechShield with < 100 MB memory, achieves state-of-the-art (SOTA) speech transcription performance while filtering about 83% of private entities directly on-device. SpeechShield is 16x smaller in memory, 3.3x faster and 17x more compute efficient than prior privacy preserving speech frameworks and has a relative reduction in word error rate (WER) by 38.8-77.5% when compared to existing offline transcription services.
Authors: Shreya Shukla, Jose Torres, Akshaj Murhekar, Christina Liu, Abhijit Mishra, Jacek Gwizdka, Shounak Roychowdhury
Abstract: Decoding neural activity into human-interpretable representations is a key research direction in brain-computer interfaces (BCIs) and computational neuroscience. Recent progress in machine learning and generative AI has driven growing interest in transforming non-invasive Electroencephalography (EEG) signals into images, text, and audio. This survey consolidates and analyzes developments across EEG-to-image synthesis, EEG-to-text generation, and EEG-to-audio reconstruction. We conducted a structured literature search across major databases (2017-2025), extracting key information on datasets, generative architectures (GANs, VAEs, transformers, diffusion models), EEG feature-encoding techniques, evaluation metrics, and the major challenges shaping current work in this area. Our review finds that EEG-to-image models predominantly employ encoder-decoder architectures built on GANs, VAEs, or diffusion models; EEG-to-text approaches increasingly leverage transformer-based language models for open-vocabulary decoding; and EEG-to-audio methods commonly map EEG signals to mel-spectrograms that are subsequently rendered into audio using neural vocoders. Despite promising advances, the field remains constrained by small and heterogeneous datasets, limited cross-subject generalization, and the absence of standardized benchmarks. By consolidating methodological trends and available datasets, this survey provides a foundational reference for advancing EEG-based generative AI and supporting reproducible research. We further highlight open-source datasets and baseline implementations to facilitate systematic benchmarking and accelerate progress in EEG-driven neural decoding.
Authors: L\'eo Dana (SIERRA), Francis Bach (SIERRA), Loucas Pillaud-Vivien (ENPC, CERMICS)
Abstract: We analyse the convergence of one-hidden-layer ReLU networks trained by gradient flow on $n$ data points. Our main contribution leverages the high dimensionality of the ambient space, which implies low correlation of the input samples, to demonstrate that a network with width of order $\log(n)$ neurons suffices for global convergence with high probability. Our analysis uses a Polyak-{\L}ojasiewicz viewpoint along the gradient-flow trajectory, which provides an exponential rate of convergence of $\frac{1}{n}$. When the data are exactly orthogonal, we give further refined characterizations of the convergence speed, proving its asymptotic behavior lies between the orders $\frac{1}{n}$ and $\frac{1}{\sqrt{n}}$, and exhibiting a phase-transition phenomenon in the convergence rate, during which it evolves from the lower bound to the upper, and in a relative time of order $\frac{1}{\log(n)}$.
Authors: Chengpiao Huang, Yuhang Wu, Kaizheng Wang
Abstract: Large language models (LLMs) are increasingly used to simulate survey responses, but synthetic data can be misaligned with the human population, leading to unreliable inference. We develop a general framework that converts LLM-simulated responses into reliable confidence sets for population parameters of human responses, addressing the distribution shift between the simulated and real populations. The key design choice is the number of simulated responses: too many produce overly narrow sets with poor coverage, while too few yield excessively loose estimates. We propose a data-driven approach that adaptively selects the simulation sample size to achieve nominal average-case coverage, regardless of the LLM's simulation fidelity or the confidence set construction procedure. The selected sample size is further shown to reflect the effective human population size that the LLM can represent, providing a quantitative measure of its simulation fidelity. Experiments on real survey datasets reveal heterogeneous fidelity gaps across different LLMs and domains.
Authors: Yuan Sui, Yufei He, Tri Cao, Simeng Han, Yulin Chen, Bryan Hooi
Abstract: Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they still tend to explore unproductive solution paths without effective backtracking or strategy adjustment. In this paper, we propose Meta-Reasoner, a new framework that empowers LLMs to "think about how to think". It optimizes the inference process by dynamically adapting reasoning strategies in real-time. Our approach employs contextual multi-armed bandits (CMABs) to learn an adaptive policy. It learns to evaluate the current state of LLM's reasoning and determine optimal strategy that is most likely to lead to a successful outcome during inference, like whether to backtrack, switch to a new approach, or restart the problem-solving process. This meta-guidance helps avoid unproductive paths exploration during inference and hence improves computational efficiency. We evaluate Meta-Reasoner on math problems (e.g., Game-of-24, TheoremQA) and scientific tasks (e.g., SciBench). Results show that our method outperform previous SOTA methods by 9-12\% in accuracy, while reducing inference time by 28-35\% under the same compute budget. Additional experiments on creative writing demonstrate the generalizability of our approach to diverse reasoning-intensive tasks.
Authors: Ziqiao Meng, Qichao Wang, Zhiyang Dou, Zixing Song, Zhipeng Zhou, Irwin King, Peilin Zhao
Abstract: Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an artificial ordering on inherently unordered point sets, forcing shape generation to proceed as a sequence of local predictions. This sequential bias emphasizes short-range continuity but undermines the model's capacity to capture long-range dependencies, hindering its ability to enforce global structural properties such as symmetry, consistent topology, and large-scale geometric regularities. Inspired by the level-of-detail (LOD) principle in shape modeling, we propose PointNSP, a coarse-to-fine generative framework that preserves global shape structure at low resolutions and progressively refines fine-grained geometry at higher scales through a next-scale prediction paradigm. This multi-scale factorization aligns the autoregressive objective with the permutation-invariant nature of point sets, enabling rich intra-scale interactions while avoiding brittle fixed orderings. Experiments on ShapeNet show that PointNSP establishes state-of-the-art (SOTA) generation quality for the first time within the autoregressive paradigm. In addition, it surpasses strong diffusion-based baselines in parameter, training, and inference efficiency. Finally, in dense generation with 8,192 points, PointNSP's advantages become even more pronounced, underscoring its scalability potential.
Authors: Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
Abstract: Language Models (LMs) are widely used in software engineering for code generation, but they may produce erroneous code. Rather than repairing outputs, a more thorough remedy is to address underlying model failures. LM repair offers a lightweight solution: it requires minimal data, lowers computational cost, and limits side effects. Unlike full retraining, LM repair focuses on applying tailored updates to targeted neurons, making it suitable for limited resources, high-performance demands, or strict safety requirements. In this paper, we propose Semantic Targeting for Analytical Repair (STAR), a novel semantic-based optimization method for repairing LLMs. STAR realizes the main operations of repairing LMs in an optimization process, including locating ``buggy neurons'', solving ``neuron patches'', and patching ``buggy neurons''. The neuron patches are computed with a solid semantic-based analytical formula, which directly bridges the changes to logits with the deltas of neurons, by steering latent representations. Compared to the prior work of LM repair (MINT) and standard optimization methods (SGD), STAR integrates their strengths while mitigating their limitations. By reformulating LM repair as an optimization process, STAR may solve multiple failures together, significantly improving the usefulness. Evaluated on coding tasks using popular code LMs, STAR demonstrates superior effectiveness compared with the state-of-the-art. Besides, STAR exhibits better efficiency. In terms of side effects, namely the balance between generalization and specificity, STAR outperforms prior work by a significant margin. Additionally, we conducted assessments on the overfitting risk of LM repair as well as the cumulative impact. Further, we analyzed the differences with pipeline-based methods and explained the reason why STAR is better and how it mitigated the common limitations of LM repair.
Authors: Le Qiu, Zelai Xu, Qixin Tan, Wenhao Tang, Chao Yu, Yu Wang
Abstract: Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches often struggle to identify vulnerabilities that are both effective-meaning the autonomous vehicle is genuinely responsible for the accidents-and diverse-meaning they span various failure types. To address these challenges, we propose AED, a framework that uses large language models (LLMs) to automatically discover effective and diverse vulnerabilities in autonomous driving policies. We first utilize an LLM to automatically design reward functions for RL training. Then we let the LLM consider a diverse set of accident types and train adversarial policies for different accident types in parallel. Finally, we use preference-based learning to filter ineffective accidents and enhance the effectiveness of each vulnerability. Experiments across multiple simulated traffic scenarios and tested policies show that AED uncovers a broader range of vulnerabilities and achieves higher attack success rates compared with expert-designed rewards, thereby reducing the need for manual reward engineering and improving the diversity and effectiveness of vulnerability discovery. The implementation can be found on: https://github.com/thu-nics/AED .
Authors: Leonardo Massai, Muhammad Zakwan, Giancarlo Ferrari-Trecate
Abstract: Structured state-space models (SSMs) have recently emerged as a powerful architecture at the intersection of machine learning and control, featuring layers composed of discrete-time linear time-invariant (LTI) systems followed by pointwise nonlinearities. These models combine the expressiveness of deep neural networks with the interpretability and inductive bias of dynamical systems, offering strong performance on long-sequence tasks with favorable computational complexity. However, their adoption in applications such as system identification and optimal control remains limited by the difficulty of enforcing stability and robustness in a principled and tractable manner. We introduce L2RU, a class of SSMs endowed with a prescribed $\mathcal{L}_2$-gain bound, guaranteeing input--output stability and robustness for all parameter values. The L2RU architecture is derived from free parametrizations of LTI systems satisfying an $\mathcal{L}_2$ constraint, enabling unconstrained optimization via standard gradient-based methods while preserving rigorous stability guarantees. Specifically, we develop two complementary parametrizations: a non-conservative formulation that provides a complete characterization of square LTI systems with a given $\mathcal{L}_2$-bound, and a conservative formulation that extends the approach to general (possibly non-square) systems while improving computational efficiency through a structured representation of the system matrices. Both parametrizations admit efficient initialization schemes that facilitate training long-memory models. We demonstrate the effectiveness of the proposed framework on a nonlinear system identification benchmark, where L2RU achieves improved performance and training stability compared to existing SSM architectures, highlighting its potential as a principled and robust building block for learning and control.
Authors: Andrew Rosemberg, Michael Klamkin, Pascal Van Hentenryck
Abstract: The growing scale of power systems and the increasing uncertainty introduced by renewable energy sources necessitates novel optimization techniques that are significantly faster and more accurate than existing methods. The AC Optimal Power Flow (AC-OPF) problem, a core component of power grid optimization, is often approximated using linearized DC Optimal Power Flow (DC-OPF) models for computational tractability, albeit at the cost of suboptimal and inefficient decisions. To address these limitations, we propose a novel deep learning-based framework for network equivalency that enhances DC-OPF to more closely mimic the behavior of AC-OPF. The approach utilizes recent advances in differentiable optimization, incorporating a neural network trained to predict adjusted nodal shunt conductances and branch susceptances in order to account for nonlinear power flow behavior. The model can be trained end-to-end using modern deep learning frameworks by leveraging the implicit function theorem. Results demonstrate the framework's ability to significantly improve prediction accuracy.
Authors: Yu Min Park, Yan Kyaw Tun, Eui-Nam Huh, Walid Saad, Choong Seon Hong
Abstract: Beamforming is a key technology in millimeter-wave (mmWave) communications that improves signal transmission by optimizing directionality and intensity. However, conventional channel estimation methods, such as pilot signals or beam sweeping, often fail to adapt to rapidly changing communication environments. To address this limitation, multimodal sensing-aided beam prediction has gained significant attention, using various sensing data from devices such as LiDAR, radar, GPS, and RGB images to predict user locations or network conditions. Despite its promising potential, the adoption of multimodal sensing-aided beam prediction is hindered by high computational complexity, high costs, and limited datasets. Thus, in this paper, a novel resource-efficient learning framework is introduced for beam prediction, which leverages a custom-designed cross-modal relational knowledge distillation (CRKD) algorithm specifically tailored for beam prediction tasks, to transfer knowledge from a multimodal network to a radar-only student model, achieving high accuracy with reduced computational cost. To enable multimodal learning with realistic data, a novel multimodal simulation framework is developed while integrating sensor data generated from the autonomous driving simulator CARLA with MATLAB-based mmWave channel modeling, and reflecting real-world conditions. The proposed CRKD achieves its objective by distilling relational information across different feature spaces, which enhances beam prediction performance without relying on expensive sensor data. Simulation results demonstrate that CRKD efficiently distills multimodal knowledge, allowing a radar-only model to achieve $94.62%$ of the teacher performance. In particular, this is achieved with just $10%$ of the teacher network's parameters, thereby significantly reducing computational complexity and dependence on multimodal sensor data.
Authors: Sneh Pandya, Yuanyuan Yang, Nicholas Van Alfen, Jonathan Blazek, Robin Walters
Abstract: The intrinsic alignments (IA) of galaxies, a key contaminant in weak lensing analyses, arise from correlations in galaxy shapes driven by tidal interactions and galaxy formation processes. Accurate IA modeling is essential for robust cosmological inference, but current approaches rely on perturbative methods that break down on nonlinear scales or on expensive simulations. We introduce IAEmu, a neural network-based emulator that predicts the galaxy position-position ($\xi$), position-orientation ($\omega$), and orientation-orientation ($\eta$) correlation functions and their uncertainties using mock catalogs based on the halo occupation distribution (HOD) framework. Compared to simulations, IAEmu achieves ~3% average error for $\xi$ and ~5% for $\omega$, while capturing the stochasticity of $\eta$ without overfitting. The emulator provides both aleatoric and epistemic uncertainties, helping identify regions where predictions may be less reliable. We also demonstrate generalization to non-HOD alignment signals by fitting to IllustrisTNG hydrodynamical simulation data. As a fully differentiable neural network, IAEmu enables $\sim$10,000$\times$ speed-ups in mapping HOD parameters to correlation functions on GPUs, compared to CPU-based simulations. This acceleration facilitates inverse modeling via gradient-based sampling, making IAEmu a powerful surrogate model for galaxy bias and IA studies with direct applications to Stage IV weak lensing surveys.
Authors: Suyu Ye, Haojun Shi, Darren Shih, Hyokun Yun, Tanya Roosta, Tianmin Shu
Abstract: To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing web-based agent benchmarks, sequential instruction following in the real world poses significant challenges beyond performing a single, clearly defined task. For instance, real-world human instructions can be ambiguous, require different levels of AI assistance, and may evolve over time, reflecting changes in the user's mental state. To address this gap, we introduce RealWebAssist, a novel benchmark designed to evaluate sequential instruction-following in realistic scenarios involving long-horizon interactions with the web, visual GUI grounding, and understanding ambiguous real-world user instructions. RealWebAssist includes a dataset of sequential instructions collected from real-world human users. Each user instructs a web-based assistant to perform a series of tasks on multiple websites. A successful agent must reason about the true intent behind each instruction, keep track of the mental state of the user, understand user-specific routines, and ground the intended tasks to actions on the correct GUI elements. Our experimental results show that state-of-the-art models struggle to understand and ground user instructions, posing critical challenges in following real-world user instructions for long-horizon web assistance.
Authors: Sahil Sethi, Sai Reddy, Mansi Sakarvadia, Jordan Serotte, Darlington Nwaudo, Nicholas Maassen, Lewis Shi
Abstract: Deep learning has shown strong performance in musculoskeletal imaging, but prior work has largely targeted conditions where diagnosis is relatively straightforward. More challenging problems remain underexplored, such as detecting Bankart lesions (anterior-inferior glenoid labral tears) on standard MRIs. These lesions are difficult to diagnose due to subtle imaging features, often necessitating invasive MRI arthrograms (MRAs). We introduce ScopeMRI, the first publicly available, expert-annotated dataset for shoulder pathologies, and present a deep learning framework for Bankart lesion detection on both standard MRIs and MRAs. ScopeMRI contains shoulder MRIs from patients who underwent arthroscopy, providing ground-truth labels from intraoperative findings, the diagnostic gold standard. Separate models were trained for MRIs and MRAs using CNN- and transformer-based architectures, with predictions ensembled across multiple imaging planes. Our models achieved radiologist-level performance, with accuracy on standard MRIs surpassing radiologists interpreting MRAs. External validation on independent hospital data demonstrated initial generalizability across imaging protocols. By releasing ScopeMRI and a modular codebase for training and evaluation, we aim to accelerate research in musculoskeletal imaging and foster development of datasets and models that address clinically challenging diagnostic tasks.
Authors: Anton Selitskiy, Maitreya Kocharekar
Abstract: In this work, we address the voice conversion (VC) task using a vector-based interface. To align audio embeddings between speakers, we employ discrete optimal transport mapping. Our evaluation results demonstrate the high quality and effectiveness of this method. Additionally, we show that applying discrete optimal transport as a post-processing step in audio generation can lead to the incorrect classification of synthetic audio as real.
Authors: Guy Davidson, Todd M. Gureckis, Brenden M. Lake, Adina Williams
Abstract: Demonstrations and instructions are two primary approaches for prompting language models to perform in-context learning (ICL) tasks. Do identical tasks elicited in different ways result in similar representations of the task? An improved understanding of task representation mechanisms would offer interpretability insights and may aid in steering models. We study this through \textit{function vectors} (FVs), recently proposed as a mechanism to extract few-shot ICL task representations. We generalize FVs to alternative task presentations, focusing on short textual instruction prompts, and successfully extract instruction function vectors that promote zero-shot task accuracy. We find evidence that demonstration- and instruction-based function vectors leverage different model components, and offer several controls to dissociate their contributions to task performance. Our results suggest that different task promptings forms do not induce a common task representation through FVs but elicit different, partly overlapping mechanisms. Our findings offer principled support to the practice of combining instructions and task demonstrations, imply challenges in universally monitoring task inference across presentation forms, and encourage further examinations of LLM task inference mechanisms.
Authors: A. Feder Cooper, Aaron Gokaslan, Ahmed Ahmed, Amy B. Cyphert, Christopher De Sa, Mark A. Lemley, Daniel E. Ho, Percy Liang
Abstract: Plaintiffs and defendants in copyright lawsuits over generative AI often make sweeping, opposing claims about the extent to which large language models (LLMs) have memorized plaintiffs' protected expression in their training data. Drawing on both machine learning and copyright law, we show that these polarized positions dramatically oversimplify the relationship between memorization and copyright. To do so, we extend a recent probabilistic extraction technique to measure memorization of 50 books in 17 open-weight LLMs. Through thousands of experiments, we show that the extent of memorization varies both by model and by book. With respect to our specific extraction methodology, we find that most LLMs do not memorize most books -- either in whole or in part. However, we also find that Llama 3.1 70B entirely memorizes some books, like the first Harry Potter book and 1984. In fact, the first Harry Potter is so memorized that, using a seed prompt consisting of just the first few tokens of the first chapter, we can deterministically generate the entire book near-verbatim. We discuss why our results have significant implications for copyright cases, though not ones that unambiguously favor either side.
Authors: Yuezhou Ma, Haixu Wu, Hang Zhou, Huikun Weng, Jianmin Wang, Mingsheng Long
Abstract: Physics sensing plays a central role in many scientific and engineering domains, which inherently involves two coupled tasks: reconstructing dense physical fields from sparse observations and optimizing scattered sensor placements to observe maximum information. While deep learning has made rapid advances in sparse-data reconstruction, existing methods generally omit optimization of sensor placements, leaving the mutual enhancement between reconstruction and placement on the shelf. To change this suboptimal practice, we propose PhySense, a synergistic two-stage framework that learns to jointly reconstruct physical fields and to optimize sensor placements, both aiming for accurate physics sensing. The first stage involves a flow-based generative model enhanced by cross-attention to adaptively fuse sparse observations. Leveraging the reconstruction feedback, the second stage performs sensor placement via projected gradient descent to satisfy spatial constraints. We further prove that the learning objectives of the two stages are consistent with classical variance-minimization principles, providing theoretical guarantees. Extensive experiments across three challenging benchmarks, especially a 3D geometry dataset, indicate PhySense achieves state-of-the-art physics sensing accuracy and discovers informative sensor placements previously unconsidered. Code is available at this repository: https://github.com/thuml/PhySense.
Authors: Lorenzo Baldassari, Josselin Garnier, Knut Solna, Maarten V. de Hoop
Abstract: Designing algorithms for solving high-dimensional Bayesian inverse problems directly in infinite-dimensional function spaces - where such problems are naturally formulated - is crucial to ensure stability and convergence as the discretization of the underlying problem is refined. In this paper, we contribute to this line of work by analyzing a widely used sampler for linear inverse problems: Langevin dynamics driven by score-based generative models (SGMs) acting as priors, formulated directly in function space. Building on the theoretical framework for SGMs in Hilbert spaces, we give a rigorous definition of this sampler in the infinite-dimensional setting and derive, for the first time, error estimates that explicitly depend on the approximation error of the score. As a consequence, we obtain sufficient conditions for global convergence in Kullback-Leibler divergence on the underlying function space. Preventing numerical instabilities requires preconditioning of the Langevin algorithm and we prove the existence and the form of an optimal preconditioner. The preconditioner depends on both the score error and the forward operator and guarantees a uniform convergence rate across all posterior modes. Our analysis applies to both Gaussian and a general class of non-Gaussian priors. Finally, we present examples that illustrate and validate our theoretical findings.
Authors: Atsushi Suzuki, Jing Wang
Abstract: Will further scaling up of machine learning models continue to bring success? A significant challenge in answering this question lies in understanding generalization gap, which is the impact of overfitting. Understanding generalization gap behavior of increasingly large-scale machine learning models remains a significant area of investigation, as conventional analyses often link error bounds to model complexity, failing to fully explain the success of extremely large architectures. This research introduces a novel perspective by establishing a model-independent upper bound for generalization gap applicable to algorithms whose outputs are determined solely by the data's histogram, such as empirical risk minimization or gradient-based methods. Crucially, this bound is shown to depend only on the R\'enyi entropy of the data-generating distribution, suggesting that a small generalization gap can be maintained even with arbitrarily large models, provided the data quantity is sufficient relative to this entropy. This framework offers a direct explanation for the phenomenon where generalization performance degrades significantly upon injecting random noise into data, where the performance degrade is attributed to the consequent increase in the data distribution's R\'enyi entropy. Furthermore, we adapt the no-free-lunch theorem to be data-distribution-dependent, demonstrating that an amount of data corresponding to the R\'enyi entropy is indeed essential for successful learning, thereby highlighting the tightness of our proposed generalization bound.
Authors: Xiaoqi Liu, Dorian Baudry, Julian Zimmert, Patrick Rebeschini, Arya Akhavan
Abstract: Bandit Convex Optimization is a fundamental class of sequential decision-making problems, where the learner selects actions from a continuous domain and observes a loss (but not its gradient) at only one point per round. We study this problem in non-stationary environments, and aim to minimize the regret under three standard measures of non-stationarity: the number of switches $S$ in the comparator sequence, the total variation $\Delta$ of the loss functions, and the path-length $P$ of the comparator sequence. We propose a polynomial-time algorithm, Tilted Exponentially Weighted Average with Sleeping Experts (TEWA-SE), which adapts the sleeping experts framework from online convex optimization to the bandit setting. For strongly convex losses, we prove that TEWA-SE is minimax-optimal with respect to known $S$ and $\Delta$ by establishing matching upper and lower bounds. By equipping TEWA-SE with the Bandit-over-Bandit framework, we extend our analysis to environments with unknown non-stationarity measures. For general convex losses, we introduce a second algorithm, clipped Exploration by Optimization (cExO), based on exponential weights over a discretized action space. While not polynomial-time computable, this method achieves minimax-optimal regret with respect to known $S$ and $\Delta$, and improves on the best existing bounds with respect to $P$.
Authors: Riley Simmons-Edler, Ryan P. Badman, Felix Baastad Berg, Raymond Chua, John J. Vastola, Joshua Lunger, William Qian, Kanaka Rajan
Abstract: Understanding the behavior of deep reinforcement learning (DRL) agents -particularly as task and agent sophistication increase- requires more than simple comparison of reward curves, yet standard methods for behavioral analysis remain underdeveloped in DRL. We apply tools from neuroscience and ethology to study DRL agents in a novel, complex, partially observable environment, ForageWorld, designed to capture key aspects of real-world animal foraging- including sparse, depleting resource patches, predator threats, and spatially extended arenas. We use this environment as a platform for applying joint behavioral and neural analysis to agents, revealing detailed, quantitatively grounded insights into agent strategies, memory, and planning. Contrary to common assumptions, we find that model-free RNN-based DRL agents can exhibit structured, planning-like behavior purely through emergent dynamics- without requiring explicit memory modules or world models. Our results show that studying DRL agents like animals -analyzing them with neuroethology-inspired tools that reveal structure in both behavior and neural dynamics- uncovers rich structure in their learning dynamics that would otherwise remain invisible. We distill these tools into a general analysis framework linking core behavioral and representational features to diagnostic methods, which can be reused for a wide range of tasks and agents. As agents grow more complex and autonomous, bridging neuroscience, cognitive science, and AI will be essential- not just for understanding their behavior, but for ensuring safe alignment and maximizing desirable behaviors that are hard to measure via reward. We show how this can be done by drawing on lessons from how biological intelligence is studied.
Authors: Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva, Vladimir Arkhipkin, Denis Dimitrov
Abstract: Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to mitigating common artifacts in KL-VAE training without requiring radical architectural changes. We present a detailed taxonomy of five prevalent artifacts - color shift, grid patterns, blur, corner and droplet artifacts - and analyze their root causes. Through straightforward modifications, including adjustments to loss weights, padding strategies, and the integration of Spatially Conditional Normalization, we demonstrate significant improvements in VAE performance. Our method achieves state-of-the-art results in image reconstruction metrics (PSNR and SSIM) across multiple benchmarks and enhances text-to-image generation quality, as evidenced by superior CLIP scores. By preserving the simplicity of the KL-VAE framework while addressing its practical challenges, VIVAT offers actionable insights for researchers and practitioners aiming to optimize VAE training.
Authors: Ben Jacobsen, Kassem Fawaz
Abstract: We study the problem of differentially private continual counting in the unbounded setting where the input size $n$ is not known in advance. Current state-of-the-art algorithms based on optimal instantiations of the matrix mechanism cannot be directly applied here because their privacy guarantees only hold when key parameters are tuned to $n$. Using the common `doubling trick' avoids knowledge of $n$ but leads to suboptimal and non-smooth error. We solve this problem by introducing novel matrix factorizations based on logarithmic perturbations of the function $\frac{1}{\sqrt{1-z}}$ studied in prior works, which may be of independent interest. The resulting algorithm has smooth error, and for any $\alpha > 0$ and $t\leq n$ it is able to privately estimate the sum of the first $t$ data points with $O(\log^{2+2\alpha}(t))$ variance. It requires $O(t)$ space and amortized $O(\log t)$ time per round, compared to $O(\log(n)\log(t))$ variance, $O(n)$ space and $O(n \log n)$ pre-processing time for the nearly-optimal bounded-input algorithm of Henzinger et al. (SODA 2023). Empirically, we find that our algorithm's performance is also comparable to theirs in absolute terms: our variance is less than $1.5\times$ theirs for $t$ as large as $2^{24}$.
Authors: Xiaomeng Xu, Yifan Hou, Zeyi Liu, Shuran Song
Abstract: We address key challenges in Dataset Aggregation (DAgger) for real-world contact-rich manipulation: how to collect informative human correction data and how to effectively update policies with this new data. We introduce Compliant Residual DAgger (CR-DAgger), which contains two novel components: 1) a Compliant Intervention Interface that leverages compliance control, allowing humans to provide gentle, accurate delta action corrections without interrupting the ongoing robot policy execution; and 2) a Compliant Residual Policy formulation that learns from human corrections while incorporating force feedback and force control. Our system significantly enhances performance on precise contact-rich manipulation tasks using minimal correction data, improving base policy success rates by over 50\% on two challenging tasks (book flipping and belt assembly) while outperforming both retraining-from-scratch and finetuning approaches. Through extensive real-world experiments, we provide practical guidance for implementing effective DAgger in real-world robot learning tasks. Result videos are available at: https://compliant-residual-dagger.github.io/
Authors: Pranav Atreya, Karl Pertsch, Tony Lee, Moo Jin Kim, Arhan Jain, Artur Kuramshin, Clemens Eppner, Cyrus Neary, Edward Hu, Fabio Ramos, Jonathan Tremblay, Kanav Arora, Kirsty Ellis, Luca Macesanu, Marcel Torne Villasevil, Matthew Leonard, Meedeum Cho, Ozgur Aslan, Shivin Dass, Jie Wang, William Reger, Xingfang Yuan, Xuning Yang, Abhishek Gupta, Dinesh Jayaraman, Glen Berseth, Kostas Daniilidis, Roberto Martin-Martin, Youngwoon Lee, Percy Liang, Chelsea Finn, Sergey Levine
Abstract: Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standardization, either by specifying fixed evaluation tasks and environments, or by hosting centralized ''robot challenges'', and do not readily scale to evaluating generalist policies across a broad range of tasks and environments. In this work, we propose RoboArena, a new approach for scalable evaluation of generalist robot policies in the real world. Instead of standardizing evaluations around fixed tasks, environments, or locations, we propose to crowd-source evaluations across a distributed network of evaluators. Importantly, evaluators can freely choose the tasks and environments they evaluate on, enabling easy scaling of diversity, but they are required to perform double-blind evaluations over pairs of policies. Then, by aggregating preference feedback from pairwise comparisons across diverse tasks and environments, we can derive a ranking of policies. We instantiate our approach across a network of evaluators at seven academic institutions using the DROID robot platform. Through more than 600 pairwise real-robot evaluation episodes across seven generalist policies, we demonstrate that our crowd-sourced approach can more accurately rank the performance of existing generalist policies than conventional, centralized evaluation approaches, while being more scalable, resilient, and trustworthy. We open our evaluation network to the community and hope that it can enable more accessible comparisons of generalist robot policies.
Authors: Xingting Yao, Qinghao Hu, Fei Zhou, Tielong Liu, Gang Li, Peisong Wang, Jian Cheng
Abstract: Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point where the performance improvements become disproportionate. Based on the insight that different layers demonstrate different importance and extra bits could be wasted and interfering, this paper presents an adaptive bit allocation strategy for direct-trained SNNs, achieving fine-grained layer-wise allocation of memory and computation resources. Thus, SNN's efficiency and accuracy can be improved. Specifically, we parametrize the temporal lengths and the bit widths of weights and spikes, and make them learnable and controllable through gradients. To address the challenges caused by changeable bit widths and temporal lengths, we propose the refined spiking neuron, which can handle different temporal lengths, enable the derivation of gradients for temporal lengths, and suit spike quantization better. In addition, we theoretically formulate the step-size mismatch problem of learnable bit widths, which may incur severe quantization errors to SNN, and accordingly propose the step-size renewal mechanism to alleviate this issue. Experiments on various datasets, including the static CIFAR and ImageNet datasets and the dynamic CIFAR-DVS and DVS-GESTURE datasets, demonstrate that our methods can reduce the overall memory and computation cost while achieving higher accuracy. Particularly, our SEWResNet-34 can achieve a 2.69\% accuracy gain and 4.16$\times$ lower bit budgets over the advanced baseline work on ImageNet. This work is open-sourced at \href{https://github.com/Ikarosy/Towards-Efficient-and-Accurate-Spiking-Neural-Networks-via-Adaptive-Bit-Allocation}{this link}.
Authors: Anantha Narayanan Suresh Babu, Akhil Sadam, Pierre F. J. Lermusiaux
Abstract: Typically, numerical simulations of Earth systems are coarse, and Earth observations are sparse and gappy. We apply four generative diffusion modeling approaches to super-resolution and inference of forced two-dimensional quasi-geostrophic turbulence on the beta-plane from coarse, sparse, and gappy observations. Two guided approaches minimally adapt a pre-trained unconditional model: SDEdit modifies the initial condition, and Diffusion Posterior Sampling (DPS) modifies the reverse diffusion process score. Two conditional approaches, a vanilla variant and classifier-free guidance, require training with paired high-resolution and observation data. We consider multiple test cases spanning: two regimes, eddy and anisotropic-jet turbulence; two Reynolds numbers, 10^3 and 10^4; and two observation types, 4x coarse-resolution fields and coarse, sparse and gappy observations. Our comprehensive skill metrics include norms of the reconstructed vorticity fields, turbulence statistical quantities, and quantifications of the super-resolved probabilistic ensembles and their errors. We also study the sensitivity to tuning parameters such as guidance strength. Results show that the generated super-resolution fields of SDEdit are unphysical, while those of DPS are reasonable but with smoothed fine-scale features; however, neither of these lower-cost models propagates observational information effectively to unobserved regions. The two conditional models require re-training, but reconstruct missing fine-scale features, are cycle-consistent with observations, and predict correct turbulence statistics, including the tails. Further, their mean errors are highly correlated with and predictable from their ensemble standard deviations. Results highlight the tradeoffs between ease of implementation, fidelity (sharpness), and cycle-consistency of the diffusion models, and offer practical guidance for deployment.
Authors: Marc Damie, Florian Hahn, Andreas Peter, Jan Ramon
Abstract: Ishai et al. (FOCS'06) introduced secure shuffling as an efficient building block for private data aggregation. Recently, the field of differential privacy has revived interest in secure shufflers by highlighting the privacy amplification they can provide in various computations. Although several works argue for the utility of secure shufflers, they often treat them as black boxes; overlooking the practical vulnerabilities and performance trade-offs of existing implementations. This leaves a central question open: what makes a good secure shuffler? This survey addresses that question by identifying, categorizing, and comparing 26 secure protocols that realize the necessary shuffling functionality. To enable a meaningful comparison, we adapt and unify existing security definitions into a consistent set of properties. We also present an overview of privacy-preserving technologies that rely on secure shufflers, offer practical guidelines for selecting appropriate protocols, and outline promising directions for future work.
Authors: Clement Ruah, Houssem Sifaou, Osvaldo Simeone, Bashir M. Al-Hashimi
Abstract: Training effective artificial intelligence models for telecommunications is challenging due to the scarcity of deployment-specific data. Real data collection is expensive, and available datasets often fail to capture the unique operational conditions and contextual variability of the network environment. Digital twinning provides a potential solution to this problem, as simulators tailored to the current network deployment can generate site-specific data to augment the available training datasets. However, there is a need to develop solutions to bridge the inherent simulation-to-reality (sim-to-real) gap between synthetic and real-world data. This paper reviews recent advances on two complementary strategies: 1) the calibration of digital twins (DTs) through real-world measurements, and 2) the use of sim-to-real gap-aware training strategies to robustly handle residual discrepancies between digital twin-generated and real data. For the latter, we evaluate two conceptually distinct methods that model the sim-to-real gap either at the level of the environment via Bayesian learning or at the level of the training loss via prediction-powered inference.
Authors: Eunsu Baek, Keondo Park, Jeonggil Ko, Min-hwan Oh, Taesik Gong, Hyung-Sin Kim
Abstract: Current AI advances largely rely on scaling neural models and expanding training datasets to achieve generalization and robustness. Despite notable successes, this paradigm incurs significant environmental, economic, and ethical costs, limiting sustainability and equitable access. Inspired by biological sensory systems, where adaptation occurs dynamically at the input (e.g., adjusting pupil size, refocusing vision)--we advocate for adaptive sensing as a necessary and foundational shift. Adaptive sensing proactively modulates sensor parameters (e.g., exposure, sensitivity, multimodal configurations) at the input level, significantly mitigating covariate shifts and improving efficiency. Empirical evidence from recent studies demonstrates that adaptive sensing enables small models (e.g., EfficientNet-B0) to surpass substantially larger models (e.g., OpenCLIP-H) trained with significantly more data and compute. We (i) outline a roadmap for broadly integrating adaptive sensing into real-world applications spanning humanoid, healthcare, autonomous systems, agriculture, and environmental monitoring, (ii) critically assess technical and ethical integration challenges, and (iii) propose targeted research directions, such as standardized benchmarks, real-time adaptive algorithms, multimodal integration, and privacy-preserving methods. Collectively, these efforts aim to transition the AI community toward sustainable, robust, and equitable artificial intelligence systems.
Authors: Qian Qi
Abstract: We derive a new class of non-linear expectations from first-principles deterministic chaotic dynamics. The homogenization of the system's skew-adjoint microscopic generator is achieved using the spectral theory of transfer operators for uniformly hyperbolic flows. We prove convergence in the viscosity sense to a macroscopic evolution governed by a fully non-linear Hamilton-Jacobi-Bellman (HJB) equation. Our central result establishes that the HJB Hamiltonian possesses a rigid structure: affine in the Hessian but demonstrably non-convex in the gradient. This defines a new $\theta$-expectation and constructively establishes a class of non-convex stochastic control problems fundamentally outside the sub-additive framework of G-expectations.
Authors: Daoze Zhang, Chenghan Fu, Zhanheng Nie, Jianyu Liu, Wanxian Guan, Yuan Gao, Jun Song, Pengjie Wang, Jian Xu, Bo Zheng
Abstract: With the rapid advancement of e-commerce, exploring general representations rather than task-specific ones has attracted increasing research attention. For product understanding, although existing discriminative dual-flow architectures drive progress in this field, they inherently struggle to model the many-to-one alignment between multiple images and texts of products. Therefore, we argue that generative Multimodal Large Language Models (MLLMs) hold significant potential for improving product representation learning. Nevertheless, achieving this goal still remains non-trivial due to several key challenges: the lack of multimodal and aspect-aware modeling modules in typical LLMs; the common presence of background noise in product images; and the absence of a standard benchmark for evaluation. To address these issues, we propose the first generative MLLM-based model named MOON for product representation learning. Our method (1) employs a guided Mixture-of-Experts (MoE) module for targeted modeling of multimodal and aspect-specific product content; (2) effectively detects core semantic regions in product images to mitigate the distraction and interference caused by background noise; and (3) introduces the specialized negative sampling strategy to increase the difficulty and diversity of negative samples. In addition, we release a large-scale multimodal benchmark MBE for various product understanding tasks. Experimentally, our model demonstrates competitive zero-shot performance on both our benchmark and the public dataset, showcasing strong generalization across various downstream tasks, including cross-modal retrieval, product classification, and attribute prediction. Furthermore, the case study and visualization illustrate the effectiveness of MOON for product understanding.
Authors: Karan Shah, Attila Cangi
Abstract: Time-dependent density functional theory (TDDFT) is a widely used method to investigate electron dynamics under external time-dependent perturbations such as laser fields. In this work, we present a machine learning approach to accelerate electron dynamics simulations based on real time TDDFT using autoregressive neural operators as time-propagators for the electron density. By leveraging physics-informed constraints and featurization, and high-resolution training data, our model achieves superior accuracy and computational speed compared to traditional numerical solvers. We demonstrate the effectiveness of our model on a class of one-dimensional diatomic molecules under the influence of a range of laser parameters. This method has potential in enabling on-the-fly modeling of laser-irradiated molecules and materials by utilizing fast machine learning predictions in a large space of varying experimental parameters of the laser.
Authors: Martina Boschi, J\"urgen Lerner, Ernst C. Wit
Abstract: Recent technological advances have made it easier to collect large and complex networks of time-stamped relational events connecting two or more entities. Relational hyper-event models (RHEMs) aim to explain the dynamics of these events by modeling the event rate as a function of statistics based on past history and external information. However, despite the complexity of the data, most current RHEM approaches still rely on a linearity assumption to model this relationship. In this work, we address this limitation by introducing a more flexible model that allows the effects of statistics to vary non-linearly and over time. While time-varying and non-linear effects have been used in relational event modeling, we take this further by modeling joint time-varying and non-linear effects using tensor product smooths. We validate our methodology on both synthetic and empirical data. In particular, we use RHEMs to study how patterns of scientific collaboration and impact evolve over time. Our approach provides deeper insights into the dynamic factors driving relational hyper-events, allowing us to evaluate potential non-monotonic patterns that cannot be identified using linear models.
Authors: Tuomas Kelom\"aki, Abel Lacabanne, Daniel Tubbenhauer, Pedro Vaz, Victor L. Zhang
Abstract: We prove that the detection rate of n-crossing alternating links by many standard link invariants decays exponentially in n, implying that they detect alternating links with probability zero. This phenomenon applies broadly, in particular to the Jones and HOMFLYPT polynomials and integral Khovanov homology. We also use a big-data approach to analyze knots and provide evidence that, for knots as well, these invariants exhibit the same asymptotic failure of detection.
Authors: Aysenur Kulunk, Berk Taskin, M. Furkan Eseoglu, H. Bahadir Sahin
Abstract: In large scale e-commerce marketplaces, duplicate product listings frequently cause consumer confusion and operational inefficiencies, degrading trust on the platform and increasing costs. Traditional keyword-based search methodologies falter in accurately identifying duplicates due to their reliance on exact textual matches, neglecting semantic similarities inherent in product titles. To address these challenges, we introduce a scalable, multimodal product deduplication designed specifically for the e-commerce domain. Our approach employs a domain-specific text model grounded in BERT architecture in conjunction with MaskedAutoEncoders for image representations. Both of these architectures are augmented with dimensionality reduction techniques to produce compact 128-dimensional embeddings without significant information loss. Complementing this, we also developed a novel decider model that leverages both text and image vectors. By integrating these feature extraction mechanisms with Milvus, an optimized vector database, our system can facilitate efficient and high-precision similarity searches across extensive product catalogs exceeding 200 million items with just 100GB of system RAM consumption. Empirical evaluations demonstrate that our matching system achieves a macro-average F1 score of 0.90, outperforming third-party solutions which attain an F1 score of 0.83. Our findings show the potential of combining domain-specific adaptations with state-of-the-art machine learning techniques to mitigate duplicate listings in large-scale e-commerce environments.
Authors: Jiazhao Shi, Yichen Lin, Yiheng Hua, Ziyu Wang, Zijian Zhang, Wenjia Zheng, Yun Song, Kuan Lu, Shoufeng Lu
Abstract: Lane-change maneuvers are a leading cause of highway accidents, underscoring the need for accurate intention prediction to improve the safety and decision-making of autonomous driving systems. While prior studies using machine learning and deep learning methods (e.g., SVM, CNN, LSTM, Transformers) have shown promise, most approaches remain limited by binary classification, lack of scenario diversity, and degraded performance under longer prediction horizons. In this study, we propose a physics-informed AI framework that explicitly integrates vehicle kinematics, interaction feasibility, and traffic-safety metrics (e.g., distance headway, time headway, time-to-collision, closing gap time) into the learning process. lane-change prediction is formulated as a three-class problem that distinguishes left change, right change, and no change, and is evaluated across both straight highway segments (highD) and complex ramp scenarios (exiD). By integrating vehicle kinematics with interaction features, our machine learning models, particularly LightGBM, achieve state-of-the-art accuracy and strong generalization. Results show up to 99.8% accuracy and 93.6% macro F1 on highD, and 96.1% accuracy and 88.7% macro F1 on exiD at a 1-second horizon, outperforming a two-layer stacked LSTM baseline. These findings demonstrate the practical advantages of a physics-informed and feature-rich machine learning framework for real-time lane-change intention prediction in autonomous driving systems.
Authors: Anil Kamber, Rahul Parhi
Abstract: Understanding the geometry of the loss landscape near a minimum is key to explaining the implicit bias of gradient-based methods in non-convex optimization problems such as deep neural network training and deep matrix factorization. A central quantity to characterize this geometry is the maximum eigenvalue of the Hessian of the loss, which measures the sharpness of the landscape. Currently, its precise role has been obfuscated because no exact expressions for this sharpness measure were known in general settings. In this paper, we present the first exact expression for the maximum eigenvalue of the Hessian of the squared-error loss at any minimizer in general overparameterized deep matrix factorization (i.e., deep linear neural network training) problems, resolving an open question posed by Mulayoff & Michaeli (2020). This expression uncovers a fundamental property of the loss landscape of depth-2 matrix factorization problems: a minimum is flat if and only if it is spectral-norm balanced, which implies that flat minima are not necessarily Frobenius-norm balanced. Furthermore, to complement our theory, we empirically investigate an escape phenomenon observed during gradient-based training near a minimum that crucially relies on our exact expression of the sharpness.
Authors: David Romero, Ariana Bermudez, Hao Li, Fabio Pizzati, Ivan Laptev
Abstract: Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, however, current approaches still struggle to generate physically plausible object interactions and lack object-level control mechanisms. To address these limitations, we introduce KineMask, an approach for video generation that enables realistic rigid body control, interactions, and effects. Given a single image and a specified object velocity, our method generates videos with inferred motions and future object interactions. We propose a two-stage training strategy that gradually removes future motion supervision via object masks. Using this strategy we train video diffusion models (VDMs) on synthetic scenes of simple interactions and demonstrate significant improvements of object interactions in real scenes. Furthermore, KineMask integrates low-level motion control with high-level textual conditioning via predicted scene descriptions, leading to support for synthesis of complex dynamical phenomena. Our experiments show that KineMask achieves strong improvements over recent models of comparable size. Ablation studies further highlight the complementary roles of low- and high-level conditioning in VDMs. Our code, model, and data will be made publicly available. Project Page: https://daromog.github.io/KineMask/
Authors: Buyun Liang, Liangzu Peng, Jinqi Luo, Darshan Thaker, Kwan Ho Ryan Chan, Ren\'e Vidal
Abstract: Large Language Models (LLMs) are increasingly deployed in high-risk domains. However, state-of-the-art LLMs often produce hallucinations, raising serious concerns about their reliability. Prior work has explored adversarial attacks for hallucination elicitation in LLMs, but it often produces unrealistic prompts, either by inserting gibberish tokens or by altering the original meaning. As a result, these approaches offer limited insight into how hallucinations may occur in practice. While adversarial attacks in computer vision often involve realistic modifications to input images, the problem of finding realistic adversarial prompts for eliciting LLM hallucinations has remained largely underexplored. To address this gap, we propose Semantically Equivalent and Coherent Attacks (SECA) to elicit hallucinations via realistic modifications to the prompt that preserve its meaning while maintaining semantic coherence. Our contributions are threefold: (i) we formulate finding realistic attacks for hallucination elicitation as a constrained optimization problem over the input prompt space under semantic equivalence and coherence constraints; (ii) we introduce a constraint-preserving zeroth-order method to effectively search for adversarial yet feasible prompts; and (iii) we demonstrate through experiments on open-ended multiple-choice question answering tasks that SECA achieves higher attack success rates while incurring almost no semantic equivalence or semantic coherence errors compared to existing methods. SECA highlights the sensitivity of both open-source and commercial gradient-inaccessible LLMs to realistic and plausible prompt variations. Code is available at https://github.com/Buyun-Liang/SECA.
Authors: Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky, Mohamed Amine Ferrag, Tam\'as Bisztray
Abstract: In this paper, we present the first large-scale study exploring whether JavaScript code generated by Large Language Models (LLMs) can reveal which model produced it, enabling reliable authorship attribution and model fingerprinting. With the rapid rise of AI-generated code, attribution is playing a critical role in detecting vulnerabilities, flagging malicious content, and ensuring accountability. While AI-vs-human detection usually treats AI as a single category we show that individual LLMs leave unique stylistic signatures, even among models belonging to the same family or parameter size. To this end, we introduce LLM-NodeJS, a dataset of 50,000 Node.js back-end programs from 20 large language models. Each has four transformed variants, yielding 250,000 unique JavaScript samples and two additional representations (JSIR and AST) for diverse research applications. Using this dataset, we benchmark traditional machine learning classifiers against fine-tuned Transformer encoders and introduce CodeT5-JSA, a custom architecture derived from the 770M-parameter CodeT5 model with its decoder removed and a modified classification head. It achieves 95.8% accuracy on five-class attribution, 94.6% on ten-class, and 88.5% on twenty-class tasks, surpassing other tested models such as BERT, CodeBERT, and Longformer. We demonstrate that classifiers capture deeper stylistic regularities in program dataflow and structure, rather than relying on surface-level features. As a result, attribution remains effective even after mangling, comment removal, and heavy code transformations. To support open science and reproducibility, we release the LLM-NodeJS dataset, Google Colab training scripts, and all related materials on GitHub: https://github.com/LLM-NodeJS-dataset.
Authors: Ji Cao, Yu Wang, Tongya Zheng, Jie Song, Qinghong Guo, Zujie Ren, Canghong Jin, Gang Chen, Mingli Song
Abstract: Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis. From a behavioral perspective, a trajectory reflects a sequence of route choices within an urban environment. However, most existing TRL methods ignore this underlying decision-making process and instead treat trajectories as static, passive spatiotemporal sequences, thereby limiting the semantic richness of the learned representations. To bridge this gap, we propose CORE, a TRL framework that integrates context-aware route choice semantics into trajectory embeddings. CORE first incorporates a multi-granular Environment Perception Module, which leverages large language models (LLMs) to distill environmental semantics from point of interest (POI) distributions, thereby constructing a context-enriched road network. Building upon this backbone, CORE employs a Route Choice Encoder with a mixture-of-experts (MoE) architecture, which captures route choice patterns by jointly leveraging the context-enriched road network and navigational factors. Finally, a Transformer encoder aggregates the route-choice-aware representations into a global trajectory embedding. Extensive experiments on 4 real-world datasets across 6 downstream tasks demonstrate that CORE consistently outperforms 12 state-of-the-art TRL methods, achieving an average improvement of 9.79% over the best-performing baseline. Our code is available at https://github.com/caoji2001/CORE.
Authors: Antonio Norelli, Michael Bronstein
Abstract: A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conceal a secret manuscript. This uncanny state of affairs is now possible thanks to Large Language Models, and in this paper we present Calgacus, a simple and efficient protocol to achieve it. We show that even modest 8-billion-parameter open-source LLMs are sufficient to obtain high-quality results, and a message as long as this abstract can be encoded and decoded locally on a laptop in seconds. The existence of such a protocol demonstrates a radical decoupling of text from authorial intent, further eroding trust in written communication, already shaken by the rise of LLM chatbots. We illustrate this with a concrete scenario: a company could covertly deploy an unfiltered LLM by encoding its answers within the compliant responses of a safe model. This possibility raises urgent questions for AI safety and challenges our understanding of what it means for a Large Language Model to know something.
Authors: Eddison Pham, Prisha Priyadarshini, Adrian Maliackel, Kanishk Bandi, Cristian Meo, Kevin Zhu
Abstract: Scene-level captioning in instructional videos can enhance learning by requiring an understanding of both visual cues and temporal structure. By aligning visual cues with textual guidance, this understanding supports procedural learning and multimodal reasoning, providing a richer context for skill acquisition. However, captions that fail to capture this structure may lack coherence and quality, which can create confusion and undermine the video's educational intent. To address this gap, we introduce DynaStride, a pipeline to generate coherent, scene-level captions without requiring manual scene segmentation. Using the YouCookII dataset's scene annotations, DynaStride performs adaptive frame sampling and multimodal windowing to capture key transitions within each scene. It then employs a multimodal chain-of-thought process to produce multiple action-object pairs, which are refined and fused using a dynamic stride window selection algorithm that adaptively balances temporal context and redundancy. The final scene-level caption integrates visual semantics and temporal reasoning in a single instructional caption. Empirical evaluations against strong baselines, including VLLaMA3 and GPT-4o, demonstrate consistent gains on both N-gram-based metrics (BLEU, METEOR) and semantic similarity measures (BERTScore, CLIPScore). Qualitative analyses further show that DynaStride produces captions that are more temporally coherent and informative, suggesting a promising direction for improving AI-powered instructional content generation.
Authors: Danyal Maqbool, Changhee Lee, Zachary Huemann, Samuel D. Church, Matthew E. Larson, Scott B. Perlman, Tomas A. Romero, Joshua D. Warner, Meghan Lubner, Xin Tie, Jameson Merkow, Junjie Hu, Steve Y. Cho, Tyler J. Bradshaw
Abstract: Generating automated reports for 3D positron emission tomography (PET) is an important and challenging task in medical imaging. PET plays a vital role in oncology, but automating report generation is difficult due to the complexity of whole-body 3D volumes, the wide range of potential clinical findings, and the limited availability of annotated datasets. To address these challenges, we introduce PETARSeg-11K, the first large-scale, publicly available dataset that provides lesion-level correspondence between 3D PET/CT volumes and free-text radiological findings. It comprises 11,356 lesion descriptions paired with 3D segmentations. Second, we propose PETAR-4B, a 3D vision-language model designed for mask-aware, spatially grounded PET/CT reporting. PETAR-4B jointly encodes PET, CT, and 3D lesion segmentation masks, using a 3D focal prompt to capture fine-grained details of lesions that normally comprise less than 0.1% of the volume. Evaluations using automated metrics show PETAR-4B substantially outperforming all 2D and 3D baselines. A human study involving five physicians -- the first of its kind for automated PET reporting -- confirms the model's clinical utility and establishes correlations between automated metrics and expert judgment. This work provides a foundational dataset and a novel architecture, advancing 3D medical vision-language understanding in PET.
Authors: Ritik Raj, Hong Wang, Tushar Krishna
Abstract: Agentic AI frameworks add a decision-making orchestrator embedded with external tools, including web search, Python interpreter, contextual database, and others, on top of monolithic LLMs, turning them from passive text oracles into autonomous problem-solvers that can plan, call tools, remember past steps, and adapt on the fly. This paper aims to characterize and understand the system bottlenecks introduced by agentic AI workloads from a largely overlooked CPU-centric perspective. We first systematically characterize Agentic AI on the basis of orchestrator/decision making component, inference path dynamics and repetitiveness of the agentic flow which directly influences the system-level performance. Thereafter, based on the characterization, we choose five representative agentic AI workloads- Haystack RAG, Toolformer, ChemCrow, Langchain and SWE-Agent to profile latency, throughput and energy metrics and demystify the significant impact of CPUs on these metrics relative to GPUs. We observe that - 1. Tool processing on CPUs can take up to 90.6% of the total latency; 2. Agentic throughput gets bottlenecked either by CPU factors - coherence, synchronization and over-subscription of cores or GPU factors - main memory capacity and bandwidth; \circled{3} CPU dynamic energy consumes up to 44% of the total dynamic energy at large batch sizes. Based on the profiling insights, we present two key optimizations- 1. CPU and GPU-Aware Micro-batching (CGAM) and 2. Mixed Agentic Workload Scheduling (MAWS) for homogeneous and heterogeneous agentic workloads respectively to demonstrate the potential to improve the performance, efficiency, and scalability of agentic AI. We achieve up to 2.1x and 1.41x P50 latency speedup compared to the multi-processing benchmark for homogeneous and heterogeneous agentic workloads respectively.
Authors: Jicong Fan
Abstract: Missing data is a fundamental challenge in data science, significantly hindering analysis and decision-making across a wide range of disciplines, including healthcare, bioinformatics, social science, e-commerce, and industrial monitoring. Despite decades of research and numerous imputation methods, the literature remains fragmented across fields, creating a critical need for a comprehensive synthesis that connects statistical foundations with modern machine learning advances. This work systematically reviews core concepts-including missingness mechanisms, single versus multiple imputation, and different imputation goals-and examines problem characteristics across various domains. It provides a thorough categorization of imputation methods, spanning classical techniques (e.g., regression, the EM algorithm) to modern approaches like low-rank and high-rank matrix completion, deep learning models (autoencoders, GANs, diffusion models, graph neural networks), and large language models. Special attention is given to methods for complex data types, such as tensors, time series, streaming data, graph-structured data, categorical data, and multimodal data. Beyond methodology, we investigate the crucial integration of imputation with downstream tasks like classification, clustering, and anomaly detection, examining both sequential pipelines and joint optimization frameworks. The review also assesses theoretical guarantees, benchmarking resources, and evaluation metrics. Finally, we identify critical challenges and future directions, emphasizing model selection and hyperparameter optimization, the growing importance of privacy-preserving imputation via federated learning, and the pursuit of generalizable models that can adapt across domains and data types, thereby outlining a roadmap for future research.
Authors: Hongyin Zhang, Shuo Zhang, Junxi Jin, Qixin Zeng, Runze Li, Donglin Wang
Abstract: Vision-Language-Action (VLA) models have recently emerged as powerful general-purpose policies for robotic manipulation, benefiting from large-scale multi-modal pre-training. However, they often fail to generalize reliably in out-of-distribution deployments, where unavoidable disturbances such as observation noise, sensor errors, or actuation perturbations become prevalent. While recent Reinforcement Learning (RL)-based post-training provides a practical means to adapt pre-trained VLA models, existing methods mainly emphasize reward maximization and overlook robustness to environmental uncertainty. In this work, we introduce RobustVLA, a lightweight online RL post-training method designed to explicitly enhance the resilience of VLA models. Through a systematic robustness analysis, we identify two key regularizations: Jacobian regularization, which mitigates sensitivity to observation noise, and smoothness regularization, which stabilizes policies under action perturbations. Extensive experiments across diverse robotic environments demonstrate that RobustVLA significantly outperforms prior state-of-the-art methods in robustness and reliability. Our results highlight the importance of principled robustness-aware RL post-training as a key step toward improving the reliability and robustness of VLA models.
Authors: Brennen A. Hill
Abstract: Traditional neural networks, while powerful, rely on biologically implausible learning mechanisms such as global backpropagation. This paper introduces the Structurally Adaptive Predictive Inference Network (SAPIN), a novel computational model inspired by the principles of active inference and the morphological plasticity observed in biological neural cultures. SAPIN operates on a 2D grid where processing units, or cells, learn by minimizing local prediction errors. The model features two primary, concurrent learning mechanisms: a local, Hebbian-like synaptic plasticity rule based on the temporal difference between a cell's actual activation and its learned expectation, and a structural plasticity mechanism where cells physically migrate across the grid to optimize their information-receptive fields. This dual approach allows the network to learn both how to process information (synaptic weights) and also where to position its computational resources (network topology). We validated the SAPIN model on the classic Cart Pole reinforcement learning benchmark. Our results demonstrate that the architecture can successfully solve the CartPole task, achieving robust performance. The network's intrinsic drive to minimize prediction error and maintain homeostasis was sufficient to discover a stable balancing policy. We also found that while continual learning led to instability, locking the network's parameters after achieving success resulted in a stable policy. When evaluated for 100 episodes post-locking (repeated over 100 successful agents), the locked networks maintained an average 82% success rate.
Authors: Jian Zhu, Xin Zou, Jun Sun, Cheng Luo, Lei Liu, Lingfang Zeng, Ning Zhang, Bian Wu, Chang Tang, Lirong Dai
Abstract: In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL.
Authors: Zhangsong Li
Abstract: We study the computational task of detecting and estimating correlated signals in a pair of spiked matrices $$ X=\tfrac{\lambda}{\sqrt{n}} xu^{\top}+W, \quad Y=\tfrac{\mu}{\sqrt{n}} yv^{\top}+Z $$ where the spikes $x,y$ have correlation $\rho$. Specifically, we consider two fundamental models: (1) Correlated spiked Wigner model with signal-to-noise ratio $\lambda,\mu$; (2) Correlated spiked $n*N$ Wishart (covariance) model with signal-to-noise ratio $\sqrt\lambda,\sqrt\mu$. We propose an efficient detection and estimation algorithm based on counting a specific family of edge-decorated cycles. The algorithm's performance is governed by the function $$ F(\lambda,\mu,\rho,\gamma)=\max\Big\{ \frac{ \lambda^2 }{ \gamma }, \frac{ \mu^2 }{ \gamma }, \frac{ \lambda^2 \rho^2 }{ \gamma-\lambda^2+\lambda^2 \rho^2 } + \frac{ \mu^2 \rho^2 }{ \gamma-\mu^2+\mu^2 \rho^2 } \Big\} \,. $$ We prove our algorithm succeeds for the correlated spiked Wigner model whenever $F(\lambda,\mu,\rho,1)>1$, and succeeds for the correlated spiked Wishart model whenever $F(\lambda,\mu,\rho,\tfrac{n}{N})>1$. Our result shows that an algorithm can leverage the correlation between the spikes to detect and estimate the signals even in regimes where efficiently recovering either $x$ from ${X}$ alone or $y$ from ${Y}$ alone is believed to be computationally infeasible. We complement our algorithmic results with evidence for a matching computational lower bound. In particular, we prove that when $F(\lambda,\mu,\rho,1)<1$ for the correlated spiked Wigner model and when $F(\lambda,\mu,\rho,\tfrac{n}{N})<1$ for the spiked Wishart model, all algorithms based on low-degree polynomials fails to distinguish $({X},{Y})$ with two independent noise matrices. This strongly suggests that $F=1$ is the precise computation threshold for our models.
Authors: Zhen Wang, Yufan Zhou, Zhongyan Luo, Lyumanshan Ye, Adam Wood, Man Yao, Saab Mansour, Luoshang Pan
Abstract: Simulating human profiles by instilling personas into large language models (LLMs) is rapidly transforming research in agentic behavioral simulation, LLM personalization, and human-AI alignment. However, most existing synthetic personas remain shallow and simplistic, capturing minimal attributes and failing to reflect the rich complexity and diversity of real human identities. We introduce DEEPPERSONA, a scalable generative engine for synthesizing narrative-complete synthetic personas through a two-stage, taxonomy-guided method. First, we algorithmically construct the largest-ever human-attribute taxonomy, comprising over hundreds of hierarchically organized attributes, by mining thousands of real user-ChatGPT conversations. Second, we progressively sample attributes from this taxonomy, conditionally generating coherent and realistic personas that average hundreds of structured attributes and roughly 1 MB of narrative text, two orders of magnitude deeper than prior works. Intrinsic evaluations confirm significant improvements in attribute diversity (32 percent higher coverage) and profile uniqueness (44 percent greater) compared to state-of-the-art baselines. Extrinsically, our personas enhance GPT-4.1-mini's personalized question answering accuracy by 11.6 percent on average across ten metrics and substantially narrow (by 31.7 percent) the gap between simulated LLM citizens and authentic human responses in social surveys. Our generated national citizens reduced the performance gap on the Big Five personality test by 17 percent relative to LLM-simulated citizens. DEEPPERSONA thus provides a rigorous, scalable, and privacy-free platform for high-fidelity human simulation and personalized AI research.
Authors: Johannes Kiechle, Stefan M. Fischer, Daniel M. Lang, Cosmin I. Bercea, Matthew J. Nyflot, Lina Felsner, Julia A. Schnabel, Jan C. Peeken
Abstract: The sharp rise in medical tomography examinations has created a demand for automated systems that can reliably extract informative features for downstream tasks such as tumor characterization. Although 3D volumes contain richer information than individual slices, effective 3D classification remains difficult: volumetric data encode complex spatial dependencies, and the scarcity of large-scale 3D datasets has constrained progress toward 3D foundation models. As a result, many recent approaches rely on 2D vision foundation models trained on natural images, repurposing them as feature extractors for medical scans with surprisingly strong performance. Despite their practical success, current methods that apply 2D foundation models to 3D scans via slice-based decomposition remain fundamentally limited. Standard slicing along axial, sagittal, and coronal planes often fails to capture the true spatial extent of a structure when its orientation does not align with these canonical views. More critically, most approaches aggregate slice features independently, ignoring the underlying 3D geometry and losing spatial coherence across slices. To overcome these limitations, we propose TomoGraphView, a novel framework that integrates omnidirectional volume slicing with spherical graph-based feature aggregation. Instead of restricting the model to axial, sagittal, or coronal planes, our method samples both canonical and non-canonical cross-sections generated from uniformly distributed points on a sphere enclosing the volume. We publicly share our accessible code base at http://github.com/compai-lab/2025-MedIA-kiechle and provide a user-friendly library for omnidirectional volume slicing at https://pypi.org/project/OmniSlicer.
URLs: http://github.com/compai-lab/2025-MedIA-kiechle, https://pypi.org/project/OmniSlicer.
Authors: Peter Halmos, Boris Hanin
Abstract: Wasserstein gradient flow provides a general framework for minimizing an energy functional $J$ over the space of probability measures on a Riemannian manifold $(M,g)$. Its canonical time-discretization, the Jordan-Kinderlehrer-Otto (JKO) scheme, produces for any step size $\eta>0$ a sequence of probability distributions $\rho_k^\eta$ that approximate to first order in $\eta$ Wasserstein gradient flow on $J$. But the JKO scheme also has many other remarkable properties not shared by other first order integrators, e.g. it preserves energy dissipation and exhibits unconditional stability for $\lambda$-geodesically convex functionals $J$. To better understand the JKO scheme we characterize its implicit bias at second order in $\eta$. We show that $\rho_k^\eta$ are approximated to order $\eta^2$ by Wasserstein gradient flow on a modified energy \[ J^{\eta}(\rho) = J(\rho) - \frac{\eta}{4}\int_M \Big\lVert \nabla_g \frac{\delta J}{\delta \rho} (\rho) \Big\rVert_{2}^{2} \,\rho(dx), \] obtained by subtracting from $J$ the squared metric curvature of $J$ times $\eta/4$. The JKO scheme therefore adds at second order in $\eta$ a deceleration in directions where the metric curvature of $J$ is rapidly changing. This corresponds to canonical implicit biases for common functionals: for entropy the implicit bias is the Fisher information, for KL-divergence it is the Fisher-Hyv{\"a}rinen divergence, and for Riemannian gradient descent it is the kinetic energy in the metric $g$. To understand the differences between minimizing $J$ and $J^\eta$ we study JKO-Flow, Wasserstein gradient flow on $J^\eta$, in several simple numerical examples. These include exactly solvable Langevin dynamics on the Bures-Wasserstein space and Langevin sampling from a quartic potential in 1D.
Authors: Yusuf \c{C}elebi, \"Ozay Ezerceli, Mahmoud El Hussieni
Abstract: This study presents PARROT (Persuasion and Agreement Robustness Rating of Output Truth), a robustness focused framework designed to measure the degradation in accuracy that occurs under social pressure exerted on users through authority and persuasion in large language models (LLMs) the phenomenon of sycophancy (excessive conformity). PARROT (i) isolates causal effects by comparing the neutral version of the same question with an authoritatively false version using a double-blind evaluation, (ii) quantifies confidence shifts toward the correct and imposed false responses using log-likelihood-based calibration tracking, and (iii) systematically classifies failure modes (e.g., robust correct, sycophantic agreement, reinforced error, stubborn error, self-correction, etc.) using an eight-state behavioral taxonomy. We evaluated 22 models using 1,302 MMLU-style multiple-choice questions across 13 domains and domain-specific authority templates. Findings show marked heterogeneity: advanced models (e.g., GPT-5, GPT-4.1, Claude Sonnet 4.5) exhibit low "follow rates" ($\leq 11\%$, GPT-5: 4\%) and minimal accuracy loss, while older/smaller models show severe epistemic collapse (GPT-4: 80\%, Qwen 2.5-1.5B: 94\%). The danger is not limited to response changes; weak models reduce confidence in the correct response while increasing confidence in the imposed incorrect response. While international law and global knowledge at the domain level exhibit high fragility, elementary mathematics is relatively resilient. Consequently, we argue that the goal of "resistance to overfitting pressure" should be addressed as a primary objective alongside accuracy, harm avoidance, and privacy for safe deployment in the real world.
Authors: Yiming Qin, Bomin Wei, Jiaxin Ge, Konstantinos Kallidromitis, Stephanie Fu, Trevor Darrell, XuDong Wang
Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that current VLMs have limited mechanisms to capture dense visual information across spatial dimensions. We introduce Chain-of-Visual-Thought (COVT), a framework that enables VLMs to reason not only in words but also through continuous visual tokens-compact latent representations that encode rich perceptual cues. Within a small budget of roughly 20 tokens, COVT distills knowledge from lightweight vision experts, capturing complementary properties such as 2D appearance, 3D geometry, spatial layout, and edge structure. During training, the VLM with COVT autoregressively predicts these visual tokens to reconstruct dense supervision signals (e.g., depth, segmentation, edges, and DINO features). At inference, the model reasons directly in the continuous visual token space, preserving efficiency while optionally decoding dense predictions for interpretability. Evaluated across more than ten diverse perception benchmarks, including CV-Bench, MMVP, RealWorldQA, MMStar, WorldMedQA, and HRBench, integrating COVT into strong VLMs such as Qwen2.5-VL and LLaVA consistently improves performance by 3% to 16% and demonstrates that compact continuous visual thinking enables more precise, grounded, and interpretable multimodal intelligence.
Authors: Mousam Sinha, Tirtha Sarathi Ghosh, Ridam Pal
Abstract: Feature selection has remained a daunting challenge in machine learning and artificial intelligence, where increasingly complex, high-dimensional datasets demand principled strategies for isolating the most informative predictors. Despite widespread adoption, many established techniques suffer from notable limitations; some incur substantial computational cost, while others offer no definite statistical driven stopping criteria or assesses the significance of their importance scores. A common heuristic approach introduces multiple random noise features and retains all predictors ranked above the strongest noise feature. Although intuitive, this strategy lacks theoretical justification and depends heavily on heuristics. This paper proposes a novel feature selection method that addresses these limitations. Our approach introduces multiple random noise features and evaluates each feature's importance against the maximum importance value among these noise features incorporating a non-parametric bootstrap-based hypothesis testing framework to establish a solid theoretical foundation. We establish the conceptual soundness of our approach through statistical derivations that articulate the principles guiding the design of our algorithm. To evaluate its reliability, we generated simulated datasets under controlled statistical settings and benchmarked performance against Boruta and Knockoff-based methods, observing consistently stronger recovery of meaningful signal. As a demonstration of practical utility, we applied the technique across diverse real-world datasets, where it surpassed feature selection techniques including Boruta, RFE, and Extra Trees. Hence, the method emerges as a robust algorithm for principled feature selection, enabling the distillation of informative predictors that support reliable inference, enhanced predictive performance, and efficient computation.
Authors: Soumojit Das, Nairanjana Dasgupta, Prashanta Dutta
Abstract: Modern artificial intelligence systems make critical decisions yet often fail silently when uncertain -- even well-calibrated models provide no mechanism to identify \textit{which specific predictions} are unreliable. We develop a geometric framework addressing both calibration and instance-level uncertainty quantification for neural network probability outputs. Treating probability vectors as points on the $(c-1)$-dimensional probability simplex equipped with the Fisher--Rao metric, we construct: (i) Additive Log-Ratio (ALR) calibration maps that reduce exactly to Platt scaling for binary problems while extending naturally to multi-class settings, and (ii) geometric reliability scores that translate calibrated probabilities into actionable uncertainty measures, enabling principled deferral of ambiguous predictions to human review. Theoretical contributions include: consistency of the calibration estimator at rate $O_p(n^{-1/2})$ via M-estimation theory (Theorem~1), and tight concentration bounds for reliability scores with explicit sub-Gaussian parameters enabling sample size calculations for validation set design (Theorem~2). We conjecture Neyman--Pearson optimality of our neutral zone construction based on connections to Bhattacharyya coefficients. Empirical validation on Adeno-Associated Virus classification demonstrates that the two-stage framework captures 72.5\% of errors while deferring 34.5\% of samples, reducing automated decision error rates from 16.8\% to 6.9\%. Notably, calibration alone yields marginal accuracy gains; the operational benefit arises primarily from the reliability scoring mechanism, which applies to any well-calibrated probability output. This work bridges information geometry and statistical learning, offering formal guarantees for uncertainty-aware classification in applications requiring rigorous validation.
Authors: Jerry Lin, Zeyuan Hu, Tom Beucler, Katherine Frields, Hannah Christensen, Walter Hannah, Helge Heuer, Peter Ukkonnen, Laura A. Mansfield, Tian Zheng, Liran Peng, Ritwik Gupta, Pierre Gentine, Yusef Al-Naher, Mingjiang Duan, Kyo Hattori, Weiliang Ji, Chunhan Li, Kippei Matsuda, Naoki Murakami, Shlomo Ron, Marec Serlin, Hongjian Song, Yuma Tanabe, Daisuke Yamamoto, Jianyao Zhou, Mike Pritchard
Abstract: Subgrid machine-learning (ML) parameterizations have the potential to introduce a new generation of climate models that incorporate the effects of higher-resolution physics without incurring the prohibitive computational cost associated with more explicit physics-based simulations. However, important issues, ranging from online instability to inconsistent online performance, have limited their operational use for long-term climate projections. To more rapidly drive progress in solving these issues, domain scientists and machine learning researchers opened up the offline aspect of this problem to the broader machine learning and data science community with the release of ClimSim, a NeurIPS Datasets and Benchmarks publication, and an associated Kaggle competition. This paper reports on the downstream results of the Kaggle competition by coupling emulators inspired by the winning teams' architectures to an interactive climate model (including full cloud microphysics, a regime historically prone to online instability) and systematically evaluating their online performance. Our results demonstrate that online stability in the low-resolution, real-geography setting is reproducible across multiple diverse architectures, which we consider a key milestone. All tested architectures exhibit strikingly similar offline and online biases, though their responses to architecture-agnostic design choices (e.g., expanding the list of input variables) can differ significantly. Multiple Kaggle-inspired architectures achieve state-of-the-art (SOTA) results on certain metrics such as zonal mean bias patterns and global RMSE, indicating that crowdsourcing the essence of the offline problem is one path to improving online performance in hybrid physics-AI climate simulation.
Authors: Sonia Laguna, Andrea Agostini, Alain Ryser, Samuel Ruiperez-Campillo, Irene Cannistraci, Moritz Vandenhirtz, Stephan Mandt, Nicolas Deperrois, Farhad Nooralahzadeh, Michael Krauthammer, Thomas M. Sutter, Julia E. Vogt
Abstract: Building robust medical machine learning systems requires pretraining strategies that exploit the intrinsic structure present in clinical data. We introduce Multiview Masked Autoencoder (MVMAE), a self-supervised framework that leverages the natural multi-view organization of radiology studies to learn view-invariant and disease-relevant representations. MVMAE combines masked image reconstruction with cross-view alignment, transforming clinical redundancy across projections into a powerful self-supervisory signal. We further extend this approach with MVMAE-V2T, which incorporates radiology reports as an auxiliary text-based learning signal to enhance semantic grounding while preserving fully vision-based inference. Evaluated on a downstream disease classification task on three large-scale public datasets, MIMIC-CXR, CheXpert, and PadChest, MVMAE consistently outperforms supervised and vision-language baselines. Furthermore, MVMAE-V2T provides additional gains, particularly in low-label regimes where structured textual supervision is most beneficial. Together, these results establish the importance of structural and textual supervision as complementary paths toward scalable, clinically grounded medical foundation models.
Authors: Valeria D\'iaz Moreno, Ryan P Khalili, Daniel Schug, Patrick J. Walsh, Justyna P. Zwolak
Abstract: Semiconductor quantum dots (QDs) are a leading platform for scalable quantum processors. However, scaling to large arrays requires reliable, automated tuning strategies for devices' bootstrapping, calibration, and operation, with many tuning aspects depending on accurately identifying QD device states from charge-stability diagrams (CSDs). In this work, we present a comprehensive benchmarking study of four modern machine learning (ML) architectures for multi-class state recognition in double-QD CSDs. We evaluate their performance across different data budgets and normalization schemes using both synthetic and experimental data. We find that the more resource-intensive models -- U-Nets and visual transformers (ViTs) -- achieve the highest MSE score (defined as $1-\mathrm{MSE}$) on synthetic data (over $0.98$) but fail to generalize to experimental data. MDNs are the most computationally efficient and exhibit highly stable training, but with substantially lower peak performance. CNNs offer the most favorable trade-off on experimental CSDs, achieving strong accuracy with two orders of magnitude fewer parameters than the U-Nets and ViTs. Normalization plays a nontrivial role: min-max scaling generally yields higher MSE scores but less stable convergence, whereas z-score normalization produces more predictable training dynamics but at reduced accuracy for most models. Overall, our study shows that CNNs with min-max normalization are a practical approach for QD CSDs.