Authors: Peter Hedstr\"om, Victor Lamelas Cubero, J\'on Sigurdsson, Viktor \"Osterberg, Satish Kolli, Joakim Odqvist, Ziyong Hou, Wangzhong Mu, Viswanadh Gowtham Arigela
Abstract: Machine learning (ML) has emerged as a powerful tool for accelerating the computational design and production of materials. In materials science, ML has primarily supported large-scale discovery of novel compounds using first-principles data and digital twin applications for optimizing manufacturing processes. However, applying general-purpose ML frameworks to complex industrial materials such as steel remains a challenge. A key obstacle is accurately capturing the intricate relationship between chemical composition, processing parameters, and the resulting microstructure and properties. To address this, we introduce a computational framework that combines physical insights with ML to develop a physics-informed continuous cooling transformation (CCT) model for steels. Our model, trained on a dataset of 4,100 diagrams, is validated against literature and experimental data. It demonstrates high computational efficiency, generating complete CCT diagrams with 100 cooling curves in under 5 seconds. It also shows strong generalizability across alloy steels, achieving phase classification F1 scores above 88% for all phases. For phase transition temperature regression, it attains mean absolute errors (MAE) below 20 {\deg}C across all phases except bainite, which shows a slightly higher MAE of 27 {\deg}C. This framework can be extended with additional generic and customized ML models to establish a universal digital twin platform for heat treatment. Integration with complementary simulation tools and targeted experiments will further support accelerated materials design workflows.
Authors: Andrew S. Cassidy, Guillaume Garreau, Jay Sivagnaname, Mike Grassi, Bernard Brezzo, John V. Arthur, Dharmendra S. Modha
Abstract: We show for invertible problems that transform data from a source domain (for example, Logic Condition Tables (LCTs)) to a destination domain (for example, Hardware Description Language (HDL) code), an approach of using Large Language Models (LLMs) as a lossless encoder from source to destination followed by as a lossless decoder back to the source, comparable to lossless compression in information theory, can mitigate most of the LLM drawbacks of hallucinations and omissions. Specifically, using LCTs as inputs, we generate the full HDL for a two-dimensional network-on-chip router (13 units, 1500-2000 lines of code) using seven different LLMs, reconstruct the LCTs from the auto-generated HDL, and compare the original and reconstructed LCTs. This approach yields significant productivity improvements, not only confirming correctly generated LLM logic and detecting incorrectly generated LLM logic but also assisting developers in finding design specification errors.
Authors: Ciro Benito Raggio, Lucia Migliorelli, Nils Skupien, Mathias Krohmer Zabaleta, Oliver Blanck, Francesco Cicone, Giuseppe Lucio Cascini, Paolo Zaffino, Maria Francesca Spadea
Abstract: Federated Learning (FL) holds the potential to advance equality in health by enabling diverse institutions to collaboratively train deep learning (DL) models, even with limited data. However, the significant resource requirements of FL often exclude centres with limited computational infrastructure, further widening existing healthcare disparities. To address this issue, we propose a Green AI-oriented adaptive layer-freezing strategy designed to reduce energy consumption and computational load while maintaining model performance. We tested our approach using different federated architectures for Magnetic Resonance Imaging (MRI)-to-Computed Tomography (CT) conversion. The proposed adaptive strategy optimises the federated training by selectively freezing the encoder weights based on the monitored relative difference of the encoder weights from round to round. A patience-based mechanism ensures that freezing only occurs when updates remain consistently minimal. The energy consumption and CO2eq emissions of the federation were tracked using the CodeCarbon library. Compared to equivalent non-frozen counterparts, our approach reduced training time, total energy consumption and CO2eq emissions by up to 23%. At the same time, the MRI-to-CT conversion performance was maintained, with only small variations in the Mean Absolute Error (MAE). Notably, for three out of the five evaluated architectures, no statistically significant differences were observed, while two architectures exhibited statistically significant improvements. Our work aligns with a research paradigm that promotes DL-based frameworks meeting clinical requirements while ensuring climatic, social, and economic sustainability. It lays the groundwork for novel FL evaluation frameworks, advancing privacy, equity and, more broadly, justice in AI-driven healthcare.
Authors: Xiaowu Sun, Thabo Mahendiran, Ortal Senouf, Denise Auberson, Bernard De Bruyne, Stephane Fournier, Olivier Muller, Pascal Frossard, Emmanuel Abbe, Dorina Thanou
Abstract: Cardiovascular disease is the leading global cause of mortality, with coronary artery disease (CAD) as its most prevalent form, necessitating early risk prediction. While 3D coronary artery digital twins reconstructed from imaging offer detailed anatomy for personalized assessment, their analysis relies on computationally intensive computational fluid dynamics (CFD), limiting scalability. Data-driven approaches are hindered by scarce labeled data and lack of physiological priors. To address this, we present PINS-CAD, a physics-informed self-supervised learning framework. It pre-trains graph neural networks on 200,000 synthetic coronary digital twins to predict pressure and flow, guided by 1D Navier-Stokes equations and pressure-drop laws, eliminating the need for CFD or labeled data. When fine-tuned on clinical data from 635 patients in the multicenter FAME2 study, PINS-CAD predicts future cardiovascular events with an AUC of 0.73, outperforming clinical risk scores and data-driven baselines. This demonstrates that physics-informed pretraining boosts sample efficiency and yields physiologically meaningful representations. Furthermore, PINS-CAD generates spatially resolved pressure and fractional flow reserve curves, providing interpretable biomarkers. By embedding physical priors into geometric deep learning, PINS-CAD transforms routine angiography into a simulation-free, physiology-aware framework for scalable, preventive cardiology.
Authors: Zhidong Gao, Zimeng Pan, Yuhang Yao, Chenyue Xie, Wei Wei
Abstract: Diffusion models like Stable Diffusion (SD) drive a vibrant open-source ecosystem including fully fine-tuned checkpoints and parameter-efficient adapters such as LoRA, LyCORIS, and ControlNet. However, these adaptation components are tightly coupled to a specific base model, making them difficult to reuse when the base model is upgraded (e.g., from SD 1.x to 2.x) due to substantial changes in model parameters and architecture. In this work, we propose Delta Sampling (DS), a novel method that enables knowledge transfer across base models with different architectures, without requiring access to the original training data. DS operates entirely at inference time by leveraging the delta: the difference in model predictions before and after the adaptation of a base model. This delta is then used to guide the denoising process of a new base model. We evaluate DS across various SD versions, demonstrating that DS achieves consistent improvements in creating desired effects (e.g., visual styles, semantic concepts, and structures) under different sampling strategies. These results highlight DS as an effective, plug-and-play mechanism for knowledge transfer in diffusion-based image synthesis. Code:~ https://github.com/Zhidong-Gao/DeltaSampling
Authors: Duy-Tung Pham, An The Nguyen, Viet-Hoang Tran, Nhan-Phu Chung, Xin T. Tong, Tan M. Nguyen, Thieu N. Vo
Abstract: This paper investigates the dynamical properties of tokens in pre-trained Transformer models and explores their application to improving Transformers. To this end, we analyze the dynamical system governing the continuous-time limit of the pre-trained model and characterize the asymptotic behavior of its solutions. Specifically, we characterize when tokens move closer to or farther from one another over time, depending on the model parameters. We provide sufficient conditions, based on these parameters, to identify scenarios where tokens either converge to zero or diverge to infinity. Unlike prior works, our conditions are broader in scope and more applicable to real-world models. Furthermore, we investigate how different forms of positional encoding -- specifically absolute and rotary -- affect these dynamical regimes. Empirical evidence reveals that the convergence scenario adversely impacts model performance. Motivated by these insights, we propose simple refinements to Transformer architectures that mitigate convergence behavior in models with absolute or rotary positional encoding. These findings support theoretical foundations and design principles for improving Transformer models.
Authors: Jiaju Qi, Lei Lei, Thorsteinn Jonsson, Dusit Niyato
Abstract: The integration of Electric Buses (EBs) with renewable energy sources such as photovoltaic (PV) panels is a promising approach to promote sustainable and low-carbon public transportation. However, optimizing EB charging schedules to minimize operational costs while ensuring safe operation without battery depletion remains challenging - especially under real-world conditions, where uncertainties in PV generation, dynamic electricity prices, variable travel times, and limited charging infrastructure must be accounted for. In this paper, we propose a safe Hierarchical Deep Reinforcement Learning (HDRL) framework for solving the EB Charging Scheduling Problem (EBCSP) under multi-source uncertainties. We formulate the problem as a Constrained Markov Decision Process (CMDP) with options to enable temporally abstract decision-making. We develop a novel HDRL algorithm, namely Double Actor-Critic Multi-Agent Proximal Policy Optimization Lagrangian (DAC-MAPPO-Lagrangian), which integrates Lagrangian relaxation into the Double Actor-Critic (DAC) framework. At the high level, we adopt a centralized PPO-Lagrangian algorithm to learn safe charger allocation policies. At the low level, we incorporate MAPPO-Lagrangian to learn decentralized charging power decisions under the Centralized Training and Decentralized Execution (CTDE) paradigm. Extensive experiments with real-world data demonstrate that the proposed approach outperforms existing baselines in both cost minimization and safety compliance, while maintaining fast convergence speed.
Authors: Jing Pan, Li Shi, Paul Lo
Abstract: Heterogeneous Treatment Effect (HTE) and Conditional Average Treatment Effect (CATE) models relax the assumption that treatment effects are the same for every user. We present a large scale industrial framework for estimating HTE using experimental data from hundreds of millions of Snapchat users. By combining results across many experiments, the framework uncovers latent user characteristics that were previously unmeasurable and produces stable treatment effect estimates at scale. We describe the core components that enabled this system, including experiment selection, base learner design, and incremental training. We also highlight two applications: user influenceability to ads and user sensitivity to ads. An online A/B test using influenceability scores for targeting showed an improvement on key business metrics that is more than six times larger than what is typically considered significant.
Authors: Roman Rausch, David Jansen, Sukhbinder Singh, Rom\'an Or\'us
Abstract: Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression, but presents several practical hurdles, e.g. selecting appropriate layer-wise ranks and getting rid of its parameter redundancy. In this work, we present two physics-inspired improvements to SVD LLM compression: (1) \textbf{FermiGrad}, a gradient-descent algorithm that determines globally optimal layer-wise ranks by relaxing the discrete singular-value truncation into a continuous optimization using the Fermi function; (2) \textbf{PivGa}, an additional \textit{lossless} compression of the low-rank factors that exploits the intrinsic gauge freedom in their parametrization.
Authors: Nihir Chadderwala
Abstract: Generative AI agents in life sciences face a critical challenge: determining the optimal approach for diverse queries ranging from simple factoid questions to complex mechanistic reasoning. Traditional methods rely on fixed rules or expensive labeled training data, neither of which adapts to changing conditions or user preferences. We present a novel framework that combines AWS Strands Agents with Thompson Sampling contextual bandits to enable AI agents to learn optimal decision-making strategies from user feedback alone. Our system optimizes three key dimensions: generation strategy selection (direct vs. chain-of-thought), tool selection (literature search, drug databases, etc.), and domain routing (pharmacology, molecular biology, clinical specialists). Through empirical evaluation on life science queries, we demonstrate 15-30\% improvement in user satisfaction compared to random baselines, with clear learning patterns emerging after 20-30 queries. Our approach requires no ground truth labels, adapts continuously to user preferences, and provides a principled solution to the exploration-exploitation dilemma in agentic AI systems.
Authors: Loup-Noe Levy, Jeremie Bosom, Guillaume Guerard, Soufian Ben Amor, Marc Bui, Hai Tran
Abstract: This article attempts answering the following problematic: How to model and classify energy consumption profiles over a large distributed territory to optimize the management of buildings' consumption? Doing case-by-case in depth auditing of thousands of buildings would require a massive amount of time and money as well as a significant number of qualified people. Thus, an automated method must be developed to establish a relevant and effective recommendations system. To answer this problematic, pretopology is used to model the sites' consumption profiles and a multi-criterion hierarchical classification algorithm, using the properties of pretopological space, has been developed in a Python library. To evaluate the results, three data sets are used: A generated set of dots of various sizes in a 2D space, a generated set of time series and a set of consumption time series of 400 real consumption sites from a French Energy company. On the point data set, the algorithm is able to identify the clusters of points using their position in space and their size as parameter. On the generated time series, the algorithm is able to identify the time series clusters using Pearson's correlation with an Adjusted Rand Index (ARI) of 1.
Authors: Guillaume Guerard, Sonia Djebali
Abstract: The advent of the big data paradigm has transformed how industries manage and analyze information, ushering in an era of unprecedented data volume, velocity, and variety. Within this landscape, mixed-data clustering has become a critical challenge, requiring innovative methods that can effectively exploit heterogeneous data types, including numerical and categorical variables. Traditional clustering techniques, typically designed for homogeneous datasets, often struggle to capture the additional complexity introduced by mixed data, underscoring the need for approaches specifically tailored to this setting. Hierarchical and explainable algorithms are particularly valuable in this context, as they provide structured, interpretable clustering results that support informed decision-making. This paper introduces a clustering method grounded in pretopological spaces. In addition, benchmarking against classical numerical clustering algorithms and existing pretopological approaches yields insights into the performance and effectiveness of the proposed method within the big data paradigm.
Authors: Loup-Noe Levy, Guillaume Guerard, Sonia Djebali, Soufian Ben Amor
Abstract: This article presents a novel pretopology-based algorithm designed to address the challenges of clustering mixed data without the need for dimensionality reduction. Leveraging Disjunctive Normal Form, our approach formulates customizable logical rules and adjustable hyperparameters that allow for user-defined hierarchical cluster construction and facilitate tailored solutions for heterogeneous datasets. Through hierarchical dendrogram analysis and comparative clustering metrics, our method demonstrates superior performance by accurately and interpretably delineating clusters directly from raw data, thus preserving data integrity. Empirical findings highlight the algorithm's robustness in constructing meaningful clusters and reveal its potential in overcoming issues related to clustered data explainability. The novelty of this work lies in its departure from traditional dimensionality reduction techniques and its innovative use of logical rules that enhance both cluster formation and clarity, thereby contributing a significant advancement to the discourse on clustering mixed data.
Authors: Mahdi Tavassoli Kejani, Fadi Dornaika, Jean-Michel Loubes
Abstract: Graph Neural Networks (GNNs) have demonstrated exceptional efficacy in relational learning tasks, including node classification and link prediction. However, their application raises significant fairness concerns, as GNNs can perpetuate and even amplify societal biases against protected groups defined by sensitive attributes such as race or gender. These biases are often inherent in the node features, structural topology, and message-passing mechanisms of the graph itself. A critical limitation of existing fairness-aware GNN methods is their reliance on the strong assumption that sensitive attributes are fully available for all nodes during training--a condition that poses a practical impediment due to privacy concerns and data collection constraints. To address this gap, we propose a novel, model-agnostic fairness regularization framework designed for the realistic scenario where sensitive attributes are only partially available. Our approach formalizes a fairness-aware objective function that integrates both equal opportunity and statistical parity as differentiable regularization terms. Through a comprehensive empirical evaluation across five real-world benchmark datasets, we demonstrate that the proposed method significantly mitigates bias across key fairness metrics while maintaining competitive node classification performance. Results show that our framework consistently outperforms baseline models in achieving a favorable fairness-accuracy trade-off, with minimal degradation in predictive accuracy. The datasets and source code will be publicly released at https://github.com/mtavassoli/GNN-FC.
Authors: Vahid R. Ramezani, Benjamin Englard
Abstract: Tilted (entropic) risk, obtained by applying a log-exponential transform to a base loss, is a well established tool in statistics and machine learning for emphasizing rare or high loss events while retaining a tractable optimization problem. In this work, our aim is to interpret its structure for Flow Matching (FM). FM learns a velocity field that transports samples from a simple source distribution to data by integrating an ODE. In rectified FM, training pairs are obtained by linearly interpolating between a source sample and a data sample, and a neural velocity field is trained to predict the straight line displacement using a mean squared error loss. This squared loss collapses all velocity targets that reach the same space-time point into a single conditional mean, thereby ignoring higher order conditional information (variance, skewness, multi-modality) that encodes fine geometric structure about the data manifold and minority branches. We apply the standard risk-sensitive (log-exponential) transform to the conditional FM loss and show that the resulting tilted risk loss is a natural upper-bound on a meaningful conditional entropic FM objective defined at each space-time point. Furthermore, we show that a small order expansion of the gradient of this conditional entropic objective yields two interpretable first order corrections: covariance preconditioning of the FM residual, and a skew tail term that favors asymmetric or rare branches. On synthetic data designed to probe ambiguity and tails, the resulting risk-sensitive loss improves statistical metrics and recovers geometric structure more faithfully than standard rectified FM.
Authors: Congjing Zhang, Feng Lin, Xinyi Zhao, Pei Guo, Wei Li, Lin Chen, Chaoyue Zhao, Shuai Huang
Abstract: The advance of Large Language Models (LLMs) has greatly stimulated research interest in developing multi-modal LLM (MLLM)-based visual anomaly detection (VAD) algorithms that can be deployed in complex environments. The challenge is that in these complex environments, the anomalies are sometimes highly contextual and also ambiguous, and thereby, uncertainty quantification (UQ) is a crucial capacity for an MLLM-based VAD system to succeed. In this paper, we introduce our UQ-supported MLLM-based VAD framework called ALARM. ALARM integrates UQ with quality-assurance techniques like reasoning chain, self-reflection, and MLLM ensemble for robust and accurate performance and is designed based on a rigorous probabilistic inference pipeline and computational process. Extensive empirical evaluations are conducted using the real-world smart-home benchmark data and wound image classification data, which shows ALARM's superior performance and its generic applicability across different domains for reliable decision-making.
Authors: Yiwei Shi, Hongnan Ma, Mengyue Yang, Cunjia Liu, Weiru Liu
Abstract: In emergency response and other high-stakes societal applications, early-stage state estimates critically shape downstream outcomes. Yet, these initial state estimates-often based on limited or biased information-can be severely misaligned with reality, constraining subsequent actions and potentially causing catastrophic delays, resource misallocation, and human harm. Under the stationary bootstrap baseline (zero transition and no rejuvenation), bootstrap particle filters exhibit Stationarity-Induced Posterior Support Invariance (S-PSI), wherein regions excluded by the initial prior remain permanently unexplorable, making corrections impossible even when new evidence contradicts current beliefs. While classical perturbations can in principle break this lock-in, they operate in an always-on fashion and may be inefficient. To overcome this, we propose a diffusion-driven Bayesian exploration framework that enables principled, real-time correction of early state estimation errors. Our method expands posterior support via entropy-regularized sampling and covariance-scaled diffusion. A Metropolis-Hastings check validates proposals and keeps inference adaptive to unexpected evidence. Empirical evaluations on realistic hazardous-gas localization tasks show that our approach matches reinforcement learning and planning baselines when priors are correct. It substantially outperforms classical SMC perturbations and RL-based methods under misalignment, and we provide theoretical guarantees that DEPF resolves S-PSI while maintaining statistical rigor.
Authors: Mainak Singha
Abstract: Large language models (LLMs) produce fluent but unsupported answers - hallucinations - limiting safe deployment in high-stakes domains. We propose ECLIPSE, a framework that treats hallucination as a mismatch between a model's semantic entropy and the capacity of available evidence. We combine entropy estimation via multi-sample clustering with a novel perplexity decomposition that measures how models use retrieved evidence. We prove that under mild conditions, the resulting entropy-capacity objective is strictly convex with a unique stable optimum. We evaluate on a controlled financial question answering dataset with GPT-3.5-turbo (n=200 balanced samples with synthetic hallucinations), where ECLIPSE achieves ROC AUC of 0.89 and average precision of 0.90, substantially outperforming a semantic entropy-only baseline (AUC 0.50). A controlled ablation with Claude-3-Haiku, which lacks token-level log probabilities, shows AUC dropping to 0.59 with coefficient magnitudes decreasing by 95% - demonstrating that ECLIPSE is a logprob-native mechanism whose effectiveness depends on calibrated token-level uncertainties. The perplexity decomposition features exhibit the largest learned coefficients, confirming that evidence utilization is central to hallucination detection. We position this work as a controlled mechanism study; broader validation across domains and naturally occurring hallucinations remains future work.
Authors: Shuvom Sadhuka, Drew Prinster, Clara Fannjiang, Gabriele Scalia, Aviv Regev, Hanchen Wang
Abstract: Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success of their trajectories, researchers have developed verifiers, such as LLM judges and process-reward models, to score the quality of each action in an agent's trajectory. Although these heuristic scores can be informative, there are no guarantees of correctness when used to decide whether an agent will yield a successful output. Here, we introduce e-valuator, a method to convert any black-box verifier score into a decision rule with provable control of false alarm rates. We frame the problem of distinguishing successful trajectories (that is, a sequence of actions that will lead to a correct response to the user's prompt) and unsuccessful trajectories as a sequential hypothesis testing problem. E-valuator builds on tools from e-processes to develop a sequential hypothesis test that remains statistically valid at every step of an agent's trajectory, enabling online monitoring of agents over arbitrarily long sequences of actions. Empirically, we demonstrate that e-valuator provides greater statistical power and better false alarm rate control than other strategies across six datasets and three agents. We additionally show that e-valuator can be used for to quickly terminate problematic trajectories and save tokens. Together, e-valuator provides a lightweight, model-agnostic framework that converts verifier heuristics into decisions rules with statistical guarantees, enabling the deployment of more reliable agentic systems.
Authors: Jialai She
Abstract: Shapley values, a gold standard for feature attribution in Explainable AI, face two primary challenges. First, the canonical Shapley framework assumes that the worth function is additive, yet real-world payoff constructions--driven by non-Gaussian distributions, heavy tails, feature dependence, or domain-specific loss scales--often violate this assumption, leading to distorted attributions. Secondly, achieving sparse explanations in high dimensions by computing dense Shapley values and then applying ad hoc thresholding is prohibitively costly and risks inconsistency. We introduce Sparse Isotonic Shapley Regression (SISR), a unified nonlinear explanation framework. SISR simultaneously learns a monotonic transformation to restore additivity--obviating the need for a closed-form specification--and enforces an L0 sparsity constraint on the Shapley vector, enhancing computational efficiency in large feature spaces. Its optimization algorithm leverages Pool-Adjacent-Violators for efficient isotonic regression and normalized hard-thresholding for support selection, yielding implementation ease and global convergence guarantees. Analysis shows that SISR recovers the true transformation in a wide range of scenarios and achieves strong support recovery even in high noise. Moreover, we are the first to demonstrate that irrelevant features and inter-feature dependencies can induce a true payoff transformation that deviates substantially from linearity. Experiments in regression, logistic regression, and tree ensembles demonstrate that SISR stabilizes attributions across payoff schemes, correctly filters irrelevant features while standard Shapley values suffer severe rank and sign distortions. By unifying nonlinear transformation estimation with sparsity pursuit, SISR advances the frontier of nonlinear explainability, providing a theoretically grounded and practical attribution framework.
Authors: Srijani Mukherjee (INES, USMB), Laurent Vuillon (LAMA), Liliane Bou Nassif (CETHIL, INSA Lyon, CNRS), St\'ephanie Giroux-Julien (LAGEPP), Herv\'e Pabiou (CETHIL), Denys Dutykh (KUSTAR), Ionnasis Tsanakas (LITEN / CEA-DES)
Abstract: The rapid growth of solar photovoltaic (PV) systems necessitates advanced methods for performance monitoring and anomaly detection to ensure optimal operation. In this study, we propose a novel approach leveraging Temporal Graph Neural Network (Temporal GNN) to predict solar PV output power and detect anomalies using environmental and operational parameters. The proposed model utilizes graph-based temporal relationships among key PV system parameters, including irradiance, module and ambient temperature to predict electrical power output. This study is based on data collected from an outdoor facility located on a rooftop in Lyon (France) including power measurements from a PV module and meteorological parameters.
Authors: Hanbin Cho, Jecheon Yu, Hyeonbin Moon, Jiyoung Yoon, Junhyeong Lee, Giyoung Kim, Jinhyoung Park, Seunghwa Ryu
Abstract: Reliable real-time analysis of sensor data is essential for structural health monitoring (SHM) of high-value assets, yet a major challenge is to obtain spatially resolved full-field aleatoric and epistemic uncertainties for trustworthy decision-making. We present an integrated SHM framework that combines principal component analysis (PCA), a Bayesian neural network (BNN), and Hamiltonian Monte Carlo (HMC) inference, mapping sparse strain gauge measurements onto leading PCA modes to reconstruct full-field strain distributions with uncertainty quantification. The framework was validated through cyclic four-point bending tests on carbon fiber reinforced polymer (CFRP) specimens with varying crack lengths, achieving accurate strain field reconstruction (R squared value > 0.9) while simultaneously producing real-time uncertainty fields. A key contribution is that the BNN yields robust full-field strain reconstructions from noisy experimental data with crack-induced strain singularities, while also providing explicit representations of two complementary uncertainty fields. Considered jointly in full-field form, the aleatoric and epistemic uncertainty fields make it possible to diagnose at a local level, whether low-confidence regions are driven by data-inherent issues or by model-related limitations, thereby supporting reliable decision-making. Collectively, the results demonstrate that the proposed framework advances SHM toward trustworthy digital twin deployment and risk-aware structural diagnostics.
Authors: Xiwen Wei, Mustafa Munir, Radu Marculescu
Abstract: Unified Multimodal Generative Models (UMGMs) unify visual understanding and image generation within a single autoregressive framework. However, their ability to continually learn new tasks is severely hindered by catastrophic forgetting, both within a modality (intra-modal) and across modalities (inter-modal). While intra-modal forgetting has been studied in prior continual learning (CL) work, inter-modal forgetting remains largely unexplored. In this paper, we identify and empirically validate this phenomenon in UMGMs and provide a theoretical explanation rooted in gradient conflict between modalities. To address both intra- and inter-modal forgetting, we propose Modality-Decoupled Experts (MoDE), a lightweight and scalable architecture that isolates modality-specific updates to mitigate the gradient conflict and leverages knowledge distillation to prevent catastrophic forgetting and preserve pre-trained capabilities. Unlike previous CL methods that remain modality-coupled and suffer from modality gradient conflict, MoDE explicitly decouples modalities to prevent interference. Experiments across diverse benchmarks demonstrate that MoDE significantly mitigates both inter- and intra-modal forgetting, outperforming prior CL baselines in unified multimodal generation settings. Codes will be publicly available: https://github.com/Christina200/MoDE-official.git
Authors: Ziyu Xiong, Yichi Zhang, Foyez Alauddin, Chu Xin Cheng, Joon Soo An, Mohammad R. Seyedsayamdost, Ellen D. Zhong
Abstract: Nuclear Magnetic Resonance (NMR) spectroscopy is a cornerstone technique for determining the structures of small molecules and is especially critical in the discovery of novel natural products and clinical therapeutics. Yet, interpreting NMR spectra remains a time-consuming, manual process requiring extensive domain expertise. We introduce ChefNMR (CHemical Elucidation From NMR), an end-to-end framework that directly predicts an unknown molecule's structure solely from its 1D NMR spectra and chemical formula. We frame structure elucidation as conditional generation from an atomic diffusion model built on a non-equivariant transformer architecture. To model the complex chemical groups found in natural products, we generated a dataset of simulated 1D NMR spectra for over 111,000 natural products. ChefNMR predicts the structures of challenging natural product compounds with an unsurpassed accuracy of over 65%. This work takes a significant step toward solving the grand challenge of automating small-molecule structure elucidation and highlights the potential of deep learning in accelerating molecular discovery. Code is available at https://github.com/ml-struct-bio/chefnmr.
Authors: Adele Chinda, Richmond Azumah, Hemanth Demakethepalli Venkateswara
Abstract: Wastewater-based genomic surveillance has emerged as a powerful tool for population-level viral monitoring, offering comprehensive insights into circulating viral variants across entire communities. However, this approach faces significant computational challenges stemming from high sequencing noise, low viral coverage, fragmented reads, and the complete absence of labeled variant annotations. Traditional reference-based variant calling pipelines struggle with novel mutations and require extensive computational resources. We present a comprehensive framework for unsupervised viral variant detection using Vector-Quantized Variational Autoencoders (VQ-VAE) that learns discrete codebooks of genomic patterns from k-mer tokenized sequences without requiring reference genomes or variant labels. Our approach extends the base VQ-VAE architecture with masked reconstruction pretraining for robustness to missing data and contrastive learning for highly discriminative embeddings. Evaluated on SARS-CoV-2 wastewater sequencing data comprising approximately 100,000 reads, our VQ-VAE achieves 99.52% mean token-level accuracy and 56.33% exact sequence match rate while maintaining 19.73% codebook utilization (101 of 512 codes active), demonstrating efficient discrete representation learning. Contrastive fine-tuning with different projection dimensions yields substantial clustering improvements: 64-dimensional embeddings achieve +35% Silhouette score improvement (0.31 to 0.42), while 128-dimensional embeddings achieve +42% improvement (0.31 to 0.44), clearly demonstrating the impact of embedding dimensionality on variant discrimination capability. Our reference-free framework provides a scalable, interpretable approach to genomic surveillance with direct applications to public health monitoring.
Authors: Anthony Liang, Jonathan Berant, Adam Fisch, Abhimanyu Goyal, Kalpesh Krishna, Jacob Eisenstein
Abstract: Reasoning models often spend a significant amount of time thinking before they generate a visible response. In the meantime, they do not give the user any hints as to whether their reasoning is on the right track, and do not give the user any recourse to stop and correct them if their reasoning is flawed. This creates a frustrating, but unfortunately common, experience: the user's time is wasted while the model reasons from a false premise that could have easily been corrected. In contrast, human speakers typically perform lightweight, incremental grounding acts to ensure that participants in the conversation are on the same page; here we ask if language models can learn to leverage a similar type of behavior? With this motivation, we propose interleaved reasoning (IR), in which the model alternates between thinking and surfacing intermediate responses, as an alternative to the standard "think-then-answer" approach. By providing useful information to the user earlier, IR reduces perceived latency, the time a user waits for an initial output, without compromising the quality of the final response. We further introduce a specialization of interleaved reasoning, Plantain (Plan-Thought-Answer Interleaving), where the first intermediate response is an explicit, step-by-step plan for executing the task. This plan-first strategy allows for user intervention and early feedback for subsequent reasoning steps. We demonstrate that Plantain yields an ~6% improvement in pass@1 across several challenging math reasoning and coding benchmarks, while reducing time-to-first-response by over 60% relative to think-then-answer baselines.
Authors: Aashi Jindal
Abstract: This work introduces FiRE/FiRE.1, a novel sketching-based algorithm for anomaly detection to quickly identify rare cell sub-populations in large-scale single-cell RNA sequencing data. This method demonstrated superior performance against state-of-the-art techniques. Furthermore, the thesis proposes Enhash, a fast and resource-efficient ensemble learner that uses projection hashing to detect concept drift in streaming data, proving highly competitive in time and accuracy across various drift types.
Authors: Douglas Aberdeen, Jonathan Baxter
Abstract: Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful when memory is required. In this paper we develop several improved algorithms for learning policies with memory in an infinite-horizon setting -- directly when a known model of the environment is available, and via simulation otherwise. We compare these algorithms on some large POMDPs, including noisy robot navigation and multi-agent problems.
Authors: Nigel Tao, Jonathan Baxter, Lex Weaver
Abstract: Network routing is a distributed decision problem which naturally admits numerical performance measures, such as the average time for a packet to travel from source to destination. OLPOMDP, a policy-gradient reinforcement learning algorithm, was successfully applied to simulated network routing under a number of network models. Multiple distributed agents (routers) learned co-operative behavior without explicit inter-agent communication, and they avoided behavior which was individually desirable, but detrimental to the group's overall performance. Furthermore, shaping the reward signal by explicitly penalizing certain patterns of sub-optimal behavior was found to dramatically improve the convergence rate.
Authors: Andrea Burns, Lauren Harrell, Bart van Merri\"enboer, Vincent Dumoulin, Jenny Hamer, Tom Denton
Abstract: Perch 2.0 is a supervised bioacoustics foundation model pretrained on 14,597 species, including birds, mammals, amphibians, and insects, and has state-of-the-art performance on multiple benchmarks. Given that Perch 2.0 includes almost no marine mammal audio or classes in the training data, we evaluate Perch 2.0 performance on marine mammal and underwater audio tasks through few-shot transfer learning. We perform linear probing with the embeddings generated from this foundation model and compare performance to other pretrained bioacoustics models. In particular, we compare Perch 2.0 with previous multispecies whale, Perch 1.0, SurfPerch, AVES-bio, BirdAVES, and Birdnet V2.3 models, which have open-source tools for transfer-learning and agile modeling. We show that the embeddings from the Perch 2.0 model have consistently high performance for few-shot transfer learning, generally outperforming alternative embedding models on the majority of tasks, and thus is recommended when developing new linear classifiers for marine mammal classification with few labeled examples.
Authors: Salman Rahman, Sruthi Gorantla, Arpit Gupta, Swastik Roy, Nanyun Peng, Yang Liu
Abstract: Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning, yet their adoption remains limited by the need for expensive step-level annotations or ground truth references. We propose SPARK: a three-stage framework where in the first stage a generator model produces diverse solutions and a verifier model evaluates them using parallel scaling (self-consistency) and sequential scaling (meta-critique). In the second stage, we use these verification outputs as synthetic training data to fine-tune generative process reward models, which subsequently serve as reward signals during training. We show that aggregating multiple independent verifications at the step level produces training data for process reward models that surpass ground-truth outcome supervision, achieving 67.5 F1 on ProcessBench (a benchmark for identifying erroneous steps in mathematical reasoning) compared to 66.4 for reference-guided training and 61.9 for GPT-4o. In the final stage, we apply our generative PRM with chain-of-thought verification (PRM-CoT) as the reward model in RL experiments on mathematical reasoning, and introduce format constraints to prevent reward hacking. Using Qwen2.5-Math-7B, we achieve 47.4% average accuracy across six mathematical reasoning benchmarks, outperforming ground-truth-based RLVR (43.9%). Our work enables reference-free RL training that exceeds ground-truth methods, opening new possibilities for domains lacking verifiable answers or accessible ground truth.
Authors: Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda
Abstract: Training vision language models (VLMs) aims to align visual representations from a vision encoder with the textual representations of a pretrained large language model (LLM). However, many VLMs exhibit reduced factual recall performance compared to their LLM backbones, raising the question of how effective multimodal fine-tuning is at extending existing mechanisms within the LLM to visual inputs. We argue that factual recall based on visual inputs requires VLMs to solve a two-hop problem: (1) forming entity representations from visual inputs, and (2) recalling associated factual knowledge based on these entity representations. By benchmarking 14 VLMs with various architectures (LLaVA, Native, Cross-Attention), sizes (7B-124B parameters), and training setups on factual recall tasks against their original LLM backbone models, we find that 11 of 14 models exhibit factual recall degradation. We select three models with high and two models with low performance degradation, and use attribution patching, activation patching, and probing to show that degraded VLMs struggle to use the existing factual recall circuit of their LLM backbone, because they resolve the first hop too late in the computation. In contrast, high-performing VLMs resolve entity representations early enough to reuse the existing factual recall mechanism. Finally, we demonstrate two methods to recover performance: patching entity representations from the LLM backbone into the VLM, and prompting with chain-of-thought reasoning. Our results highlight that the speed of early entity resolution critically determines how effective VLMs are in using preexisting LLM mechanisms. More broadly, our work illustrates how mechanistic analysis can explain and unveil systematic failures in multimodal alignment.
Authors: Nicholas Sung, Steven Spreizer, Mohamed Elrefaie, Matthew C. Jones, Faez Ahmed
Abstract: Despite progress in machine learning-based aerodynamic surrogates, the scarcity of large, field-resolved datasets limits progress on accurate pointwise prediction and reproducible inverse design for aircraft. We introduce BlendedNet++, a large-scale aerodynamic dataset and benchmark focused on blended wing body (BWB) aircraft. The dataset contains over 12,000 unique geometries, each simulated at a single flight condition, yielding 12,490 aerodynamic results for steady RANS CFD. For every case, we provide (i) integrated force/moment coefficients CL, CD, CM and (ii) dense surface fields of pressure and skin friction coefficients Cp and (Cfx, Cfy, Cfz). Using this dataset, we standardize a forward-surrogate benchmark to predict pointwise fields across six model families: GraphSAGE, GraphUNet, PointNet, a coordinate Transformer (Transolver-style), a FiLMNet (coordinate MLP with feature-wise modulation), and a Graph Neural Operator Transformer (GNOT). Finally, we present an inverse design task of achieving a specified lift-to-drag ratio under fixed flight conditions, implemented via a conditional diffusion model. To assess performance, we benchmark this approach against gradient-based optimization on the same surrogate and a diffusion-optimization hybrid that first samples with the conditional diffusion model and then further optimizes the designs. BlendedNet++ provides a unified forward and inverse protocol with multi-model baselines, enabling fair, reproducible comparison across architectures and optimization paradigms. We expect BlendedNet++ to catalyze reproducible research in field-level aerodynamics and inverse design; resources (dataset, splits, baselines, and scripts) will be released upon acceptance.
Authors: Dario Fenoglio, Mohan Li, Davide Casnici, Matias Laporte, Shkurta Gashi, Silvia Santini, Martin Gjoreski, Marc Langheinrich
Abstract: Human Activity Recognition (HAR) benefits various application domains, including health and elderly care. Traditional HAR involves constructing pipelines reliant on centralized user data, which can pose privacy concerns as they necessitate the uploading of user data to a centralized server. This work proposes multi-frequency Federated Learning (FL) to enable: (1) privacy-aware ML; (2) joint ML model learning across devices with varying sampling frequency. We focus on head-worn devices (e.g., earbuds and smart glasses), a relatively unexplored domain compared to traditional smartwatch- or smartphone-based HAR. Results have shown improvements on two datasets against frequency-specific approaches, indicating a promising future in the multi-frequency FL-HAR task. The proposed network's implementation is publicly available for further research and development.
Authors: Julian Evan Chrisnanto, Nurfauzi Fadillah, Yulison Herry Chrisnanto
Abstract: Physics-Informed Neural Networks (PINNs) have emerged as a powerful, mesh-free paradigm for solving partial differential equations (PDEs). However, they notoriously struggle with stiff, multi-scale, and nonlinear systems due to the inherent spectral bias of standard multilayer perceptron (MLP) architectures, which prevents them from adequately representing high-frequency components. In this work, we introduce the Adaptive Spectral Physics-Enabled Network (ASPEN), a novel architecture designed to overcome this critical limitation. ASPEN integrates an adaptive spectral layer with learnable Fourier features directly into the network's input stage. This mechanism allows the model to dynamically tune its own spectral basis during training, enabling it to efficiently learn and represent the precise frequency content required by the solution. We demonstrate the efficacy of ASPEN by applying it to the complex Ginzburg-Landau equation (CGLE), a canonical and challenging benchmark for nonlinear, stiff spatio-temporal dynamics. Our results show that a standard PINN architecture catastrophically fails on this problem, diverging into non-physical oscillations. In contrast, ASPEN successfully solves the CGLE with exceptional accuracy. The predicted solution is visually indistinguishable from the high-resolution ground truth, achieving a low median physics residual of 5.10 x 10^-3. Furthermore, we validate that ASPEN's solution is not only pointwise accurate but also physically consistent, correctly capturing emergent physical properties, including the rapid free energy relaxation and the long-term stability of the domain wall front. This work demonstrates that by incorporating an adaptive spectral basis, our framework provides a robust and physically-consistent solver for complex dynamical systems where standard PINNs fail, opening new options for machine learning in challenging physical domains.
Authors: Echo Diyun LU, Charles Findling, Marianne Clausel, Alessandro Leite, Wei Gong, Pierric Kersaudy
Abstract: Regime transitions routinely break stationarity in time series, making calibrated uncertainty as important as point accuracy. We study distribution-free uncertainty for regime-switching forecasting by coupling Deep Switching State Space Models with Adaptive Conformal Inference (ACI) and its aggregated variant (AgACI). We also introduce a unified conformal wrapper that sits atop strong sequence baselines including S4, MC-Dropout GRU, sparse Gaussian processes, and a change-point local model to produce online predictive bands with finite-sample marginal guarantees under nonstationarity and model misspecification. Across synthetic and real datasets, conformalized forecasters achieve near-nominal coverage with competitive accuracy and generally improved band efficiency.
Authors: Pengfei Hu, Fan Ming, Xiaoxue Han, Chang Lu, Yue Ning, Dan Lu
Abstract: Deep learning models have shown promise in reservoir inflow prediction, yet their performance often deteriorates when applied to different reservoirs due to distributional differences, referred to as the domain shift problem. Domain generalization (DG) solutions aim to address this issue by extracting domain-invariant representations that mitigate errors in unseen domains. However, in hydrological settings, each reservoir exhibits unique inflow patterns, while some metadata beyond observations like spatial information exerts indirect but significant influence. This mismatch limits the applicability of conventional DG techniques to many-domain hydrological systems. To overcome these challenges, we propose HydroDCM, a scalable DG framework for cross-reservoir inflow forecasting. Spatial metadata of reservoirs is used to construct pseudo-domain labels that guide adversarial learning of invariant temporal features. During inference, HydroDCM adapts these features through light-weight conditioning layers informed by the target reservoir's metadata, reconciling DG's invariance with location-specific adaptation. Experiment results on 30 real-world reservoirs in the Upper Colorado River Basin demonstrate that our method substantially outperforms state-of-the-art DG baselines under many-domain conditions and remains computationally efficient.
Authors: Matthew Peroni, Franck Le, Vadim Sheinin
Abstract: The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that encourage desirable model properties. Prior work has mainly focused on crafting high-quality priors over generators to improve overall pretraining performance. Our insight is that parameterizing the generator distribution enables an adversarial robustness perspective: during training, we can adapt the generator to emphasize datasets that are particularly challenging for the model. We formalize this by introducing an optimality gap measure, given by the difference between TFM performance and the best achievable performance as estimated by strong baselines such as XGBoost, CatBoost, and Random Forests. Building on this idea, we propose Robust Tabular Foundation Models (RTFM), a model-agnostic adversarial training framework. Applied to the TabPFN V2 classifier, RTFM improves benchmark performance, with up to a 6% increase in mean normalized AUC over the original TabPFN and other baseline algorithms, while requiring less than 100k additional synthetic datasets. These results highlight a promising new direction for targeted adversarial training and fine-tuning of TFMs using synthetic data alone.
Authors: Aniruddha Bora, Shixuan Zhang, Khemraj Shukla, Bryce Harrop, George Em. Karniadakis, L. Ruby Leung
Abstract: Coarse resolution, imperfect parameterizations, and uncertain initial states and forcings limit Earth-system model (ESM) predictions. Traditional bias correction via data assimilation improves constrained simulations but offers limited benefit once models run freely. We introduce an operator-learning framework that maps instantaneous model states to bias-correction tendencies and applies them online during integration. Building on a U-Net backbone, we develop two operator architectures Inception U-Net (IUNet) and a multi-scale network (M\&M) that combine diverse upsampling and receptive fields to capture multiscale nonlinear features under Energy Exascale Earth System Model (E3SM) runtime constraints. Trained on two years E3SM simulations nudged toward ERA5 reanalysis, the operators generalize across height levels and seasons. Both architectures outperform standard U-Net baselines in offline tests, indicating that functional richness rather than parameter count drives performance. In online hybrid E3SM runs, M\&M delivers the most consistent bias reductions across variables and vertical levels. The ML-augmented configurations remain stable and computationally feasible in multi-year simulations, providing a practical pathway for scalable hybrid modeling. Our framework emphasizes long-term stability, portability, and cadence-limited updates, demonstrating the utility of expressive ML operators for learning structured, cross-scale relationships and retrofitting legacy ESMs.
Authors: Ngoc Bui, Shubham Sharma, Simran Lamba, Saumitra Mishra, Rex Ying
Abstract: Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization, offloading, or heuristic KV eviction, either incur high orchestration costs or rely on unreliable attention-based proxies of importance. We propose TRIM-KV, a novel approach that learns each token's intrinsic importance at creation time via a lightweight retention gate. Each gate predicts a scalar retention score that decays over time, reflecting the long-term utility of the token for a specific layer and head. Tokens with low scores are evicted when the memory budget is exceeded, ensuring that the cache always contains the most critical tokens. TRIM-KV is trained efficiently through distillation from a frozen LLM combined with a capacity loss, requiring only gate fine-tuning and adding negligible inference overhead. Across mathematical reasoning (GSM8K, MATH-500, AIME24), procedural generation (LongProc), conversational long-memory benchmarks (LongMemEval), and long-context understanding (LongBench and SCBench), TRIM-KV consistently outperforms strong eviction and learnable retrieval baselines, especially in low-memory regimes. Remarkably, it even surpasses full-cache models in some settings, showing that selective retention can serve as a form of regularization, suppressing noise from uninformative tokens. Qualitative analyses further reveal that learned retention scores align with human intuition, naturally recovering heuristics such as sink tokens, sliding windows, and gist compression without explicit design. Beyond efficiency, retention scores provide insights into layer- and head-specific roles, suggesting a new path toward LLM interpretability.
Authors: Alan T. L. Bacellar, Mustafa Munir, Felipe M. G. Fran\c{c}a, Priscila M. V. Lima, Radu Marculescu, Lizy K. John
Abstract: Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-round, data distribution invariant solution, but is limited to linear models. Subsequent non-linear approaches, like DeepAFL, regain accuracy but sacrifice the single-round benefit. In this work, we break this trade-off. We propose SAFLe, a framework that achieves scalable non-linear expressivity by introducing a structured head of bucketed features and sparse, grouped embeddings. We prove this non-linear architecture is mathematically equivalent to a high-dimensional linear regression. This key equivalence allows SAFLe to be solved with AFL's single-shot, invariant aggregation law. Empirically, SAFLe establishes a new state-of-the-art for analytic FL, significantly outperforming both linear AFL and multi-round DeepAFL in accuracy across all benchmarks, demonstrating a highly efficient and scalable solution for federated vision.
Authors: Hongseon Yeom, Jaeyoul Shin, Soojin Min, Jeongmin Yoon, Seunghak Yu, Dongyeop Kang
Abstract: Online A/B testing, the gold standard for evaluating new advertising policies, consumes substantial engineering resources and risks significant revenue loss from deploying underperforming variations. This motivates the use of Off-Policy Evaluation (OPE) for rapid, offline assessment. However, applying OPE to ad auctions is fundamentally more challenging than in domains like recommender systems, where stochastic policies are common. In online ad auctions, it is common for the highest-bidding ad to win the impression, resulting in a deterministic, winner-takes-all setting. This results in zero probability of exposure for non-winning ads, rendering standard OPE estimators inapplicable. We introduce the first principled framework for OPE in deterministic auctions by repurposing the bid landscape model to approximate the propensity score. This model allows us to derive robust approximate propensity scores, enabling the use of stable estimators like Self-Normalized Inverse Propensity Scoring (SNIPS) for counterfactual evaluation. We validate our approach on the AuctionNet simulation benchmark and against 2-weeks online A/B test from a large-scale industrial platform. Our method shows remarkable alignment with online results, achieving a 92\% Mean Directional Accuracy (MDA) in CTR prediction, significantly outperforming the parametric baseline. MDA is the most critical metric for guiding deployment decisions, as it reflects the ability to correctly predict whether a new model will improve or harm performance. This work contributes the first practical and validated framework for reliable OPE in deterministic auction environments, offering an efficient alternative to costly and risky online experiments.
Authors: Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel
Abstract: Federated learning (FL) deployed over quantum enabled and heterogeneous classical networks faces significant performance degradation due to uneven client quality, stochastic teleportation fidelity, device instability, and geometric mismatch between local and global models. Classical aggregation rules assume euclidean topology and uniform communication reliability, limiting their suitability for emerging quantum federated systems. This paper introduces A2G (Adaptive Aggregation with Two Gains), a dual gain framework that jointly regulates geometric blending through a geometry gain and modulates client importance using a QoS gain derived from teleportation fidelity, latency, and instability. We develop the A2G update rule, establish convergence guarantees under smoothness and bounded variance assumptions, and show that A2G recovers FedAvg, QoS aware averaging, and manifold based aggregation as special cases. Experiments on a quantum classical hybrid testbed demonstrate improved stability and higher accuracy under heterogeneous and noisy conditions.
Authors: Mahdi Arab Loodaricheh, Mohammad Hossein Manshaei, Anita Raja
Abstract: Modern Intrusion Detection Systems (IDS) face severe challenges due to heterogeneous network traffic, evolving cyber threats, and pronounced data imbalance between benign and attack flows. While generative models have shown promise in data augmentation, existing approaches are limited to single modalities and fail to capture cross-domain dependencies. This paper introduces MAGE-ID (Multimodal Attack Generator for Intrusion Detection), a diffusion-based generative framework that couples tabular flow features with their transformed images through a unified latent prior. By jointly training Transformer and CNN-based variational encoders with an EDM style denoiser, MAGE-ID achieves balanced and coherent multimodal synthesis. Evaluations on CIC-IDS-2017 and NSL-KDD demonstrate significant improvements in fidelity, diversity, and downstream detection performance over TabSyn and TabDDPM, highlighting the effectiveness of MAGE-ID for multimodal IDS augmentation.
Authors: Hung-Yueh Chiang, Chi-Chih Chang, Yu-Chen Lu, Chien-Yu Lin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu
Abstract: Deploying large language model (LLM) models on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by the current device workload, adding to the uncertainty of model deployment. We introduce UniQL, a unified post-training quantization and low-rank compression framework with on-device configurable pruning rates for edge LLMs. UniQL is a general framework that integrates quantization and low-rank compression for Transformers, State Space Models (SSMs), and hybrid models to support diverse edge applications. In our proposed joint framework, we introduce an efficient structured weight-sorting method that speeds up computation by 20x, quantization-aware singular value decomposition (SVD) to minimize quantization errors, state-aware weight sorting for SSMs, and a fused rotary positional embedding (RoPE) kernel for pruned models. Our framework performs weight-sorting, fine-tuning, and quantization in the cloud in a single-pass workflow, while enabling on-device configurable pruning rates up to 35%. Our experiments show that quantized and pruned models achieve a memory reduction of 4x-5.7x and a token-throughput improvement of 2.7x-3.4x, maintaining accuracy within 5% of the original models at 15% pruning across Transformers (Llama3 and Qwen2.5), SSMs (Mamba2), and hybrid models (Nemotron-H and Bamba-v2). The code and quantized models are available at: https://github.com/enyac-group/UniQL.
Authors: Lakshmi Jayalal, Sheetal Kalyani
Abstract: Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods like multiple measurement vectors orthogonal matching pursuit (M-OMP) and multiple measurement vectors FOCal Underdetermined System Solver (M-FOCUSS) often require careful parameter tuning or prior knowledge of the sparsity of the signal and/or noise variance. We introduce a novel tuning-free framework that leverages Implicit Regularization (IR) from overparameterization to overcome this limitation. Our approach reparameterizes the estimation matrix into factors that decouple the shared row-support from individual vector entries. We show that the optimization dynamics inherently promote the desired row-sparse structure by applying gradient descent to a standard least-squares objective on these factors. We prove that with a sufficiently small and balanced initialization, the optimization dynamics exhibit a "momentum-like" effect, causing the norms of rows in the true support to grow significantly faster than others. This formally guarantees that the solution trajectory converges towards an idealized row-sparse solution. Additionally, empirical results demonstrate that our approach achieves performance comparable to established methods without requiring any prior information or tuning.
Authors: Hamed Poursiami, Shay Snyder, Guojing Cong, Thomas Potok, Maryam Parsa
Abstract: Graph classification is a fundamental task in domains ranging from molecular property prediction to materials design. While graph neural networks (GNNs) achieve strong performance by learning expressive representations via message passing, they incur high computational costs, limiting their scalability and deployment on resource-constrained devices. Hyperdimensional Computing (HDC), also known as Vector Symbolic Architectures (VSA), offers a lightweight, brain-inspired alternative, yet existing HDC-based graph methods typically struggle to match the predictive performance of GNNs. In this work, we propose VS-Graph, a vector-symbolic graph learning framework that narrows the gap between the efficiency of HDC and the expressive power of message passing. VS-Graph introduces a Spike Diffusion mechanism for topology-driven node identification and an Associative Message Passing scheme for multi-hop neighborhood aggregation entirely within the high-dimensional vector space. Without gradient-based optimization or backpropagation, our method achieves competitive accuracy with modern GNNs, outperforming the prior HDC baseline by 4-5% on standard benchmarks such as MUTAG and DD. It also matches or exceeds the performance of the GNN baselines on several datasets while accelerating the training by a factor of up to 450x. Furthermore, VS-Graph maintains high accuracy even with the hypervector dimensionality reduced to D=128, demonstrating robustness under aggressive dimension compression and paving the way for ultra-efficient execution on edge and neuromorphic hardware.
Authors: Joe Edelman, Tan Zhi-Xuan, Ryan Lowe, Oliver Klingefjord, Vincent Wang-Mascianica, Matija Franklin, Ryan Othniel Kearns, Ellie Hain, Atrisha Sarkar, Michiel Bakker, Fazl Barez, David Duvenaud, Jakob Foerster, Iason Gabriel, Joseph Gubbels, Bryce Goodman, Andreas Haupt, Jobst Heitzig, Julian Jara-Ettinger, Atoosa Kasirzadeh, James Ravi Kirkpatrick, Andrew Koh, W. Bradley Knox, Philipp Koralus, Joel Lehman, Sydney Levine, Samuele Marro, Manon Revel, Toby Shorin, Morgan Sutherland, Michael Henry Tessler, Ivan Vendrov, James Wilken-Smith
Abstract: Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions.
Authors: Prakhar Gupta, Henry Conklin, Sarah-Jane Leslie, Andrew Lee
Abstract: In this work we study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers across different training stages. We use a controlled 2x2x2 Rubik's Cube and ask: (1) how does explicitly pretraining a world model affect the model's latent representations, and (2) how does world-model quality affect the model's performance after reinforcement learning post-training? We compare standard next-token prediction to two explicit world-modeling strategies -- (i) state-prediction pretraining and (ii) a joint state-prediction + next-token objective -- and assess task performance after Group Relative Policy Optimization (GRPO) is applied as post-training. We evaluate the representation quality with linear probes and causal interventions. We find that explicit world-modeling yields more linearly decodable and causally steerable state representations. More importantly, we find that improved state representations lead to higher gains for GRPO, especially on harder cube states. Our results indicate that sharpening state representations can improve the effectiveness of post-training for sequence-planning tasks.
Authors: Ziyi Ding, Xiao-Ping Zhang
Abstract: We propose GaussDetect-LiNGAM, a novel approach for bivariate causal discovery that eliminates the need for explicit Gaussianity tests by leveraging a fundamental equivalence between noise Gaussianity and residual independence in the reverse regression. Under the standard LiNGAM assumptions of linearity, acyclicity, and exogeneity, we prove that the Gaussianity of the forward-model noise is equivalent to the independence between the regressor and residual in the reverse model. This theoretical insight allows us to replace fragile and sample-sensitive Gaussianity tests with robust kernel-based independence tests. Experimental results validate the equivalence and demonstrate that GaussDetect-LiNGAM maintains high consistency across diverse noise types and sample sizes, while reducing the number of tests per decision (TPD). Our method enhances both the efficiency and practical applicability of causal inference, making LiNGAM more accessible and reliable in real-world scenarios.
Authors: Yuanbang Liang, Yang Li
Abstract: Grokking-delayed generalization that emerges well after a model has fit the training data-has been linked to robustness and representation quality. We ask whether this training regime also helps with machine unlearning, i.e., removing the influence of specified data without full retraining. We compare applying standard unlearning methods before versus after the grokking transition across vision (CNNs/ResNets on CIFAR, SVHN, and ImageNet) and language (a transformer on a TOFU-style setup). Starting from grokked checkpoints consistently yields (i) more efficient forgetting (fewer updates to reach a target forget level), (ii) less collateral damage (smaller drops on retained and test performance), and (iii) more stable updates across seeds, relative to early-stopped counterparts under identical unlearning algorithms. Analyses of features and curvature further suggest that post-grokking models learn more modular representations with reduced gradient alignment between forget and retain subsets, which facilitates selective forgetting. Our results highlight when a model is trained (pre- vs. post-grokking) as an orthogonal lever to how unlearning is performed, providing a practical recipe to improve existing unlearning methods without altering their algorithms.
Authors: Yujing Liu, Chen Yang
Abstract: In recent years, financial sentiment analysis of public opinion has become increasingly important for market forecasting and risk assessment. However, existing methods often struggle to effectively integrate diverse opinion modalities and capture fine-grained interactions across them. This paper proposes an end-to-end deep learning framework that integrates two distinct modalities of financial opinions: recency modality (timely opinions) and popularity modality (trending opinions), through a novel cross-modal attention mechanism specifically designed for financial sentiment analysis. While both modalities consist of textual data, they represent fundamentally different information channels: recency-driven market updates versus popularity-driven collective sentiment. Our model first uses BERT (Chinese-wwm-ext) for feature embedding and then employs our proposed Financial Multi-Head Cross-Attention (FMHCA) structure to facilitate information exchange between these distinct opinion modalities. The processed features are optimized through a transformer layer and fused using multimodal factored bilinear pooling for classification into negative, neutral, and positive sentiment. Extensive experiments on a comprehensive dataset covering 837 companies demonstrate that our approach achieves an accuracy of 83.5%, significantly outperforming baselines including BERT+Transformer by 21 percent. These results highlight the potential of our framework to support more accurate financial decision-making and risk management.
Authors: Hongtao Hao, Joseph L. Austerweil
Abstract: Chronic diseases often progress differently across patients. Rather than randomly varying, there are typically a small number of subtypes for how a disease progresses across patients. To capture this structured heterogeneity, the Subtype and Stage Inference Event-Based Model (SuStaIn) estimates the number of subtypes, the order of disease progression for each subtype, and assigns each patient to a subtype from primarily cross-sectional data. It has been widely applied to uncover the subtypes of many diseases and inform our understanding of them. But how robust is its performance? In this paper, we develop a principled Bayesian subtype variant of the event-based model (BEBMS) and compare its performance to SuStaIn in a variety of synthetic data experiments with varied levels of model misspecification. BEBMS substantially outperforms SuStaIn across ordering, staging, and subtype assignment tasks. Further, we apply BEBMS and SuStaIn to a real-world Alzheimer's data set. We find BEBMS has results that are more consistent with the scientific consensus of Alzheimer's disease progression than SuStaIn.
Authors: Ian Henriques, Lynda Elhassar, Sarvesh Relekar, Denis Walrave, Shayan Hassantabar, Vishu Ghanakota, Adel Laoui, Mahmoud Aich, Rafia Tir, Mohamed Zerguine, Samir Louafi, Moncef Kimouche, Emmanuel Cosson, Niraj K Jha
Abstract: The global rise in type 2 diabetes underscores the need for scalable and cost-effective screening methods. Current diagnosis requires biochemical assays, which are invasive and costly. Advances in consumer wearables have enabled early explorations of machine learning-based disease detection, but prior studies were limited to controlled settings. We present SweetDeep, a compact neural network trained on physiological and demographic data from 285 (diabetic and non-diabetic) participants in the EU and MENA regions, collected using Samsung Galaxy Watch 7 devices in free-living conditions over six days. Each participant contributed multiple 2-minute sensor recordings per day, totaling approximately 20 recordings per individual. Despite comprising fewer than 3,000 parameters, SweetDeep achieves 82.5% patient-level accuracy (82.1% macro-F1, 79.7% sensitivity, 84.6% specificity) under three-fold cross-validation, with an expected calibration error of 5.5%. Allowing the model to abstain on less than 10% of low-confidence patient predictions yields an accuracy of 84.5% on the remaining patients. These findings demonstrate that combining engineered features with lightweight architectures can support accurate, rapid, and generalizable detection of type 2 diabetes in real-world wearable settings.
Authors: Hongtao Hao, Joseph L. Austerweil
Abstract: Event-based models (EBMs) infer disease progression from cross-sectional data, and standard EBMs assume a single underlying disease per individual. In contrast, mixed pathologies are common in neurodegeneration. We introduce the Joint Progression Model (JPM), a probabilistic framework that treats single-disease trajectories as partial rankings and builds a prior over joint progressions. We study several JPM variants (Pairwise, Bradley-Terry, Plackett-Luce, and Mallows) and analyze three properties: (i) calibration -- whether lower model energy predicts smaller distance to the ground truth ordering; (ii) separation -- the degree to which sampled rankings are distinguishable from random permutations; and (iii) sharpness -- the stability of sampled aggregate rankings. All variants are calibrated, and all achieve near-perfect separation; sharpness varies by variant and is well-predicted by simple features of the input partial rankings (number and length of rankings, conflict, and overlap). In synthetic experiments, JPM improves ordering accuracy by roughly 21 percent over a strong EBM baseline (SA-EBM) that treats the joint disease as a single condition. Finally, using NACC, we find that the Mallows variant of JPM and the baseline model (SA-EBM) have results that are more consistent with prior literature on the possible disease progression of the mixed pathology of AD and VaD.
Authors: Juan Diego Toscano, Daniel T. Chen, George Em Karniadakis
Abstract: Bridging the gap between theoretical conceptualization and computational implementation is a major bottleneck in Scientific Computing (SciC) and Scientific Machine Learning (SciML). We introduce ATHENA (Agentic Team for Hierarchical Evolutionary Numerical Algorithms), an agentic framework designed as an Autonomous Lab to manage the end-to-end computational research lifecycle. Its core is the HENA loop, a knowledge-driven diagnostic process framed as a Contextual Bandit problem. Acting as an online learner, the system analyzes prior trials to select structural `actions' ($A_n$) from combinatorial spaces guided by expert blueprints (e.g., Universal Approximation, Physics-Informed constraints). These actions are translated into executable code ($S_n$) to generate scientific rewards ($R_n$). ATHENA transcends standard automation: in SciC, it autonomously identifies mathematical symmetries for exact analytical solutions or derives stable numerical solvers where foundation models fail. In SciML, it performs deep diagnosis to tackle ill-posed formulations and combines hybrid symbolic-numeric workflows (e.g., coupling PINNs with FEM) to resolve multiphysics problems. The framework achieves super-human performance, reaching validation errors of $10^{-14}$. Furthermore, collaborative ``human-in-the-loop" intervention allows the system to bridge stability gaps, improving results by an order of magnitude. This paradigm shift focuses from implementation mechanics to methodological innovation, accelerating scientific discovery.
Authors: Antonin Sulc
Abstract: We propose Modal Logical Neural Networks (MLNNs), a neurosymbolic framework that integrates deep learning with the formal semantics of modal logic, enabling reasoning about necessity and possibility. Drawing on Kripke semantics, we introduce specialized neurons for the modal operators $\Box$ and $\Diamond$ that operate over a set of possible worlds, enabling the framework to act as a differentiable ``logical guardrail.'' The architecture is highly flexible: the accessibility relation between worlds can either be fixed by the user to enforce known rules or, as an inductive feature, be parameterized by a neural network. This allows the model to optionally learn the relational structure of a logical system from data while simultaneously performing deductive reasoning within that structure. This versatile construction is designed for flexibility. The entire framework is differentiable from end to end, with learning driven by minimizing a logical contradiction loss. This not only makes the system resilient to inconsistent knowledge but also enables it to learn nonlinear relationships that can help define the logic of a problem space. We illustrate MLNNs on four case studies: grammatical guardrailing, axiomatic detection of the unknown, multi-agent epistemic trust, and detecting constructive deception in natural language negotiation. These experiments demonstrate how enforcing or learning accessibility can increase logical consistency and interpretability without changing the underlying task architecture.
Authors: Xuanxuan Yang, Xiuyang Zhang, Haofeng Chen, Gang Ma, Xiaojie Wang
Abstract: Electrical impedance tomography (EIT) provides an attractive solution for large-area tactile sensing due to its minimal wiring and shape flexibility, but its nonlinear inverse problem often leads to severe artifacts and inaccurate contact reconstruction. This work presents PhyDNN, a physics-driven deep reconstruction framework that embeds the EIT forward model directly into the learning objective. By jointly minimizing the discrepancy between predicted and ground-truth conductivity maps and enforcing consistency with the forward PDE, PhyDNN reduces the black-box nature of deep networks and improves both physical plausibility and generalization. To enable efficient backpropagation, we design a differentiable forward-operator network that accurately approximates the nonlinear EIT response, allowing fast physics-guided training. Extensive simulations and real tactile experiments on a 16-electrode soft sensor show that PhyDNN consistently outperforms NOSER, TV, and standard DNNs in reconstructing contact shape, location, and pressure distribution. PhyDNN yields fewer artifacts, sharper boundaries, and higher metric scores, demonstrating its effectiveness for high-quality tomographic tactile sensing.
Authors: Adil Rasheed, Mikael Aleksander Jansen Shahly, Muhammad Faisal Aftab
Abstract: Compressed sensing enables sparse sampling but relies on generic bases and random measurements, limiting efficiency and reconstruction quality. Optimal sensor placement uses historcal data to design tailored sampling patterns, yet its fixed, linear bases cannot adapt to nonlinear or sample-specific variations. Generative model-based compressed sensing improves reconstruction using deep generative priors but still employs suboptimal random sampling. We propose an adaptive sparse sensing framework that couples a variational autoencoder prior with reinforcement learning to select measurements sequentially. Experiments show that this approach outperforms CS, OSP, and Generative model-based reconstruction from sparse measurements.
Authors: Zhiming Xu, Baile Xu, Jian Zhao, Furao Shen, Suorong Yang
Abstract: Existing class-incremental learning (CIL) approaches based on replay or knowledge distillation are often constrained by forgetting or the stability-plasticity dilemma. Some expansion-based approaches could achieve higher accuracy. However, they always require significant parameter increases. In this paper, we propose a plugin extension paradigm termed the Deployment of extra LoRA Components (DLC) for non-pre-trained CIL scenarios.We treat the feature extractor trained through replay or distillation as a base model with rich knowledge. For each task, we use Low-Rank Adaptation (LoRA) to inject task-specific residuals into the base model's deep layers. During inference, representations with task-specific residuals are aggregated to produce classification predictions. To mitigate interference from non-target LoRA plugins, we introduce a lightweight weighting unit. This unit learns to assign importance scores to different LoRA-tuned representations. Like downloadable contents in software, our method serves as a plug-and-play enhancement that efficiently extends the base methods. Remarkably, on the large-scale ImageNet-100, with merely 4 % of the parameters of a standard ResNet-18, our DLC model achieves a significant 8 % improvement in accuracy, demonstrating exceptional efficiency. Moreover, it could surpass state-of-the-art methods under the fixed memory budget.
Authors: Xun Yuan, Zilong Zhao, Jiayu Li, Aryan Pasikhani, Prosanta Gope, Biplab Sikdar
Abstract: Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models forget specific training data and prevent the generation of sensitive or unwanted content. Current machine unlearning methods for diffusion models are primarily designed for conditional diffusion models and focus on unlearning specific data classes or features. Among these methods, finetuning-based machine unlearning methods are recognized for their efficiency and effectiveness, which update the parameters of pre-trained diffusion models by minimizing carefully designed loss functions. However, in this paper, we propose a novel attack named Diffusion Model Relearning Attack (DiMRA), which can reverse the finetuning-based machine unlearning methods, posing a significant vulnerability of this kind of technique. Without prior knowledge of the unlearning elements, DiMRA optimizes the unlearned diffusion model on an auxiliary dataset to reverse the unlearning, enabling the model to regenerate previously unlearned elements. To mitigate this vulnerability, we propose a novel machine unlearning method for diffusion models, termed as Diffusion Model Unlearning by Memorization (DiMUM). Unlike traditional methods that focus on forgetting, DiMUM memorizes alternative data or features to replace targeted unlearning data or features in order to prevent generating such elements. In our experiments, we demonstrate the effectiveness of DiMRA in reversing state-of-the-art finetuning-based machine unlearning methods for diffusion models, highlighting the need for more robust solutions. We extensively evaluate DiMUM, demonstrating its superior ability to preserve the generative performance of diffusion models while enhancing robustness against DiMRA.
Authors: Florent Forest, Amaury Wei, Olga Fink
Abstract: Time series extrinsic regression (TSER) refers to the task of predicting a continuous target variable from an input time series. It appears in many domains, including healthcare, finance, environmental monitoring, and engineering. In these settings, accurate predictions and trustworthy reasoning are both essential. Although state-of-the-art TSER models achieve strong predictive performance, they typically operate as black boxes, making it difficult to understand which temporal patterns drive their decisions. Post-hoc interpretability techniques, such as feature attribution, aim to to explain how the model arrives at its predictions, but often produce coarse, noisy, or unstable explanations. Recently, inherently interpretable approaches based on concepts, additive decompositions, or symbolic regression, have emerged as promising alternatives. However, these approaches remain limited: they require explicit supervision on the concepts themselves, often cannot capture interactions between time-series features, lack expressiveness for complex temporal patterns, and struggle to scale to high-dimensional multivariate data. To address these limitations, we propose MAGNETS (Mask-and-AGgregate NEtwork for Time Series), an inherently interpretable neural architecture for TSER. MAGNETS learns a compact set of human-understandable concepts without requiring any annotations. Each concept corresponds to a learned, mask-based aggregation over selected input features, explicitly revealing both which features drive predictions and when they matter in the sequence. Predictions are formed as combinations of these learned concepts through a transparent, additive structure, enabling clear insight into the model's decision process.
Authors: Sanjit Dandapanthula, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan, Aaditya Ramdas, Ziv Goldfeld
Abstract: Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating heterogeneous datasets -- tasks ubiquitous in data science and machine learning. Because these frameworks are computationally expensive, large-scale applications often rely on closed-form solutions for Gaussian distributions under quadratic cost. This work provides a comprehensive treatment of Gaussian, quadratic cost OT and inner product GW (IGW) alignment, closing several gaps in the literature to broaden applicability. First, we treat the open problem of IGW alignment between uncentered Gaussians on separable Hilbert spaces by giving a closed-form expression up to a quadratic optimization over unitary operators, for which we derive tight analytic upper and lower bounds. If at least one Gaussian measure is centered, the solution reduces to a fully closed-form expression, which we further extend to an analytic solution for the IGW barycenter between centered Gaussians. We also present a reduction of Gaussian multimarginal OT with pairwise quadratic costs to a tractable optimization problem and provide an efficient algorithm to solve it using a rank-deficiency constraint. To demonstrate utility, we apply our results to knowledge distillation and heterogeneous clustering on synthetic and real-world datasets.
Authors: Thomas Gr\"aupl, Andreas Reisenbauer, Marcel Hecko, Anil Rasouli, Anita Graser, Melitta Dragaschnig, Axel Weissenfeld, Gilles Dejaegere, Mahmoud Sakr
Abstract: This paper presents the VesselEdge system, which leverages federated learning and bandwidth-constrained trajectory compression to enhance maritime situational awareness by extending AIS coverage. VesselEdge transforms vessels into mobile sensors, enabling real-time anomaly detection and efficient data transmission over low-bandwidth connections. The system integrates the M3fed model for federated learning and the BWC-DR-A algorithm for trajectory compression, prioritizing anomalous data. Preliminary results demonstrate the effectiveness of VesselEdge in improving AIS coverage and situational awareness using historical data.
Authors: Matteo Peduto, Qidong Yang, Jonathan Giezendanner, Devis Tuia, Sherrie Wang
Abstract: Accurate marine wind forecasts are essential for safe navigation, ship routing, and energy operations, yet they remain challenging because observations over the ocean are sparse, heterogeneous, and temporally variable. We reformulate wind forecasting as observation-informed correction of a global numerical weather prediction (NWP) model. Rather than forecasting winds directly, we learn local correction patterns by assimilating the latest in-situ observations to adjust the Global Forecast System (GFS) output. We propose a transformer-based deep learning architecture that (i) handles irregular and time-varying observation sets through masking and set-based attention mechanisms, (ii) conditions predictions on recent observation-forecast pairs via cross-attention, and (iii) employs cyclical time embeddings and coordinate-aware location representations to enable single-pass inference at arbitrary spatial coordinates. We evaluate our model over the Atlantic Ocean using observations from the International Comprehensive Ocean-Atmosphere Data Set (ICOADS) as reference. The model reduces GFS 10-meter wind RMSE at all lead times up to 48 hours, achieving 45% improvement at 1-hour lead time and 13% improvement at 48-hour lead time. Spatial analyses reveal the most persistent improvements along coastlines and shipping routes, where observations are most abundant. The tokenized architecture naturally accommodates heterogeneous observing platforms (ships, buoys, tide gauges, and coastal stations) and produces both site-specific predictions and basin-scale gridded products in a single forward pass. These results demonstrate a practical, low-latency post-processing approach that complements NWP by learning to correct systematic forecast errors.
Authors: Julius Lenz
Abstract: Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging) is a multi-stage, context-sensitive, loss-based, and iterative optimization method across layers, neurons, and weight levels that aligns decisions with loss differences and thresholds and prevents harmful updates through rollback. CoGraM is an optimization method that addresses the weaknesses of methods such as Fisher and can significantly improve the merged network.
Authors: Edward C. C. Steele, Dinesh Mane, Emilio Monti, Luis Orus, Rebecca Chantrill-Cheyette, Matthew Couch, Kirstine I. Dale, Simon Eaton, Govindarajan Rangarajan, Amir Majlesi, Steven Ramsdale, Michael Sharpe, Craig Smith, Jonathan Smith, Rebecca Yates, Holly Ellis, Charles Ewen
Abstract: Despite the promising capability of multimodal foundation models, their application to the generation of meteorological products and services remains nascent. To accelerate aspiration and adoption, we explore the novel use of a vision language model for writing the iconic Shipping Forecast text directly from video-encoded gridded weather data. These early results demonstrate promising scalable technological opportunities for enhancing production efficiency and service innovation within the weather enterprise and beyond.
Authors: Jan Saynisch-Wagner, Saran Rajendran Sari
Abstract: This study proposes a method to enhance neural network performance when training data and application data are not very similar, e.g., out of distribution problems, as well as pattern and regime shifts. The method consists of three main steps: 1) Retrain the neural network towards reasonable subsets of the training data set and note down the resulting weight anomalies. 2) Choose reasonable predictors and derive a regression between the predictors and the weight anomalies. 3) Extrapolate the weights, and thereby the neural network, to the application data. We show and discuss this method in three use cases from the climate sciences, which include successful temporal, spatial and cross-domain extrapolations of neural networks.
Authors: Salim Khazem, Houssam Kanso
Abstract: Accurate electricity consumption forecasting is essential for demand management and smart grid operations. This paper introduces a unified deep learning framework that integrates cyclical temporal encoding with hybrid LSTM-CNN architectures to enhance multistep energy forecasting. We systematically transform calendar-based attributes using sine cosine encodings to preserve periodic structure and evaluate their predictive relevance through correlation analysis. To exploit both long-term seasonal effects and short-term local patterns, we employ an ensemble model composed of an LSTM, a CNN, and a meta-learner of MLP regressors specialized for each forecast horizon. Using a one year national consumption dataset, we conduct an extensive experimental study including ablation analyses with and without cyclical encodings and calendar features and comparisons with established baselines from the literature. Results demonstrate consistent improvements across all seven forecast horizons, with our hybrid model achieving lower RMSE and MAE than individual architectures and prior methods. These findings confirm the benefit of combining cyclical temporal representations with complementary deep learning structures. To our knowledge, this is the first work to jointly evaluate temporal encodings, calendar-based features, and hybrid ensemble architectures within a unified short-term energy forecasting framework.
Authors: Alex Ferrando, Xavier Suau, Jordi Gonz\`alez, Pau Rodriguez
Abstract: Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer. DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected. At generation time, DSAS computes context-dependent scaling factors that selectively adjust the strength of any steering method. We also show how DSAS can be jointly optimized end-to-end together with the steering function. When combined with existing steering methods, DSAS consistently improves the Pareto front with respect to steering alone, achieving a better trade-off between toxicity mitigation and utility preservation. We further demonstrate DSAS's generality by applying it to a text-to-image diffusion model, showing how adaptive steering allows the modulation of specific concepts. Finally, DSAS introduces minimal computational overhead while improving interpretability, pinpointing which tokens require steering and by how much.
Authors: Hao-Run Cai, Han-Jia Ye
Abstract: While tabular machine learning has achieved remarkable success, temporal distribution shifts pose significant challenges in real-world deployment, as the relationships between features and labels continuously evolve. Static models assume fixed mappings to ensure generalization, whereas adaptive models may overfit to transient patterns, creating a dilemma between robustness and adaptability. In this paper, we analyze key factors essential for constructing an effective dynamic mapping for temporal tabular data. We discover that evolving feature semantics-particularly objective and subjective meanings-introduce concept drift over time. Crucially, we identify that feature transformation strategies are able to mitigate discrepancies in feature representations across temporal stages. Motivated by these insights, we propose a feature-aware temporal modulation mechanism that conditions feature representations on temporal context, modulating statistical properties such as scale and skewness. By aligning feature semantics across time, our approach achieves a lightweight yet powerful adaptation, effectively balancing generalizability and adaptability. Benchmark evaluations validate the effectiveness of our method in handling temporal shifts in tabular data.
Authors: Mohammad Doost, Mohammad Manthouri
Abstract: We propose a novel QTGNN framework for detecting fraudulent transactions in large-scale financial networks. By integrating quantum embedding, variational graph convolutions, and topological data analysis, QTGNN captures complex transaction dynamics and structural anomalies indicative of fraud. The methodology includes quantum data embedding with entanglement enhancement, variational quantum graph convolutions with non-linear dynamics, extraction of higher-order topological invariants, hybrid quantum-classical anomaly learning with adaptive optimization, and interpretable decision-making via topological attribution. Rigorous convergence guarantees ensure stable training on noisy intermediate-scale quantum (NISQ) devices, while stability of topological signatures provides robust fraud detection. Optimized for NISQ hardware with circuit simplifications and graph sampling, the framework scales to large transaction networks. Simulations on financial datasets, such as PaySim and Elliptic, benchmark QTGNN against classical and quantum baselines, using metrics like ROC-AUC, precision, and false positive rate. An ablation study evaluates the contributions of quantum embeddings, topological features, non-linear channels, and hybrid learning. QTGNN offers a theoretically sound, interpretable, and practical solution for financial fraud detection, bridging quantum machine learning, graph theory, and topological analysis.
Authors: Xuhui Lin, Qiuchen Lu
Abstract: Urban transportation systems face increasing resilience challenges from extreme weather events, but current assessment methods rely on surface-level recovery indicators that miss hidden structural damage. Existing approaches cannot distinguish between true recovery and "false recovery," where traffic metrics normalize, but the underlying system dynamics permanently degrade. To address this, a new physics-constrained Hamiltonian learning algorithm combining "structural irreversibility detection" and "energy landscape reconstruction" has been developed. Our approach extracts low-dimensional state representations, identifies quasi-Hamiltonian structures through physics-constrained optimization, and quantifies structural changes via energy landscape comparison. Analysis of London's extreme rainfall in 2021 demonstrates that while surface indicators were fully recovered, our algorithm detected 64.8\% structural damage missed by traditional monitoring. Our framework provides tools for proactive structural risk assessment, enabling infrastructure investments based on true system health rather than misleading surface metrics.
Authors: Sathya Edamadaka, Soojung Yang, Ju Li, Rafael G\'omez-Bombarelli
Abstract: Machine learning models of vastly different modalities and architectures are being trained to predict the behavior of molecules, materials, and proteins. However, it remains unclear whether they learn similar internal representations of matter. Understanding their latent structure is essential for building scientific foundation models that generalize reliably beyond their training domains. Although representational convergence has been observed in language and vision, its counterpart in the sciences has not been systematically explored. Here, we show that representations learned by nearly sixty scientific models, spanning string-, graph-, 3D atomistic, and protein-based modalities, are highly aligned across a wide range of chemical systems. Models trained on different datasets have highly similar representations of small molecules, and machine learning interatomic potentials converge in representation space as they improve in performance, suggesting that foundation models learn a common underlying representation of physical reality. We then show two distinct regimes of scientific models: on inputs similar to those seen during training, high-performing models align closely and weak models diverge into local sub-optima in representation space; on vastly different structures from those seen during training, nearly all models collapse onto a low-information representation, indicating that today's models remain limited by training data and inductive bias and do not yet encode truly universal structure. Our findings establish representational alignment as a quantitative benchmark for foundation-level generality in scientific models. More broadly, our work can track the emergence of universal representations of matter as models scale, and for selecting and distilling models whose learned representations transfer best across modalities, domains of matter, and scientific tasks.
Authors: Stephen Law, Tao Yang, Nanjiang Chen, Xuhui Lin
Abstract: Urban analytics increasingly relies on AI-driven trajectory analysis, yet current approaches suffer from methodological fragmentation: trajectory learning captures movement patterns but ignores spatial context, while spatial embedding methods encode street networks but miss temporal dynamics. Three gaps persist: (1) lack of joint training that integrates spatial and temporal representations, (2) origin-agnostic treatment that ignores directional asymmetries in navigation ($A \to B \ne B \to A$), and (3) over-reliance on auxiliary data (POIs, imagery) rather than fundamental geometric properties of urban space. We introduce a conditional trajectory encoder that jointly learns spatial and movement representations while preserving origin-dependent asymmetries using geometric features. This framework decomposes urban navigation into shared cognitive patterns and origin-specific spatial narratives, enabling quantitative measurement of cognitive asymmetries across starting locations. Our bidirectional LSTM processes visibility ratio and curvature features conditioned on learnable origin embeddings, decomposing representations into shared urban patterns and origin-specific signatures through contrastive learning. Results from six synthetic cities and real-world validation on Beijing's Xicheng District demonstrate that urban morphology creates systematic cognitive inequalities. This provides urban planners quantitative tools for assessing experiential equity, offers architects insights into layout decisions' cognitive impacts, and enables origin-aware analytics for navigation systems.
Authors: Nir Shlezinger, Santiago Segarra, Yi Zhang, Dvir Avrahami, Zohar Davidov, Tirza Routtenberg, Yonina C. Eldar
Abstract: Optimization methods play a central role in signal processing, serving as the mathematical foundation for inference, estimation, and control. While classical iterative optimization algorithms provide interpretability and theoretical guarantees, they often rely on surrogate objectives, require careful hyperparameter tuning, and exhibit substantial computational latency. Conversely, machine learning (ML ) offers powerful data-driven modeling capabilities but lacks the structure, transparency, and efficiency needed for optimization-driven inference. Deep unfolding has recently emerged as a compelling framework that bridges these two paradigms by systematically transforming iterative optimization algorithms into structured, trainable ML architectures. This article provides a tutorial-style overview of deep unfolding, presenting a unified perspective of methodologies for converting optimization solvers into ML models and highlighting their conceptual, theoretical, and practical implications. We review the foundations of optimization for inference and for learning, introduce four representative design paradigms for deep unfolding, and discuss the distinctive training schemes that arise from their iterative nature. Furthermore, we survey recent theoretical advances that establish convergence and generalization guarantees for unfolded optimizers, and provide comparative qualitative and empirical studies illustrating their relative trade-offs in complexity, interpretability, and robustness.
Authors: Conor McCarthy, Jan Peter van Zandwijk, Marcel Worring, Zeno Geradts
Abstract: Smartphones and smartwatches are ever-present in daily life, and provide a rich source of information on their users' behaviour. In particular, digital traces derived from the phone's embedded movement sensors present an opportunity for a forensic investigator to gain insight into a person's physical activities. In this work, we present a machine learning-based approach to translate digital traces into likelihood ratios (LRs) for different types of physical activities. Evaluating on a new dataset, NFI\_FARED, which contains digital traces from four different types of iPhones labelled with 19 activities, it was found that our approach could produce useful LR systems to distinguish 167 out of a possible 171 activity pairings. The same approach was extended to analyse likelihoods for multiple activities (or groups of activities) simultaneously and create activity timelines to aid in both the early and latter stages of forensic investigations. The dataset and all code required to replicate the results have also been made public to encourage further research on this topic.
Authors: Francesco Vitale, Nicola Mazzocca
Abstract: Clinical pathways are specialized healthcare plans that model patient treatment procedures. They are developed to provide criteria-based progression and standardize patient treatment, thereby improving care, reducing resource use, and accelerating patient recovery. However, manual modeling of these pathways based on clinical guidelines and domain expertise is difficult and may not reflect the actual best practices for different variations or combinations of diseases. We propose a two-phase modeling method using process mining, which extends the knowledge base of clinical pathways by leveraging conformance checking diagnostics. In the first phase, historical data of a given disease is collected to capture treatment in the form of a process model. In the second phase, new data is compared against the reference model to verify conformance. Based on the conformance checking results, the knowledge base can be expanded with more specific models tailored to new variants or disease combinations. We demonstrate our approach using Synthea, a benchmark dataset simulating patient treatments for SARS-CoV-2 infections with varying COVID-19 complications. The results show that our method enables expanding the knowledge base of clinical pathways with sufficient precision, peaking to 95.62% AUC while maintaining an arc-degree simplicity of 67.11%.
Authors: Hanhui Deng, Xinglin Li, Jie Luo, Zhanpeng Jin, Di Wu
Abstract: Electrocardiogram is a useful diagnostic signal that can detect cardiac abnormalities by measuring the electrical activity generated by the heart. Due to its rapid, non-invasive, and richly informative characteristics, ECG has many emerging applications. In this paper, we study novel deep learning technologies to effectively manage and analyse ECG data, with the aim of building a diagnostic model, accurately and quickly, that can substantially reduce the burden on medical workers. Unlike the existing ECG models that exhibit a high misdiagnosis rate, our deep learning approaches can automatically extract the features of ECG data through end-to-end training. Specifically, we first devise EfficientECG, an accurate and lightweight classification model for ECG analysis based on the existing EfficientNet model, which can effectively handle high-frequency long-sequence ECG data with various leading types. On top of that, we next propose a cross-attention-based feature fusion model of EfficientECG for analysing multi-lead ECG data with multiple features (e.g., gender and age). Our evaluations on representative ECG datasets validate the superiority of our model against state-of-the-art works in terms of high precision, multi-feature fusion, and lightweights.
Authors: Tai Nguyen, Phong Le, Andr\'e Biedenkapp, Carola Doerr, Nguyen Dang
Abstract: Dynamic Algorithm Configuration (DAC) studies the efficient identification of control policies for parameterized optimization algorithms. Numerous studies have leveraged the robustness of decision-making in Reinforcement Learning (RL) to address the optimization challenges in algorithm configuration. However, applying RL to DAC is challenging and often requires extensive domain expertise. We conduct a comprehensive study of deep-RL algorithms in DAC through a systematic analysis of controlling the population size parameter of the (1+($\lambda$,$\lambda$))-GA on OneMax instances. Our investigation of DDQN and PPO reveals two fundamental challenges that limit their effectiveness in DAC: scalability degradation and learning instability. We trace these issues to two primary causes: under-exploration and planning horizon coverage, each of which can be effectively addressed through targeted solutions. To address under-exploration, we introduce an adaptive reward shifting mechanism that leverages reward distribution statistics to enhance DDQN agent exploration, eliminating the need for instance-specific hyperparameter tuning and ensuring consistent effectiveness across different problem scales. In dealing with the planning horizon coverage problem, we demonstrate that undiscounted learning effectively resolves it in DDQN, while PPO faces fundamental variance issues that necessitate alternative algorithmic designs. We further analyze the hyperparameter dependencies of PPO, showing that while hyperparameter optimization enhances learning stability, it consistently falls short in identifying effective policies across various configurations. Finally, we demonstrate that DDQN equipped with our adaptive reward shifting strategy achieves performance comparable to theoretically derived policies with vastly improved sample efficiency, outperforming prior DAC approaches by several orders of magnitude.
Authors: Timoth\'ee Chauvin, Erwan Le Merrer, Fran\c{c}ois Ta\"iani, Gilles Tredan
Abstract: When using an LLM through an API provider, users expect the served model to remain consistent over time, a property crucial for the reliability of downstream applications and the reproducibility of research. Existing audit methods are too costly to apply at regular time intervals to the wide range of available LLM APIs. This means that model updates are left largely unmonitored in practice. In this work, we show that while LLM log probabilities (logprobs) are usually non-deterministic, they can still be used as the basis for cost-effective continuous monitoring of LLM APIs. We apply a simple statistical test based on the average value of each token logprob, requesting only a single token of output. This is enough to detect changes as small as one step of fine-tuning, making this approach more sensitive than existing methods while being 1,000x cheaper. We introduce the TinyChange benchmark as a way to measure the sensitivity of audit methods in the context of small, realistic model changes.
Authors: Junlin Chang, Yubo Han, Hnag Yue, John S Thompson, Rongke Liu
Abstract: The widespread adoption of depth sensors has substantially lowered the barrier to point-cloud acquisition. This letter proposes a semantic wireless transmission framework for three dimension (3D) point clouds built on Deep Joint Source - Channel Coding (DeepJSCC). Instead of sending raw features, the transmitter predicts combination weights over a receiver-side semantic orthogonal feature pool, enabling compact representations and robust reconstruction. A folding-based decoder deforms a 2D grid into 3D, enforcing manifold continuity while preserving geometric fidelity. Trained with Chamfer Distance (CD) and an orthogonality regularizer, the system is evaluated on ModelNet40 across varying Signal-to-Noise Ratios (SNRs) and bandwidths. Results show performance on par with SEmantic Point cloud Transmission (SEPT) at high bandwidth and clear gains in bandwidth-constrained regimes, with consistent improvements in both Peak Signal-to-Noise Ratio (PSNR) and CD. Ablation experiments confirm the benefits of orthogonalization and the folding prior.
Authors: Dingwei Zhu, Zhiheng Xi, Shihan Dou, Yuhui Wang, Sixian Li, Junjie Ye, Honglin Guo, Shichun Liu, Chenhao Huang, Yajie Yang, Junlin Shang, Senjie Jin, Ming Zhang, Jiazheng Zhang, Caishuang Huang, Yunke Zhang, Demei Yan, Yuran Wang, Tao Gui
Abstract: Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex and unreliable supervision signals can destabilize training and harm generalization. While existing approaches such as worst-case optimization (e.g., RFQI, CQL) and mean-based methods (e.g., PPO, GRPO) can improve stability, they often overlook generalization and may produce overly conservative policies, leading to uneven performance across diverse real scenarios. To this end, we introduce DVPO (Distributional Value Modeling with Risk-aware Policy Optimization), a new RL framework that combines conditional risk theory with distributional value modeling to better balance robustness and generalization. DVPO learns token-level value distributions to provide fine-grained supervision, and applies an asymmetric risk regularization to shape the distribution tails: it contracts the lower tail to dampen noisy negative deviations, while expanding the upper tail to preserve exploratory diversity. Across extensive experiments and analysis in multi-turn dialogue, math reasoning, and scientific QA, DVPO consistently outperforms PPO, GRPO, and robust Bellman-based PPO under noisy supervision, showing its potential for LLM post-training in the real-world.
Authors: Gaetano Signorelli, Michele Lombardi
Abstract: Decision support systems often rely on solving complex optimization problems that may require to estimate uncertain parameters beforehand. Recent studies have shown how using traditionally trained estimators for this task can lead to suboptimal solutions. Using the actual decision cost as a loss function (called Decision Focused Learning) can address this issue, but with a severe loss of scalability at training time. To address this issue, we propose an acceleration method based on replacing costly loss function evaluations with an efficient surrogate. Unlike previously defined surrogates, our approach relies on unbiased estimators reducing the risk of spurious local optima and can provide information on its local confidence allowing one to switch to a fallback method when needed. Furthermore, the surrogate is designed for a black-box setting, which enables compensating for simplifications in the optimization model and account- ing for recourse actions during cost computation. In our results, the method reduces costly inner solver calls, with a solution quality comparable to other state-of-the-art techniques.
Authors: Danny Hoang, Anandkumar Patel, Ruimen Chen, Rajiv Malhotra, Farhad Imani
Abstract: Smart manufacturing can significantly improve efficiency and reduce energy consumption, yet the energy demands of AI models may offset these gains. This study utilizes in-situ sensing-based prediction of geometric quality in smart machining to compare the energy consumption, accuracy, and speed of common AI models. HyperDimensional Computing (HDC) is introduced as an alternative, achieving accuracy comparable to conventional models while drastically reducing energy consumption, 200$\times$ for training and 175 to 1000$\times$ for inference. Furthermore, HDC reduces training times by 200$\times$ and inference times by 300 to 600$\times$, showcasing its potential for energy-efficient smart manufacturing.
Authors: Haidong Kang, Wei Wu, Hanling Wang
Abstract: Few-shot class incremental learning (FSCIL) is a more realistic and challenging paradigm in continual learning to incrementally learn unseen classes and overcome catastrophic forgetting on base classes with only a few training examples. Previous efforts have primarily centered around studying more effective FSCIL approaches. By contrast, less attention was devoted to thinking the security issues in contributing to FSCIL. This paper aims to provide a holistic study of the impact of attacks on FSCIL. We first derive insights by systematically exploring how human expert-designed attack methods (i.e., PGD, FGSM) affect FSCIL. We find that those methods either fail to attack base classes, or suffer from huge labor costs due to relying on huge expert knowledge. This highlights the need to craft a specialized attack method for FSCIL. Grounded in these insights, in this paper, we propose a simple yet effective ACraft method to automatically steer and discover optimal attack methods targeted at FSCIL by leveraging Large Language Models (LLMs) without human experts. Moreover, to improve the reasoning between LLMs and FSCIL, we introduce a novel Proximal Policy Optimization (PPO) based reinforcement learning to optimize learning, making LLMs generate better attack methods in the next generation by establishing positive feedback. Experiments on mainstream benchmarks show that our ACraft significantly degrades the performance of state-of-the-art FSCIL methods and dramatically beyond human expert-designed attack methods while maintaining the lowest costs of attack.
Authors: Janis Keck (Hannaneh), Lukas Silvester Barth (Hannaneh), Fatemeh (Hannaneh), Fahimi, Parvaneh Joharinad, J\"urgen Jost
Abstract: Fuzzy simplicial sets have become an object of interest in dimensionality reduction and manifold learning, most prominently through their role in UMAP. However, their definition through tools from algebraic topology without a clear probabilistic interpretation detaches them from commonly used theoretical frameworks in those areas. In this work we introduce a framework that explains fuzzy simplicial sets as marginals of probability measures on simplicial sets. In particular, this perspective shows that the fuzzy weights of UMAP arise from a generative model that samples Vietoris-Rips filtrations at random scales, yielding cumulative distribution functions of pairwise distances. More generally, the framework connects fuzzy simplicial sets to probabilistic models on the face poset, clarifies the relation between Kullback-Leibler divergence and fuzzy cross-entropy in this setting, and recovers standard t-norms and t-conorms via Boolean operations on the underlying simplicial sets. We then show how new embedding methods may be derived from this framework and illustrate this on an example where we generalize UMAP using \v{C}ech filtrations with triplet sampling. In summary, this probabilistic viewpoint provides a unified probabilistic theoretical foundation for fuzzy simplicial sets, clarifies the role of UMAP within this framework, and enables the systematic derivation of new dimensionality reduction methods.
Authors: Xiang Rao, Yina Liu, Yuxuan Shen
Abstract: Solving partial differential equations (PDEs) for reservoir seepage is critical for optimizing oil and gas field development and predicting production performance. Traditional numerical methods suffer from mesh-dependent errors and high computational costs, while classical Physics-Informed Neural Networks (PINNs) face bottlenecks in parameter efficiency, high-dimensional expression, and strong nonlinear fitting. To address these limitations, we propose a Discrete Variable (DV)-Circuit Quantum-Classical Physics-Informed Neural Network (QCPINN) and apply it to three typical reservoir seepage models for the first time: the pressure diffusion equation for heterogeneous single-phase flow, the nonlinear Buckley-Leverett (BL) equation for two-phase waterflooding, and the convection-diffusion equation for compositional flow considering adsorption. The QCPINN integrates classical preprocessing/postprocessing networks with a DV quantum core, leveraging quantum superposition and entanglement to enhance high-dimensional feature mapping while embedding physical constraints to ensure solution consistency. We test three quantum circuit topologies (Cascade, Cross-mesh, Alternate) and demonstrate through numerical experiments that QCPINNs achieve high prediction accuracy with fewer parameters than classical PINNs. Specifically, the Alternate topology outperforms others in heterogeneous single-phase flow and two-phase BL equation simulations, while the Cascade topology excels in compositional flow with convection-dispersion-adsorption coupling. Our work verifies the feasibility of QCPINN for reservoir engineering applications, bridging the gap between quantum computing research and industrial practice in oil and gas engineering.
Authors: Michele Alessi, Alessio Ansuini, Alex Rodriguez
Abstract: We introduce Density-Informed VAE (DiVAE), a lightweight, data-driven regularizer that aligns the VAE log-prior probability $\log p_Z(z)$ with a log-density estimated from data. Standard VAEs match latents to a simple prior, overlooking density structure in the data-space. DiVAE encourages the encoder to allocate posterior mass in proportion to data-space density and, when the prior is learnable, nudges the prior toward high-density regions. This is realized by adding a robust, precision-weighted penalty to the ELBO, incurring negligible computational overhead. On synthetic datasets, DiVAE (i) improves distributional alignment of latent log-densities to its ground truth counterpart, (ii) improves prior coverage, and (iii) yields better OOD uncertainty calibration. On MNIST, DiVAE improves alignment of the prior with external estimates of the density, providing better interpretability, and improves OOD detection for learnable priors.
Authors: Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias, Edson Bollis, Lucas Pellicer, Rosimeire Pereira Costa, Anna Helena Reali Costa, Artur Jordao
Abstract: In the vision domain, dataset distillation arises as a technique to condense a large dataset into a smaller synthetic one that exhibits a similar result in the training process. While image data presents an extensive literature of distillation methods, text dataset distillation has fewer works in comparison. Text dataset distillation initially grew as an adaptation of efforts from the vision universe, as the particularities of the modality became clear obstacles, it rose into a separate branch of research. Several milestones mark the development of this area, such as the introduction of methods that use transformer models, the generation of discrete synthetic text, and the scaling to decoder-only models with over 1B parameters. Despite major advances in modern approaches, the field remains in a maturing phase, with room for improvement on benchmarking standardization, approaches to overcome the discrete nature of text, handling complex tasks, and providing explicit examples of real-world applications. In this report, we review past and recent advances in dataset distillation for text, highlighting different distillation strategies, key contributions, and general challenges.
Authors: Franki Nguimatsia Tiofack, Th\'eotime Le Hellard, Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier
Abstract: Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their regularization components. We introduce Guided Flow Policy (GFP), which couples a multi-step flow-matching policy with a distilled one-step actor. The actor directs the flow policy through weighted behavior cloning to focus on cloning high-value actions from the dataset rather than indiscriminately imitating all state-action pairs. In turn, the flow policy constrains the actor to remain aligned with the dataset's best transitions while maximizing the critic. This mutual guidance enables GFP to achieve state-of-the-art performance across 144 state and pixel-based tasks from the OGBench, Minari, and D4RL benchmarks, with substantial gains on suboptimal datasets and challenging tasks. Webpage: https://simple-robotics.github.io/publications/guided-flow-policy/
URLs: https://simple-robotics.github.io/publications/guided-flow-policy/
Authors: Oren Rachmil, Roy Betser, Itay Gershon, Omer Hofman, Nitay Yakoby, Yuval Meron, Idan Yankelev, Asaf Shabtai, Yuval Elovici, Roman Vainshtein
Abstract: Aligning proprietary large language models (LLMs) with internal organizational policies has become an urgent priority as organizations increasingly deploy LLMs in sensitive domains such as legal support, finance, and medical services. Beyond generic safety filters, enterprises require reliable mechanisms to detect policy violations within their regulatory and operational frameworks, where breaches can trigger legal and reputational risks. Existing content moderation frameworks, such as guardrails, remain largely confined to the safety domain and lack the robustness to capture nuanced organizational policies. LLM-as-a-judge and fine-tuning approaches, though flexible, introduce significant latency and lack interpretability. To address these limitations, we propose a training-free and efficient method that treats policy violation detection as an out-of-distribution (OOD) detection problem. Inspired by whitening techniques, we apply a linear transformation to decorrelate the model's hidden activations and standardize them to zero mean and unit variance, yielding near-identity covariance matrix. In this transformed space, we use the Euclidean norm as a compliance score to detect policy violations. The method requires only the policy text and a small number of illustrative samples, which makes it light-weight and easily deployable. On a challenging policy benchmark, our approach achieves state-of-the-art results, surpassing both existing guardrails and fine-tuned reasoning models. This work provides organizations with a practical and statistically grounded framework for policy-aware oversight of LLMs, advancing the broader goal of deployable AI governance. Code is available at: https://tinyurl.com/policy-violation-detection
Authors: Yanlin Chen, Kehua Chen, Yinhai Wang
Abstract: Traffic state estimation (TSE) becomes challenging when probe-vehicle penetration is low and observations are spatially sparse. Pure data-driven methods lack physical explanations and have poor generalization when observed data is sparse. In contrast, physical models have difficulty integrating uncertainties and capturing the real complexity of traffic. To bridge this gap, recent studies have explored combining them by embedding physical structure into Gaussian process. These approaches typically introduce the governing equations as soft constraints through pseudo-observations, enabling the integration of model structure within a variational framework. However, these methods rely heavily on penalty tuning and lack principled uncertainty calibration, which makes them sensitive to model mis-specification. In this work, we address these limitations by presenting a novel Physics-Embedded Gaussian Process (PEGP), designed to integrate domain knowledge with data-driven methods in traffic state estimation. Specifically, we design two multi-output kernels informed by classic traffic flow models, constructed via the explicit application of the linearized differential operator. Experiments on HighD, NGSIM show consistent improvements over non-physics baselines. PEGP-ARZ proves more reliable under sparse observation, while PEGP-LWR achieves lower errors with denser observation. Ablation study further reveals that PEGP-ARZ residuals align closely with physics and yield calibrated, interpretable uncertainty, whereas PEGP-LWR residuals are more orthogonal and produce nearly constant variance fields. This PEGP framework combines physical priors, uncertainty quantification, which can provide reliable support for TSE.
Authors: Connall Garrod, Jonathan P. Keating, Christos Thrampoulidis
Abstract: Cross-entropy (CE) training loss dominates deep learning practice, yet existing theory often relies on simplifications, either replacing it with squared loss or restricting to convex models, that miss essential behavior. CE and squared loss generate fundamentally different dynamics, and convex linear models cannot capture the complexities of non-convex optimization. We provide an in-depth characterization of multi-class CE optimization dynamics beyond the convex regime by analyzing a canonical two-layer linear neural network with standard-basis vectors as inputs: the simplest non-convex extension for which the implicit bias remained unknown. This model coincides with the unconstrained features model used to study neural collapse, making our work the first to prove that gradient flow on CE converges to the neural collapse geometry. We construct an explicit Lyapunov function that establishes global convergence, despite the presence of spurious critical points in the non-convex landscape. A key insight underlying our analysis is an inconspicuous finding: Hadamard Initialization diagonalizes the softmax operator, freezing the singular vectors of the weight matrices and reducing the dynamics entirely to their singular values. This technique opens a pathway for analyzing CE training dynamics well beyond our specific setting considered here.
Authors: Zo\"e Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin, Nicolas Papernot, Shafi Goldwasser
Abstract: Training with differential privacy (DP) provides a guarantee to members in a dataset that they cannot be identified by users of the released model. However, those data providers, and, in general, the public, lack methods to efficiently verify that models trained on their data satisfy DP guarantees. The amount of compute needed to verify DP guarantees for current algorithms scales with the amount of compute required to train the model. In this paper we design the first DP algorithm with near optimal privacy-utility trade-offs but whose DP guarantees can be verified cheaper than training. We focus on DP stochastic convex optimization (DP-SCO), where optimal privacy-utility trade-offs are known. Here we show we can obtain tight privacy-utility trade-offs by privately minimizing a series of regularized objectives and only using the standard DP composition bound. Crucially, this method can be verified with much less compute than training. This leads to the first known DP-SCO algorithm with near optimal privacy-utility whose DP verification scales better than training cost, significantly reducing verification costs on large datasets.
Authors: Hong Yang, Devroop Kar, Qi Yu, Alex Ororbia, Travis Desell
Abstract: Why do state-of-the-art OOD detection methods exhibit catastrophic failure when models are trained on single-domain datasets? We provide the first theoretical explanation for this phenomenon through the lens of information theory. We prove that supervised learning on single-domain data inevitably produces domain feature collapse -- representations where I(x_d; z) = 0, meaning domain-specific information is completely discarded. This is a fundamental consequence of information bottleneck optimization: models trained on single domains (e.g., medical images) learn to rely solely on class-specific features while discarding domain features, leading to catastrophic failure when detecting out-of-domain samples (e.g., achieving only 53% FPR@95 on MNIST). We extend our analysis using Fano's inequality to quantify partial collapse in practical scenarios. To validate our theory, we introduce Domain Bench, a benchmark of single-domain datasets, and demonstrate that preserving I(x_d; z) > 0 through domain filtering (using pretrained representations) resolves the failure mode. While domain filtering itself is conceptually straightforward, its effectiveness provides strong empirical evidence for our information-theoretic framework. Our work explains a puzzling empirical phenomenon, reveals fundamental limitations of supervised learning in narrow domains, and has broader implications for transfer learning and when to fine-tune versus freeze pretrained models.
Authors: Yizhou Zhao, Zhiwei Steven Wu, Adam Block
Abstract: Watermarking aims to embed hidden signals in generated text that can be reliably detected when given access to a secret key. Open-weight language models pose acute challenges for such watermarking schemes because the inference-time interventions that dominate contemporary approaches cannot be enforced once model weights are public. Existing watermaking techniques for open-weight models, such as the recently proposed GaussMark, typically rely on small modifications to model weights, which can yield signals detectable to those equipped with a secret key, but achieving detection power comparable to inference-time watermarks generally requires weight perturbations that noticeably reduce generation quality. We introduce MarkTune, a theoretically principled, on-policy fine-tuning framework that treats the GaussMark signal as a reward while simultaneously regularizing against degradation in text quality. We derive MarkTune as an improvement on GaussMark and demonstrate that MarkTune consistently improves the quality-detectability trade-off over GaussMark by steering finer-grained, watermark-aware weight updates within the model's representation space while preserving generation quality. Empirically, we show that MarkTune pushes the quality-detectability frontier of GaussMark close to that of inference-time watermarking, remains robust to paraphrasing and fine-tuning attacks, and exhibits strong generalization: a model fine-tuned on one dataset retains substantial watermark detection power on unseen datasets. Together, these results establish MarkTune as a general strategy for embedding robust, high-quality watermarks into open-weight LMs.
Authors: Paul Wilson, Fabio Zanasi, George Constantinides
Abstract: Modern deep learning models require immense computational resources, motivating research into low-precision training. Quantised training addresses this by representing training components in low-bit integers, but typically relies on discretising real-valued updates. We introduce an alternative approach where the update rule itself is discrete, avoiding the quantisation of continuous updates by design. We establish convergence guarantees for a general class of such discrete schemes, and present a multinomial update rule as a concrete example, supported by empirical evaluation. This perspective opens new avenues for efficient training, particularly for models with inherently discrete structure.
Authors: Florian Bordes, Candace Ross, Justine T Kao, Evangelia Spiliopoulou, Adina Williams
Abstract: The rapid proliferation of benchmarks has created significant challenges in reproducibility, transparency, and informed decision-making. However, unlike datasets and models -- which benefit from structured documentation frameworks like Datasheets and Model Cards -- evaluation methodologies lack systematic documentation standards. We introduce Eval Factsheets, a structured, descriptive framework for documenting AI system evaluations through a comprehensive taxonomy and questionnaire-based approach. Our framework organizes evaluation characteristics across five fundamental dimensions: Context (Who made the evaluation and when?), Scope (What does it evaluate?), Structure (With what the evaluation is built?), Method (How does it work?) and Alignment (In what ways is it reliable/valid/robust?). We implement this taxonomy as a practical questionnaire spanning five sections with mandatory and recommended documentation elements. Through case studies on multiple benchmarks, we demonstrate that Eval Factsheets effectively captures diverse evaluation paradigms -- from traditional benchmarks to LLM-as-judge methodologies -- while maintaining consistency and comparability. We hope Eval Factsheets are incorporated into both existing and newly released evaluation frameworks and lead to more transparency and reproducibility.
Authors: Ashlesha Gopinath Sawant, Sahil S. Jadhav, Vidhan R. Jain, Shriraj S. Jagtap, Prachi Jadhav, Soham Jadhav, Ichha Raina
Abstract: In todays increasing world, it is very important to have good hailing services like Ola, Uber, and Rapido as it is very essential for our daily transportation. Users often face difficulties in choosing the most appropriate and efficient ride that would lead to both cost-effective and would take us to our destination in less time. This project provides you with the web application that helps you to select the most beneficial ride for you by providing users with the fare comparison between Ola, Uber, Rapido for the destination entered by the user. The backend is use to fetch the data, providing users with the fare comparison for the ride and finally providing with the best option using Python. This research paper also addresses the problem and challenges faced in accessing the data using APIs, Android Studios emulator, Appium and location comparison. Thus, the aim of the project is to provide transparency to the users in ride-hailing services and increase efficiency and provide users with better experience.
Authors: Jonathan Berant, Maximillian Chen, Adam Fisch, Reza Aghajani, Fantine Huot, Mirella Lapata, Jacob Eisenstein
Abstract: To handle underspecified or ambiguous queries, AI assistants need a policy for managing their uncertainty to determine (a) when to guess the user intent and answer directly, (b) when to enumerate and answer multiple possible intents, and (c) when to ask a clarifying question. However, such policies are contextually dependent on factors such as user preferences or modality. For example, enumerating multiple possible user intentions is cumbersome on small screens or in a voice setting. In this work, we propose to train steerable policies for managing this uncertainty using self-play. Given two agents, one simulating a user and the other an AI assistant, we generate conversations where the user issues a potentially ambiguous query, and the assistant needs to determine how to respond. Importantly, the model takes as input the numerical cost of each clarification question, and each generated word, and is asked to take the action that will maximize its final reward, which is the cost-penalized accuracy. We use Reinforced Self-Training (ReST) to train our model to achieve high reward and show this leads to a steerable policy that changes its behavior predictably conditioned on the provided costs, leading to higher reward and accuracy. Moreover, our procedure also generalizes to numerical cost values that were unobserved at training time.
Authors: Andr\'e de Souza Loureiro, Jorge Valverde-Rebaza, Julieta Noguez, David Escarcega, Ricardo Marcacini
Abstract: Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the Multi-Layered Self-Reflection with Auto-Prompting (MAPS) framework, a novel approach designed to enhance multi-step mathematical reasoning in LLMs by integrating techniques such as Chain of Thought (CoT), Self-Reflection, and Auto-Prompting. Unlike traditional static prompting methods, MAPS employs an iterative refinement process. Initially, the model generates a solution using CoT prompting. When errors are detected, an adaptive self-reflection mechanism identifies and analyzes them, generating tailored prompts to guide corrections. These dynamically adjusted prompts enable the model to iteratively refine its reasoning. Experiments on four well-established benchmarks across multiple LLMs show that MAPS significantly outperforms standard CoT and achieves competitive results with reasoning-optimized models. In addition, MAPS enables general-purpose LLMs to reach performance levels comparable to specialized reasoning models. While deeper reflection layers improve accuracy, they also increase token usage and costs. To balance this trade-off, MAPS strategically limits reflection depth, ensuring an optimal balance between cost and reasoning performance.
Authors: Samih Fadli
Abstract: Large language model safety is usually assessed with static benchmarks, but key failures are dynamic: value drift under distribution shift, jailbreak attacks, and slow degradation of alignment in deployment. Building on a recent Second Law of Intelligence that treats ethical entropy as a state variable which tends to increase unless countered by alignment work, we make this framework operational for large language models. We define a five-way behavioral taxonomy, train a classifier to estimate ethical entropy S(t) from model transcripts, and measure entropy dynamics for base and instruction-tuned variants of four frontier models across stress tests. Base models show sustained entropy growth, while tuned variants suppress drift and reduce ethical entropy by roughly eighty percent. From these trajectories we estimate an effective alignment work rate gamma_eff and embed S(t) and gamma_eff in a monitoring pipeline that raises alerts when entropy drift exceeds a stability threshold, enabling run-time oversight of value drift.
Authors: Austin Spizzirri
Abstract: I argue that AI alignment should be reconceived as architecting syntropic, reasons-responsive agents through process-based, multi-agent, developmental mechanisms rather than encoding fixed human value content. The paper makes three philosophical contributions. First, I articulate the ``specification trap'' argument demonstrating why content-based value specification appears structurally unstable due to the conjunction of the is-ought gap, value pluralism, and the extended frame problem. Second, I propose syntropy -- the recursive reduction of mutual uncertainty between agents through state alignment -- as an information-theoretic framework for understanding multi-agent alignment dynamics. Third, I establish a functional distinction between genuine and simulated moral capacity grounded in compatibilist theories of guidance control, coupled with an embodied experimental paradigm and verification regime providing operational criteria independent of phenomenological claims. This paper represents the philosophical component of a broader research program whose empirical validation is being developed in a separate project currently in preparation. While the framework generates specific, falsifiable predictions about value emergence and moral agency in artificial systems, empirical validation remains pending.
Authors: Hao Zeng
Abstract: We prove an impossibility result for conditional Probably Approximately Correct (PAC)-efficient reasoning in large language models. While recent work has established marginal PAC efficiency guarantees for composite models that switch between expensive expert models and cheaper fast models, we show that conditional (pointwise) guarantees are impossible in the distribution-free setting. Specifically, for non-atomic input spaces, any algorithm achieving conditional PAC efficiency must be trivial in the sense that it defers to the expert model with probability at least $1-\alpha$ for almost every input.
Authors: Anudeex Shetty
Abstract: Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering feature extraction capabilities (in the form of text embeddings) that benefit downstream natural language processing tasks. However, prior research has demonstrated that EaaS is vulnerable to imitation attacks, where an attacker clones the service's model in a black-box manner without access to the model's internal workings. In response, watermarks have been added to the text embeddings to protect the intellectual property of EaaS providers by allowing them to check for model ownership. This thesis focuses on defending against imitation attacks by investigating EaaS watermarks. To achieve this goal, we unveil novel attacks and propose and validate new watermarking techniques. Firstly, we show that existing EaaS watermarks can be removed through paraphrasing the input text when attackers clone the model during imitation attacks. Our study illustrates that paraphrasing can effectively bypass current state-of-the-art EaaS watermarks across various attack setups (including different paraphrasing techniques and models) and datasets in most instances. This demonstrates a new vulnerability in recent EaaS watermarking techniques. Subsequently, as a countermeasure, we propose a novel watermarking technique, WET (Watermarking EaaS with Linear Transformation), which employs linear transformation of the embeddings. Watermark verification is conducted by applying a reverse transformation and comparing the similarity between recovered and original embeddings. We demonstrate its robustness against paraphrasing attacks with near-perfect verifiability. We conduct detailed ablation studies to assess the significance of each component and hyperparameter in WET.
Authors: Zhewen Hou, Jiajin Sun, Subashree Venkatasubramanian, Peter Jin, Shuolin Li, Tian Zheng
Abstract: Machine learning (ML) has shown significant promise in studying complex geophysical dynamical systems, including turbulence and climate processes. Such systems often display sensitive dependence on initial conditions, reflected in positive Lyapunov exponents, where even small perturbations in short-term forecasts can lead to large deviations in long-term outcomes. Thus, meaningful inference requires not only accurate short-term predictions, but also consistency with the system's long-term attractor that is captured by the marginal distribution of state variables. Existing approaches attempt to address this challenge by incorporating spatial and temporal dependence, but these strategies become impractical when data are extremely sparse. In this work, we show that prior knowledge of marginal distributions offers valuable complementary information to short-term observations, motivating a distribution-informed learning framework. We introduce a calibration algorithm based on normalization and the Kernelized Stein Discrepancy (KSD) to enhance ML predictions. The method here employs KSD within a reproducing kernel Hilbert space to calibrate model outputs, improving their fidelity to known physical distributions. This not only sharpens pointwise predictions but also enforces consistency with non-local statistical structures rooted in physical principles. Through synthetic experiments-spanning offline climatological CO2 fluxes and online quasi-geostrophic flow simulations-we demonstrate the robustness and broad utility of the proposed framework.
Authors: Kai Williams, Rohan Subramani, Francis Rhys Ward
Abstract: Frontier AI developers may fail to align or control highly-capable AI agents. In many cases, it could be useful to have emergency shutdown mechanisms which effectively prevent misaligned agents from carrying out harmful actions in the world. We introduce password-activated shutdown protocols (PAS protocols) -- methods for designing frontier agents to implement a safe shutdown protocol when given a password. We motivate PAS protocols by describing intuitive use-cases in which they mitigate risks from misaligned systems that subvert other control efforts, for instance, by disabling automated monitors or self-exfiltrating to external data centres. PAS protocols supplement other safety efforts, such as alignment fine-tuning or monitoring, contributing to defence-in-depth against AI risk. We provide a concrete demonstration in SHADE-Arena, a benchmark for AI monitoring and subversion capabilities, in which PAS protocols supplement monitoring to increase safety with little cost to performance. Next, PAS protocols should be robust to malicious actors who want to bypass shutdown. Therefore, we conduct a red-team blue-team game between the developers (blue-team), who must implement a robust PAS protocol, and a red-team trying to subvert the protocol. We conduct experiments in a code-generation setting, finding that there are effective strategies for the red-team, such as using another model to filter inputs, or fine-tuning the model to prevent shutdown behaviour. We then outline key challenges to implementing PAS protocols in real-life systems, including: security considerations of the password and decisions regarding when, and in which systems, to use them. PAS protocols are an intuitive mechanism for increasing the safety of frontier AI. We encourage developers to consider implementing PAS protocols prior to internal deployment of particularly dangerous systems to reduce loss-of-control risks.
Authors: Tom\'as Villalba-Ferreiro, Eduardo Mosqueira-Rey, Diego Alvarez-Estevez
Abstract: This study explores the performance of Quantum Support Vector Classifiers (QSVCs) and Quantum Neural Networks (QNNs) in comparison to classical models for machine learning tasks. By evaluating these models on the Iris and MNIST-PCA datasets, we find that quantum models tend to outperform classical approaches as the problem complexity increases. While QSVCs generally provide more consistent results, QNNs exhibit superior performance in higher-complexity tasks due to their increased quantum load. Additionally, we analyze the impact of hyperparameter tuning, showing that feature maps and ansatz configurations significantly influence model accuracy. We also compare the PennyLane and Qiskit frameworks, concluding that Qiskit provides better optimization and efficiency for our implementation. These findings highlight the potential of Quantum Machine Learning (QML) for complex classification problems and provide insights into model selection and optimization strategies
Authors: Adeela Bashir, The Anh han, Zia Ush Shamszaman
Abstract: The integration of large language models (LLMs) into healthcare IoT systems promises faster decisions and improved medical support. LLMs are also deployed as multi-agent teams to assist AI doctors by debating, voting, or advising on decisions. However, when multiple assistant agents interact, coordinated adversaries can collude to create false consensus, pushing an AI doctor toward harmful prescriptions. We develop an experimental framework with scripted and unscripted doctor agents, adversarial assistants, and a verifier agent that checks decisions against clinical guidelines. Using 50 representative clinical questions, we find that collusion drives the Attack Success Rate (ASR) and Harmful Recommendation Rates (HRR) up to 100% in unprotected systems. In contrast, the verifier agent restores 100% accuracy by blocking adversarial consensus. This work provides the first systematic evidence of collusion risk in AI healthcare and demonstrates a practical, lightweight defence that ensures guideline fidelity.
Authors: Benoit L. Marteau, Andrew Hornback, Shaun Q. Tan, Christian Lowson, Jason Woloff, May D. Wang
Abstract: The rapid growth of Artificial Intelligence (AI) in healthcare has sparked interest in Trustworthy AI and AI Implementation Science, both of which are essential for accelerating clinical adoption. However, strict regulations, gaps between research and clinical settings, and challenges in evaluating AI systems continue to hinder real-world implementation. This study presents an AI implementation case study within Shriners Childrens (SC), a large multisite pediatric system, showcasing the modernization of SCs Research Data Warehouse (RDW) to OMOP CDM v5.4 within a secure Microsoft Fabric environment. We introduce a Python-based data quality assessment tool compatible with SCs infrastructure, extending OHDsi's R/Java-based Data Quality Dashboard (DQD) and integrating Trustworthy AI principles using the METRIC framework. This extension enhances data quality evaluation by addressing informative missingness, redundancy, timeliness, and distributional consistency. We also compare systematic and case-specific AI implementation strategies for Craniofacial Microsomia (CFM) using the FHIR standard. Our contributions include a real-world evaluation of AI implementations, integration of Trustworthy AI principles into data quality assessment, and insights into hybrid implementation strategies that blend systematic infrastructure with use-case-driven approaches to advance AI in healthcare.
Authors: Haribandhu Jena, Jyotirmaya Shivottam, Subhankar Mishra
Abstract: Graph Neural Networks (GNNs) have become indispensable in critical domains such as drug discovery, social network analysis, and recommendation systems, yet their black-box nature hinders deployment in scenarios requiring transparency and accountability. While Shapley value-based methods offer mathematically principled explanations by quantifying each component's contribution to predictions, computing exact values requires evaluating $2^n$ coalitions (or aggregating over $n!$ permutations), which is intractable for real-world graphs. Existing approximation strategies sacrifice either fidelity or efficiency, limiting their practical utility. We introduce QGShap, a quantum computing approach that leverages amplitude amplification to achieve quadratic speedups in coalition evaluation while maintaining exact Shapley computation. Unlike classical sampling or surrogate methods, our approach provides fully faithful explanations without approximation trade-offs for tractable graph sizes. We conduct empirical evaluations on synthetic graph datasets, demonstrating that QGShap achieves consistently high fidelity and explanation accuracy, matching or exceeding the performance of classical methods across all evaluation metrics. These results collectively demonstrate that QGShap not only preserves exact Shapley faithfulness but also delivers interpretable, stable, and structurally consistent explanations that align with the underlying graph reasoning of GNNs. The implementation of QGShap is available at https://github.com/smlab-niser/qgshap.
Authors: Zhenglong Chen, Zhao Zhang, Xia Yan, Jiayu Zhai, Piyang Liu, Kai Zhang
Abstract: This study proposes a new discrete neural operator for surrogate modeling of transient Darcy flow fields in heterogeneous porous media with random parameters. The new method integrates temporal encoding, operator learning and UNet to approximate the mapping between vector spaces of random parameter and spatiotemporal flow fields. The new discrete neural operator can achieve higher prediction accuracy than the SOTA attention-residual-UNet structure. Derived from the finite volume method, the transmissibility matrices rather than permeability is adopted as the inputs of surrogates to enhance the prediction accuracy further. To increase sampling efficiency, a generative latent space adaptive sampling method is developed employing the Gaussian mixture model for density estimation of generalization error. Validation is conducted on test cases of 2D/3D single- and two-phase Darcy flow field prediction. Results reveal consistent enhancement in prediction accuracy given limited training set.
Authors: Yasser Taha, Gr\'egoire Montavon, Nils K\"orber
Abstract: Modern deep learning faces significant challenges with noisy labels, class ambiguity, as well as the need to robustly reject out-of-distribution or corrupted samples. In this work, we propose a unified framework based on the concept of a "drainage node'' which we add at the output of the network. The node serves to reallocate probability mass toward uncertainty, while preserving desirable properties such as end-to-end training and differentiability. This mechanism provides a natural escape route for highly ambiguous, anomalous, or noisy samples, particularly relevant for instance-dependent and asymmetric label noise. In systematic experiments involving the addition of varying proportions of instance-dependent noise or asymmetric noise to CIFAR-10/100 labels, our drainage formulation achieves an accuracy increase of up to 9\% over existing approaches in the high-noise regime. Our results on real-world datasets, such as mini-WebVision, mini-ImageNet and Clothing-1M, match or surpass existing state-of-the-art methods. Qualitative analysis reveals a denoising effect, where the drainage neuron consistently absorbs corrupt, mislabeled, or outlier data, leading to more stable decision boundaries. Furthermore, our drainage formulation enables applications well beyond classification, with immediate benefits for web-scale, semi-supervised dataset cleaning, and open-set applications.
Authors: Yulong Dong, Christopher Kang, Murphy Yuezhen Niu
Abstract: Analog quantum simulators can directly emulate time-dependent Hamiltonian dynamics, enabling the exploration of diverse physical phenomena such as phase transitions, quench dynamics, and non-equilibrium processes. Realizing accurate analog simulations requires high-fidelity time-dependent pulse control, yet existing calibration schemes are tailored to digital gate characterization and cannot be readily extended to learn continuous pulse trajectories. We present a characterization algorithm for in situ learning of pulse trajectories by extending the Quantum Signal Processing (QSP) framework to analyze time-dependent pulses. By combining QSP with a logical-level analog-digital mapping paradigm, our method reconstructs a smooth pulse directly from queries of the time-ordered propagator, without requiring mid-circuit measurements or additional evolution. Unlike conventional Trotterization-based methods, our approach avoids unscalable performance degradation arising from accumulated local truncation errors as the logical-level segmentation increases. Through rigorous theoretical analysis and extensive numerical simulations, we demonstrate that our method achieves high accuracy with strong efficiency and robustness against SPAM as well as depolarizing errors, providing a lightweight and optimal validation protocol for analog quantum simulators capable of detecting major hardware faults.
Authors: Johannes Gaber, Meshal Alharbi, Daniele Gammelli, Gioele Zardini
Abstract: Large robot fleets are now common in warehouses and other logistics settings, where small control gains translate into large operational impacts. In this article, we address task scheduling for lifelong Multi-Agent Pickup-and-Delivery (MAPD) and propose a hybrid method that couples learning-based global guidance with lightweight optimization. A graph neural network policy trained via reinforcement learning outputs a desired distribution of free agents over an aggregated warehouse graph. This signal is converted into region-to-region rebalancing through a minimum-cost flow, and finalized by small, local assignment problems, preserving accuracy while keeping per-step latency within a 1 s compute budget. On congested warehouse benchmarks from the League of Robot Runners (LRR) with up to 500 agents, our approach improves throughput by up to 10% over the 2024 winning scheduler while maintaining real-time execution. The results indicate that coupling graph-structured learned guidance with tractable solvers reduces congestion and yields a practical, scalable blueprint for high-throughput scheduling in large fleets.
Authors: Stylianos Saroglou, Konstantinos Diamantaras, Francesco Preta, Marina Delianidi, Apostolos Benisis, Christian Johannes Meyer
Abstract: This study investigates the potential of language models to improve the classification of labor market information by linking job vacancy texts to two major European frameworks: the European Skills, Competences, Qualifications and Occupations (ESCO) taxonomy and the European Qualifications Framework (EQF). We examine and compare two prominent methodologies from the literature: Sentence Linking and Entity Linking. In support of ongoing research, we release an open-source tool, incorporating these two methodologies, designed to facilitate further work on labor classification and employment discourse. To move beyond surface-level skill extraction, we introduce two annotated datasets specifically aimed at evaluating how occupations and qualifications are represented within job vacancy texts. Additionally, we examine different ways to utilize generative large language models for this task. Our findings contribute to advancing the state of the art in job entity extraction and offer computational infrastructure for examining work, skills, and labor market narratives in a digitally mediated economy. Our code is made publicly available: https://github.com/tabiya-tech/tabiya-livelihoods-classifier
URLs: https://github.com/tabiya-tech/tabiya-livelihoods-classifier
Authors: Tanishq Patil, Snigdha Sen, Malwina Molendowska, Kieran G. Foley, Fabrizio Fasano, Mara Cercignani, Marco Palombo, Paddy J. Slator, Eleftheria Panagiotaki
Abstract: Diffusion MRI (dMRI) enables non-invasive assessment of prostate microstructure but conventional metrics such as the Apparent Diffusion Coefficient in multiparametric MRI lack specificity to underlying histology. Integrating dMRI with the compartment-based biophysical VERDICT (Vascular, Extracellular, and Restricted Diffusion for Cytometry in Tumours) framework offers richer microstructural insights, though clinical gradient systems (40-80 mT/m) suffer from poor signal-to-noise ratio (SNR) at stronger diffusion weightings due to prolonged echo times. Ultra-strong gradients (up to 300 mT/m) can mitigate these limitations by improving SNR and contrast-to-noise ratios (CNR) but their adoption has until recently been limited to research environments due to challenges with peripheral nerve stimulation thresholds and gradient non-uniformity. This study investigates whether physics-informed self-supervised VERDICT (ssVERDICT) fitting applied to ultra-strong gradients enhances prostate cancer characterization relative to current clinical acquisitions. We developed enhanced ssVERDICT fitting approaches using dense multilayer perceptron (Dense MLP) and convolutional U-Net architectures, benchmarking them against non-linear least-squares (NLLS) fitting and Diffusion Kurtosis Imaging across clinical- to ultra-strong gradient systems. Dense ssVERDICT at ultra-strong gradient notably outperformed NLLS VERDICT, boosting median CNR by 47%, cutting inter-patient Coefficient of Variation by 52%, and reducing pooled f_ic variation by 50%. Overall, it delivered the highest CNR, the most stable parameter estimates, and the clearest tumour-normal contrast compared with conventional methods and clinical gradient systems. These findings highlight the potential of advanced gradient systems and deep learning-based modelling to improve non-invasive prostate cancer characterization and reduce unnecessary biopsies.
Authors: Pangpang Liu, Junwei Lu, Will Wei Sun
Abstract: We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of model-generated answers and their preferences are used to train a reward model. However, human feedback is inherently heterogeneous, creating significant challenges for reliable reward learning. To address this, we adopt a heterogeneous preference framework that jointly models the latent reward of answers and human rationality. This leads to a challenging biconvex optimization problem, which we solve via an alternating gradient descent algorithm. We establish theoretical guarantees for the resulting estimator, including its convergence and asymptotic distribution. These results enable the construction of confidence intervals for reward estimates. Leveraging these uncertainty quantification results, we conduct valid statistical comparisons between rewards and incorporate uncertainty into the best-of-$N$ (BoN) policy framework. Extensive simulations demonstrate the effectiveness of our method, and applications to real LLM data highlight the practical value of accounting for uncertainty in reward modeling for LLM alignment.
Authors: Jingkang Wang, Henry Che, Yun Chen, Ze Yang, Lily Goli, Sivabalan Manivasagam, Raquel Urtasun
Abstract: Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. While recent differentiable rendering methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have achieved impressive photorealistic reconstruction, they suffer from scalability limitations and require annotations to decouple actor motion. Existing self-supervised methods attempt to eliminate explicit annotations by leveraging motion cues and geometric priors, yet they remain constrained by per-scene optimization and sensitivity to hyperparameter tuning. In this paper, we introduce Flux4D, a simple and scalable framework for 4D reconstruction of large-scale dynamic scenes. Flux4D directly predicts 3D Gaussians and their motion dynamics to reconstruct sensor observations in a fully unsupervised manner. By adopting only photometric losses and enforcing an "as static as possible" regularization, Flux4D learns to decompose dynamic elements directly from raw data without requiring pre-trained supervised models or foundational priors simply by training across many scenes. Our approach enables efficient reconstruction of dynamic scenes within seconds, scales effectively to large datasets, and generalizes well to unseen environments, including rare and unknown objects. Experiments on outdoor driving datasets show Flux4D significantly outperforms existing methods in scalability, generalization, and reconstruction quality.
Authors: Christophe Andrieu, Nicolas Chopin, Ettore Fincato, Mathieu Gerber
Abstract: We investigate the convergence properties of a class of iterative algorithms designed to minimize a potentially non-smooth and noisy objective function, which may be algebraically intractable and whose values may be obtained as the output of a black box. The algorithms considered can be cast under the umbrella of a generalised gradient descent recursion, where the gradient is that of a smooth approximation of the objective function. The framework we develop includes as special cases model-based and mollification methods, two classical approaches to zero-th order optimisation. The convergence results are obtained under very weak assumptions on the regularity of the objective function and involve a trade-off between the degree of smoothing and size of the steps taken in the parameter updates. As expected, additional assumptions are required in the stochastic case. We illustrate the relevance of these algorithms and our convergence results through a challenging classification example from machine learning.
Authors: Jean Pachebat, Giovanni Conforti, Alain Durmus, Yazid Janati
Abstract: We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $\exp(\lambda r)$ into $N$ sequential smaller tilts, each admitting a tractable score update via first-order Taylor expansion. This requires only forward evaluations of the reward function and avoids backpropagating through sampling chains. We validate on a two-dimensional Gaussian mixture with linear reward, where the exact tilted distribution is available in closed form.
Authors: Natalia Ponomareva, Zheng Xu, H. Brendan McMahan, Peter Kairouz, Lucas Rosenblatt, Vincent Cohen-Addad, Crist\'obal Guzm\'an, Ryan McKenna, Galen Andrew, Alex Bie, Da Yu, Alex Kurakin, Morteza Zadimoghaddam, Sergei Vassilvitskii, Andreas Terzis
Abstract: High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated data will soon have been used. Additionally, publicly available data often is not representative of users of a particular system -- for example, a research speech dataset of contractors interacting with an AI assistant will likely be more homogeneous, well articulated and self-censored than real world commands that end users will issue. Therefore unlocking high-quality data grounded in real user interactions is of vital interest. However, the direct use of user data comes with significant privacy risks. Differential Privacy (DP) is a well established framework for reasoning about and limiting information leakage, and is a gold standard for protecting user privacy. The focus of this work, \emph{Differentially Private Synthetic data}, refers to synthetic data that preserves the overall trends of source data,, while providing strong privacy guarantees to individuals that contributed to the source dataset. DP synthetic data can unlock the value of datasets that have previously been inaccessible due to privacy concerns and can replace the use of sensitive datasets that previously have only had rudimentary protections like ad-hoc rule-based anonymization. In this paper we explore the full suite of techniques surrounding DP synthetic data, the types of privacy protections they offer and the state-of-the-art for various modalities (image, tabular, text and decentralized). We outline all the components needed in a system that generates DP synthetic data, from sensitive data handling and preparation, to tracking the use and empirical privacy testing. We hope that work will result in increased adoption of DP synthetic data, spur additional research and increase trust in DP synthetic data approaches.
Authors: Ioannis Gasteratos, Antoine Jacquier, Maud Lemercier, Terry Lyons, Cristopher Salvi
Abstract: We frame novelty detection on path space as a hypothesis testing problem with signature-based test statistics. Using transportation-cost inequalities of Gasteratos and Jacquier (2023), we obtain tail bounds for false positive rates that extend beyond Gaussian measures to laws of RDE solutions with smooth bounded vector fields, yielding estimates of quantiles and p-values. Exploiting the shuffle product, we derive exact formulae for smooth surrogates of conditional value-at-risk (CVaR) in terms of expected signatures, leading to new one-class SVM algorithms optimising smooth CVaR objectives. We then establish lower bounds on type-$\mathrm{II}$ error for alternatives with finite first moment, giving general power bounds when the reference measure and the alternative are absolutely continuous with respect to each other. Finally, we evaluate numerically the type-$\mathrm{I}$ error and statistical power of signature-based test statistic, using synthetic anomalous diffusion data and real-world molecular biology data.
Authors: Enrico Grimaldi, Mario Edoardo Pandolfo, Gabriele D'Acunto, Sergio Barbarossa, Paolo Di Lorenzo
Abstract: Recent advances in AI call for a paradigm shift from bit-centric communication to goal- and semantics-oriented architectures, paving the way for AI-native 6G networks. In this context, we address a key open challenge: enabling heterogeneous AI agents to exchange compressed latent-space representations while mitigating semantic noise and preserving task-relevant meaning. We cast this challenge as learning both the communication topology and the alignment maps that govern information exchange among agents, yielding a learned network sheaf equipped with orthogonal maps. This learning process is further supported by a semantic denoising end compression module that constructs a shared global semantic space and derives sparse, structured representations of each agent's latent space. This corresponds to a nonconvex dictionary learning problem solved iteratively with closed-form updates. Experiments with mutiple AI agents pre-trained on real image data show that the semantic denoising and compression facilitates AI agents alignment and the extraction of semantic clusters, while preserving high accuracy in downstream task. The resulting communication network provides new insights about semantic heterogeneity across agents, highlighting the interpretability of our methodology.
Authors: Mark Moussa, Andre Williams, Seth Roffe, Douglas Morton
Abstract: Rapid and accurate wildfire detection is crucial for emergency response and environmental management. In airborne and spaceborne missions, real-time algorithms must distinguish between no fire, active fire, and post-fire conditions, and estimate fire intensity. Multispectral and hyperspectral thermal imagers provide rich spectral information, but high data dimensionality and limited onboard resources make real-time processing challenging. As wildfires increase in frequency and severity, the need for low-latency and computationally efficient onboard detection methods is critical. We present a systematic evaluation of multiple deep learning architectures, including custom Convolutional Neural Networks (CNNs) and Transformer-based models, for multi-class fire classification. We also introduce PyroFocus, a two-stage pipeline that performs fire classification followed by fire radiative power (FRP) regression or segmentation to reduce inference time and computational cost for onboard deployment. Using data from NASA's MODIS/ASTER Airborne Simulator (MASTER), which is similar to a next-generation fire detection sensor, we compare accuracy, inference latency, and resource efficiency. Experimental results show that the proposed two-stage pipeline achieves strong trade-offs between speed and accuracy, demonstrating significant potential for real-time edge deployment in future wildfire monitoring missions.
Authors: Hsiao-Ying Lu, Kwan-Liu Ma
Abstract: Cancer treatment outcomes are influenced not only by clinical and demographic factors but also by the collaboration of healthcare teams. However, prior work has largely overlooked the potential role of human collaboration in shaping patient survival. This paper presents an applied AI approach to uncovering the impact of healthcare professionals' (HCPs) collaboration-captured through electronic health record (EHR) systems-on cancer patient outcomes. We model EHR-mediated HCP interactions as networks and apply machine learning techniques to detect predictive signals of patient survival embedded in these collaborations. Our models are cross validated to ensure generalizability, and we explain the predictions by identifying key network traits associated with improved outcomes. Importantly, clinical experts and literature validate the relevance of the identified crucial collaboration traits, reinforcing their potential for real-world applications. This work contributes to a practical workflow for leveraging digital traces of collaboration and AI to assess and improve team-based healthcare. The approach is potentially transferable to other domains involving complex collaboration and offers actionable insights to support data-informed interventions in healthcare delivery.
Authors: Kunj Joshi, David A. Smith
Abstract: The current literature on memorization in Natural Language Models, especially Large Language Models (LLMs), poses severe security and privacy risks, as models tend to memorize personally identifying information (PIIs) from training data. We introduce Randomized Masked Fine-Tuning (RMFT), a novel privacy-preserving fine-tuning technique that reduces PII memorization while minimizing performance impact. Using the Enron Email Dataset, we demonstrate that RMFT achieves an 80.81% reduction in Total Extraction Rate and 80.17% reduction in Seen Extraction Rate compared to baseline fine-tuning, outperforming deduplication methods while maintaining only a 5.73% increase in perplexity. We present MaxTER, a Pareto-optimal evaluation framework for assessing privacy-utility tradeoffs, and show the performance of RMFT vs Deduplication by Area Under The Response Curve (AURC) metric.
Authors: Daniel D. Richman, Jessica Karaguesian, Carl-Mikael Suomivuori, Ron O. Dror
Abstract: The function of biomolecules such as proteins depends on their ability to interconvert between a wide range of structures or "conformations." Researchers have endeavored for decades to develop computational methods to predict the distribution of conformations, which is far harder to determine experimentally than a static folded structure. We present ConforMix, an inference-time algorithm that enhances sampling of conformational distributions using a combination of classifier guidance, filtering, and free energy estimation. Our approach upgrades diffusion models -- whether trained for static structure prediction or conformational generation -- to enable more efficient discovery of conformational variability without requiring prior knowledge of major degrees of freedom. ConforMix is orthogonal to improvements in model pretraining and would benefit even a hypothetical model that perfectly reproduced the Boltzmann distribution. Remarkably, when applied to a diffusion model trained for static structure prediction, ConforMix captures structural changes including domain motion, cryptic pocket flexibility, and transporter cycling, while avoiding unphysical states. Case studies of biologically critical proteins demonstrate the scalability, accuracy, and utility of this method.
Authors: Thomas Monninger, Zihan Zhang, Steffen Staab, Sihao Ding
Abstract: Accurate environmental representations are essential for autonomous driving, providing the foundation for safe and efficient navigation. Traditionally, high-definition (HD) maps are providing this representation of the static road infrastructure to the autonomous system a priori. However, because the real world is constantly changing, such maps must be constructed online from on-board sensor data. Navigation-grade standard-definition (SD) maps are widely available, but their resolution is insufficient for direct deployment. Instead, they can be used as coarse prior to guide the online map construction process. We propose NavMapFusion, a diffusion-based framework that performs iterative denoising conditioned on high-fidelity sensor data and on low-fidelity navigation maps. This paper strives to answer: (1) How can coarse, potentially outdated navigation maps guide online map construction? (2) What advantages do diffusion models offer for map fusion? We demonstrate that diffusion-based map construction provides a robust framework for map fusion. Our key insight is that discrepancies between the prior map and online perception naturally correspond to noise within the diffusion process; consistent regions reinforce the map construction, whereas outdated segments are suppressed. On the nuScenes benchmark, NavMapFusion conditioned on coarse road lines from OpenStreetMap data reaches a 21.4% relative improvement on 100 m, and even stronger improvements on larger perception ranges, while maintaining real-time capabilities. By fusing low-fidelity priors with high-fidelity sensor data, the proposed method generates accurate and up-to-date environment representations, guiding towards safer and more reliable autonomous driving. The code is available at https://github.com/tmonnin/navmapfusion
Authors: Garrett G. Wen, Hong Hu, Yue M. Lu, Zhou Fan, Theodor Misiakiewicz
Abstract: A major effort in modern high-dimensional statistics has been devoted to the analysis of linear predictors trained on nonlinear feature embeddings via empirical risk minimization (ERM). Gaussian equivalence theory (GET) has emerged as a powerful universality principle in this context: it states that the behavior of high-dimensional, complex features can be captured by Gaussian surrogates, which are more amenable to analysis. Despite its remarkable successes, numerical experiments show that this equivalence can fail even for simple embeddings -- such as polynomial maps -- under general scaling regimes. We investigate this breakdown in the setting of random feature (RF) models in the quadratic scaling regime, where both the number of features and the sample size grow quadratically with the data dimension. We show that when the target function depends on a low-dimensional projection of the data, such as generalized linear models, GET yields incorrect predictions. To capture the correct asymptotics, we introduce a Conditional Gaussian Equivalent (CGE) model, which can be viewed as appending a low-dimensional non-Gaussian component to an otherwise high-dimensional Gaussian model. This hybrid model retains the tractability of the Gaussian framework and accurately describes RF models in the quadratic scaling regime. We derive sharp asymptotics for the training and test errors in this setting, which continue to agree with numerical simulations even when GET fails. Our analysis combines general results on CLT for Wiener chaos expansions and a careful two-phase Lindeberg swapping argument. Beyond RF models and quadratic scaling, our work hints at a rich landscape of universality phenomena in high-dimensional ERM.
Authors: Faizan Farooq Khan, K J Joseph, Koustava Goswami, Mohamed Elhoseiny, Balaji Vasan Srinivasan
Abstract: Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-Step Layered Design Generation, which tasks a machine learning model with generating a design that adheres to a sequence of instructions from a designer. Leveraging recent advancements in multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic, layered change over its previous state, while being grounded in the instruction. To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches tailored to our new setup demonstrate the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area.
Authors: Yeganeh Ghamary, Victoria Wu, Hooman Vaseli, Christina Luong, Teresa Tsang, Siavash Bigdeli, Purang Abolmaesumi
Abstract: Ejection fraction (EF) is a crucial metric for assessing cardiac function and diagnosing conditions such as heart failure. Traditionally, EF estimation requires manual tracing and domain expertise, making the process time-consuming and subject to interobserver variability. Most current deep learning methods for EF prediction are black-box models with limited transparency, which reduces clinical trust. Some post-hoc explainability methods have been proposed to interpret the decision-making process after the prediction is made. However, these explanations do not guide the model's internal reasoning and therefore offer limited reliability in clinical applications. To address this, we introduce ProtoEFNet, a novel video-based prototype learning model for continuous EF regression. The model learns dynamic spatiotemporal prototypes that capture clinically meaningful cardiac motion patterns. Additionally, the proposed Prototype Angular Separation (PAS) loss enforces discriminative representations across the continuous EF spectrum. Our experiments on the EchonetDynamic dataset show that ProtoEFNet can achieve accuracy on par with its non-interpretable counterpart while providing clinically relevant insight. The ablation study shows that the proposed loss boosts performance with a 2% increase in F1 score from 77.67$\pm$2.68 to 79.64$\pm$2.10. Our source code is available at: https://github.com/DeepRCL/ProtoEF
Authors: Bharat Sharman, Elkafi Hassini
Abstract: The maximum clique problem, a well-known graph-based combinatorial optimization problem, has been addressed through various algorithmic approaches, though systematic analyses of the problem instances remain sparse. This study employs the instance space analysis (ISA) methodology to systematically analyze the instance space of this problem and assess & predict the performance of state-of-the-art (SOTA) algorithms, including exact, heuristic, and graph neural network (GNN)-based methods. A dataset was compiled using graph instances from TWITTER, COLLAB and IMDB-BINARY benchmarks commonly used in graph machine learning research. A set of 33 generic and 2 problem-specific polynomial-time-computable graph-based features, including several spectral properties, was employed for the ISA. A composite performance mea- sure incorporating both solution quality and algorithm runtime was utilized. The comparative analysis demonstrated that the exact algorithm Mixed Order Maximum Clique (MOMC) exhib- ited superior performance across approximately 74.7% of the instance space constituted by the compiled dataset. Gurobi & CliSAT accounted for superior performance in 13.8% and 11% of the instance space, respectively. The ISA-based algorithm performance prediction model run on 34 challenging test instances compiled from the BHOSLIB and DIMACS datasets yielded top-1 and top-2 best performing algorithm prediction accuracies of 88% and 97%, respectively.
Authors: Rhys Newbury, Juyan Zhang, Tin Tran, Hanna Kurniawati, Dana Kuli\'c
Abstract: Understanding and representing the structure of 3D objects in an unsupervised manner remains a core challenge in computer vision and graphics. Most existing unsupervised keypoint methods are not designed for unconditional generative settings, restricting their use in modern 3D generative pipelines; our formulation explicitly bridges this gap. We present an unsupervised framework for learning spatially structured 3D keypoints from point cloud data. These keypoints serve as a compact and interpretable representation that conditions an Elucidated Diffusion Model (EDM) to reconstruct the full shape. The learned keypoints exhibit repeatable spatial structure across object instances and support smooth interpolation in keypoint space, indicating that they capture geometric variation. Our method achieves strong performance across diverse object categories, yielding a 6 percentage-point improvement in keypoint consistency compared to prior approaches.
Authors: Zhiye Song, Steve Dai, Ben Keller, Brucek Khailany
Abstract: Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this success, enabling strong prompt adherence and realistic video quality. Despite their versatility and superior performance, these models require intensive computation. Each video generation requires dozens of iterative steps, and CFG doubles the required compute. This inefficiency hinders broader adoption in downstream applications. We introduce GalaxyDiT, a training-free method to accelerate video generation with guidance alignment and systematic proxy selection for reuse metrics. Through rank-order correlation analysis, our technique identifies the optimal proxy for each video model, across model families and parameter scales, thereby ensuring optimal computational reuse. We achieve $1.87\times$ and $2.37\times$ speedup on Wan2.1-1.3B and Wan2.1-14B with only 0.97% and 0.72% drops on the VBench-2.0 benchmark. At high speedup rates, our approach maintains superior fidelity to the base model, exceeding prior state-of-the-art approaches by 5 to 10 dB in peak signal-to-noise ratio (PSNR).
Authors: Maryam Maghsoudi, Mohsen Rezaeizadeh, Shihab Shamma
Abstract: Decoding imagined speech engages complex neural processes that are difficult to interpret due to uncertainty in timing and the limited availability of imagined-response datasets. In this study, we present a Magnetoencephalography (MEG) dataset collected from trained musicians as they imagined and listened to musical and poetic stimuli. We show that both imagined and perceived brain responses contain consistent, condition-specific information. Using a sliding-window ridge regression model, we first mapped imagined responses to listened responses at the single-subject level, but found limited generalization across subjects. At the group level, we developed an encoder-decoder convolutional neural network with a subject-specific calibration layer that produced stable and generalizable mappings. The CNN consistently outperformed the null model, yielding significantly higher correlations between predicted and true listened responses for nearly all held-out subjects. Our findings demonstrate that imagined neural activity can be transformed into perception-like responses, providing a foundation for future brain-computer interface applications involving imagined speech and music.
Authors: Johnny Peng, Thanh Tung Khuat, Ellen Otte, Katarzyna Musial, Bogdan Gabrys
Abstract: In cell culture bioprocessing, real-time batch process monitoring (BPM) refers to the continuous tracking and analysis of key process variables such as viable cell density, nutrient levels, metabolite concentrations, and product titer throughout the duration of a batch run. This enables early detection of deviations and supports timely control actions to ensure optimal cell growth and product quality. BPM plays a critical role in ensuring the quality and regulatory compliance of biopharmaceutical manufacturing processes. However, the development of accurate soft sensors for BPM is hindered by key challenges, including limited historical data, infrequent feedback, heterogeneous process conditions, and high-dimensional sensory inputs. This study presents a comprehensive benchmarking analysis of machine learning (ML) methods designed to address these challenges, with a focus on learning from historical data with limited volume and relevance in the context of bioprocess monitoring. We evaluate multiple ML approaches including feature dimensionality reduction, online learning, and just-in-time learning across three datasets, one in silico dataset and two real-world experimental datasets. Our findings highlight the importance of training strategies in handling limited data and feedback, with batch learning proving effective in homogeneous settings, while just-in-time learning and online learning demonstrate superior adaptability in cold-start scenarios. Additionally, we identify key meta-features, such as feed media composition and process control strategies, that significantly impact model transferability. The results also suggest that integrating Raman-based predictions with lagged offline measurements enhances monitoring accuracy, offering a promising direction for future bioprocess soft sensor development.
Authors: Berkani Khaled, Zeraoulia Rafik
Abstract: Malicious URLs remain a primary vector for phishing, malware, and cyberthreats. This study proposes a hybrid deep learning framework combining \texttt{HashingVectorizer} n-gram analysis, SMOTE balancing, Isolation Forest anomaly filtering, and a lightweight neural network classifier for real-time URL classification. The multi-stage pipeline processes URLs from open-source repositories with statistical features (length, dot count, entropy), achieving $O(NL + EBdh)$ training complexity and a 20\,ms prediction latency. Empirical evaluation yields 96.4\% accuracy, 95.4\% F1-score, and 97.3\% ROC-AUC, outperforming CNN (94.8\%) and SVM baselines with a $50\!\times$--$100\!\times$ speedup (Table~\ref{tab:comp-complexity}). A multilingual Tkinter GUI (Arabic/English/French) enables real-time threat assessment with clipboard integration. The framework demonstrates superior scalability and resilience against obfuscated URL patterns.
Authors: Zijian Gu, Yuxi Liu, Zhenhao Zhang, Song Wang
Abstract: Vision-language models achieve expert-level performance on medical imaging tasks but exhibit significant diagnostic accuracy disparities across demographic groups. We introduce fairness-aware Low-Rank Adaptation for medical VLMs, combining parameter efficiency with explicit fairness optimization. Our key algorithmic contribution is a differentiable MaxAccGap loss that enables end-to-end optimization of accuracy parity across demographic groups. We propose three methods: FR-LoRA integrates MaxAccGap regularization into the training objective, GR-LoRA applies inverse frequency weighting to balance gradient contributions, and Hybrid-LoRA combines both mechanisms.Evaluated on 10,000 glaucoma fundus images, GR-LoRA reduces diagnostic accuracy disparities by 69% while maintaining 53.15% overall accuracy. Ablation studies reveal that strong regularization strength achieves optimal fairness with minimal accuracy trade-off, and race-specific optimization yields 60% disparity reduction. Our approach requires only 0.24% trainable parameters, enabling practical deployment of fair medical AI in resource-constrained healthcare settings.
Authors: Di Xiu, Hongyin Tang, Bolin Rong, Lizhi Yan, Jingang Wang, Yifan Lu, Xunliang Cai
Abstract: Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hindering the advancement of tasks such as agents and multimodal applications. This report conducts a preliminary investigation into the effectiveness and theoretical mechanisms of the Top-$k$ Attention mechanism during both the decoding and training phases. First, we validate the effectiveness of exact Top-$k$ Decoding through extensive experimentation. Experiments demonstrate that retaining only the pivotal Keys with the highest similarity to the Query as the context window during the decoding stage achieves performance comparable to, or even surpassing, full attention on downstream tasks such as HELMET and LongBench v2. Second, we further explore the native Top-$k$ Attention training strategy. Experiments confirm that ensuring the consistency between training and inference regarding Top-$k$ Attention operations facilitates the further unlocking of Top-$k$ Decoding's potential, thereby significantly enhancing model performance. Furthermore, considering the high computational complexity of exact Top-$k$ Attention, we investigate the impact of approximate Top-$k$ algorithm precision on downstream tasks. Our research confirms a positive correlation between downstream task performance and approximation fidelity, and we provide statistical evaluations of the Lightning Indexer's precision within the DeepSeek-V3.2-Exp model. Finally, this report provides a theoretical interpretation from the perspective of Entropy. Experimental observations indicate that models subjected to Top-$k$ Attention SFT exhibit a distinct phenomenon of entropy reduction in downstream tasks, which validates the hypothesis that low-entropy states are better adapted to Top-$k$ Decoding.
Authors: Xiaosen Lyu, Jiayu Xiong, Yuren Chen, Wanlong Wang, Xiaoqing Dai, Jing Wang
Abstract: Multimodal Emotion Recognition in Conversation (MERC) aims to predict speakers' emotions by integrating textual, acoustic, and visual cues. Existing approaches either struggle to capture complex cross-modal interactions or experience gradient conflicts and unstable training when using deeper architectures. To address these issues, we propose Cross-Space Synergy (CSS), which couples a representation component with an optimization component. Synergistic Polynomial Fusion (SPF) serves the representation role, leveraging low-rank tensor factorization to efficiently capture high-order cross-modal interactions. Pareto Gradient Modulator (PGM) serves the optimization role, steering updates along Pareto-optimal directions across competing objectives to alleviate gradient conflicts and improve stability. Experiments show that CSS outperforms existing representative methods on IEMOCAP and MELD in both accuracy and training stability, demonstrating its effectiveness in complex multimodal scenarios.
Authors: Stefano Scanzio, Gabriele Formis, Tullio Facchinetti, Gianluca Cena
Abstract: Wireless sensor networks (WSNs) are employed across a wide range of industrial applications where ultra-low power consumption is a critical prerequisite. At the same time, these systems must maintain a certain level of determinism to ensure reliable and predictable operation. In this view, time slotted channel hopping (TSCH) is a communication technology that meets both conditions, making it an attractive option for its usage in industrial WSNs. This work proposes the use of machine learning to learn the traffic pattern generated in networks based on the TSCH protocol, in order to turn nodes into a deep sleep state when no transmission is planned and thus to improve the energy efficiency of the WSN. The ability of machine learning models to make good predictions at different network levels in a typical tree network topology was analyzed in depth, showing how their capabilities degrade while approaching the root of the tree. The application of these models on simulated data based on an accurate modeling of wireless sensor nodes indicates that the investigated algorithms can be suitably used to further and substantially reduce the power consumption of a TSCH network.
Authors: Zhening Li, Armando Solar-Lezama, Yisong Yue, Stephan Zheng
Abstract: We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree search). We introduce "probabilistic angelic nondeterminism" ("PAN"), a programming model that disentangles these two concerns, allowing the programmer to describe the agent workflow and independently experiment with different inference-time strategies by simply changing a few inputs. We provide an implementation of PAN in Python as the EnCompass framework, which uses a Python decorator to compile agent workflow programs into a search space. We present three case studies that demonstrate how the framework lets the programmer quickly improve the reliability of an agent and easily switch between different inference-time strategies, all with little additional coding.
Authors: Hanxiu Zhang, Yue Zheng
Abstract: The protection of Intellectual Property (IP) in Large Language Models (LLMs) represents a critical challenge in contemporary AI research. While fingerprinting techniques have emerged as a fundamental mechanism for detecting unauthorized model usage, existing methods -- whether behavior-based or structural -- suffer from vulnerabilities such as false claim attacks or susceptible to weight manipulations. To overcome these limitations, we propose SELF, a novel intrinsic weight-based fingerprinting scheme that eliminates dependency on input and inherently resists false claims. SELF achieves robust IP protection through two key innovations: 1) unique, scalable and transformation-invariant fingerprint extraction via singular value and eigenvalue decomposition of LLM attention weights, and 2) effective neural network-based fingerprint similarity comparison based on few-shot learning and data augmentation. Experimental results demonstrate SELF maintains high IP infringement detection accuracy while showing strong robustness against various downstream modifications, including quantization, pruning, and fine-tuning attacks. Our code is available at https://github.com/HanxiuZhang/SELF_v2.
Authors: Kohei Yamamoto, Kosuke Okusa
Abstract: Transformer-based audio SSL (self-supervised learning) models often treat spectrograms as images, applying convolutional patchification with heavy temporal downsampling. This lowers the effective Nyquist frequency and introduces aliasing, while na\"ive low-pass filtering removes task-relevant high-frequency cues. In this study, we present Aliasing-aware Patch Embedding (AaPE), a drop-in patch stem that mitigates aliasing while preserving high-frequency information. AaPE augments standard patch tokens with features produced by a band-limited complex sinusoidal kernel using a two-sided exponential window that dynamically targets alias-prone bands. Frequency and decay parameters of the kernel are estimated from the input, enabling parallel, adaptive subband analysis whose outputs are fused with the standard patch tokens. AaPE integrates seamlessly into the masked teacher-student self-supervised learning. In addition, we combine a multi-mask strategy with a contrastive objective to enforce consistency across diverse mask patterns, stabilizing training. Pre-training on AudioSet followed by fine-tuning evaluation across diverse downstream benchmarks, which spanned categories, such as environmental sounds and other common audio domains. This approach yields state-of-the-art performance on a subset of tasks and competitive results across the remainder. Complementary linear probing evaluation mirrors this pattern, yielding clear gains on several benchmarks and strong performance elsewhere. The collective analysis of these results indicates that AaPE serves to mitigate the effects of aliasing without discarding of informative high-frequency content.
Authors: Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick
Abstract: DeepSeek-OCR demonstrates that rendered text can be reconstructed with high fidelity from a small number of vision tokens. This finding has sparked excitement about vision-based context compression for language models. But the evaluation stops at reconstruction; whether these representations help language modeling remains untested. We test two assumptions implicit in the optical-compression narrative: that vision-based compression provides unique advantages for text reconstruction from compressed representations, and that DeepSeek-OCR's reconstruction results are evidence that vision-based compression will be useful for language modeling. Comparing their vision encoder against simple alternatives--parameter-free mean pooling and a learned hierarchical encoder--we find that these simple approaches match or surpass vision for reconstruction at matched compression ratios, and outperform it for language modeling--where vision-based compression fails to beat truncation. The excitement around optical context compression outpaces the evidence. Code and checkpoints are available at https://github.com/ivnle/bad-autoencoding
Authors: Vahid Nateghi, Lara Neureither, Selma Moqvist, Carsten Hartmann, Simon Olsson, Feliks N\"uske
Abstract: Coarse graining (CG) is an important task for efficient modeling and simulation of complex multi-scale systems, such as the conformational dynamics of biomolecules. This work presents a projection-based coarse-graining formalism for general underdamped Langevin dynamics. Following the Zwanzig projection approach, we derive a closed-form expression for the coarse grained dynamics. In addition, we show how the generator Extended Dynamic Mode Decomposition (gEDMD) method, which was developed in the context of Koopman operator methods, can be used to model the CG dynamics and evaluate its kinetic properties, such as transition timescales. Finally, we combine our approach with thermodynamic interpolation (TI), a generative approach to transform samples between thermodynamic conditions, to extend the scope of the approach across thermodynamic states without repeated numerical simulations. Using a two-dimensional model system, we demonstrate that the proposed method allows to accurately capture the thermodynamic and kinetic properties of the full-space model.
Authors: Seyed Mohammad Azimi-Abarghouyi, Carlo Fischione, Kaibin Huang
Abstract: Over-the-Air Federated Learning (AirFL) is an emerging paradigm that tightly integrates wireless signal processing and distributed machine learning to enable scalable AI at the network edge. By leveraging the superposition property of wireless signals, AirFL performs communication and model aggregation of the learning process simultaneously, significantly reducing latency, bandwidth, and energy consumption. This article offers a tutorial treatment of AirFL, presenting a novel classification into three design approaches: CSIT-aware, blind, and weighted AirFL. We provide a comprehensive guide to theoretical foundations, performance analysis, complexity considerations, practical limitations, and prospective research directions.
Authors: Lorenzo Marinucci, Leonardo Di Nino, Gabriele D'Acunto, Mario Edoardo Pandolfo, Paolo Di Lorenzo, Sergio Barbarossa
Abstract: Probabilistic Graphical Models (PGMs) encode conditional dependencies among random variables using a graph -nodes for variables, links for dependencies- and factorize the joint distribution into lower-dimensional components. This makes PGMs well-suited for analyzing complex systems and supporting decision-making. Recent advances in topological signal processing highlight the importance of variables defined on topological spaces in several application domains. In such cases, the underlying topology shapes statistical relationships, limiting the expressiveness of canonical PGMs. To overcome this limitation, we introduce Colored Markov Random Fields (CMRFs), which model both conditional and marginal dependencies among Gaussian edge variables on topological spaces, with a theoretical foundation in Hodge theory. CMRFs extend classical Gaussian Markov Random Fields by including link coloring: connectivity encodes conditional independence, while color encodes marginal independence. We quantify the benefits of CMRFs through a distributed estimation case study over a physical network, comparing it with baselines with different levels of topological prior.
Authors: Samantha Chapin, Kenneth Stewart, Roxana Leontie, Carl Glen Henshaw
Abstract: The US Naval Research Laboratory's (NRL's) Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) experiment pioneers the use of reinforcement learning (RL) for control of free-flying robots in the zero-gravity (zero-G) environment of space. On Tuesday, May 27th 2025 the APIARY team conducted the first ever, to our knowledge, RL control of a free-flyer in space using the NASA Astrobee robot on-board the International Space Station (ISS). A robust 6-degrees of freedom (DOF) control policy was trained using an actor-critic Proximal Policy Optimization (PPO) network within the NVIDIA Isaac Lab simulation environment, randomizing over goal poses and mass distributions to enhance robustness. This paper details the simulation testing, ground testing, and flight validation of this experiment. This on-orbit demonstration validates the transformative potential of RL for improving robotic autonomy, enabling rapid development and deployment (in minutes to hours) of tailored behaviors for space exploration, logistics, and real-time mission needs.
Authors: Kenneth Stewart, Samantha Chapin, Roxana Leontie, Carl Glen Henshaw
Abstract: Reinforcement learning (RL) offers transformative potential for robotic control in space. We present the first on-orbit demonstration of RL-based autonomous control of a free-flying robot, the NASA Astrobee, aboard the International Space Station (ISS). Using NVIDIA's Omniverse physics simulator and curriculum learning, we trained a deep neural network to replace Astrobee's standard attitude and translation control, enabling it to navigate in microgravity. Our results validate a novel training pipeline that bridges the simulation-to-reality (Sim2Real) gap, utilizing a GPU-accelerated, scientific-grade simulation environment for efficient Monte Carlo RL training. This successful deployment demonstrates the feasibility of training RL policies terrestrially and transferring them to space-based applications. This paves the way for future work in In-Space Servicing, Assembly, and Manufacturing (ISAM), enabling rapid on-orbit adaptation to dynamic mission requirements.
Authors: Kehlani Fay, Darin Anthony Djapri, Anya Zorin, James Clinton, Ali El Lahib, Hao Su, Michael T. Tolley, Sha Yi, Xiaolong Wang
Abstract: Dexterous manipulation is limited by both control and design, without consensus as to what makes manipulators best for performing dexterous tasks. This raises a fundamental challenge: how should we design and control robot manipulators that are optimized for dexterity? We present a co-design framework that learns task-specific hand morphology and complementary dexterous control policies. The framework supports 1) an expansive morphology search space including joint, finger, and palm generation, 2) scalable evaluation across the wide design space via morphology-conditioned cross-embodied control, and 3) real-world fabrication with accessible components. We evaluate the approach across multiple dexterous tasks, including in-hand rotation with simulation and real deployment. Our framework enables an end-to-end pipeline that can design, train, fabricate, and deploy a new robotic hand in under 24 hours. The full framework will be open-sourced and available on our website.
Authors: Jingyang Ou, Jiaqi Han, Minkai Xu, Shaoxuan Xu, Jianwen Xie, Stefano Ermon, Yi Wu, Chongxuan Li
Abstract: Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges. The core difficulty lies in likelihood approximation: while autoregressive models naturally provide token-level conditional probabilities essential for token-level RL objectives (e.g., GRPO), dLLMs generate sequences through iterative non-autoregressive denoising steps that lack this factorization. To address this fundamental mismatch, we propose ELBO-based Sequence-level Policy Optimization (ESPO), a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy. Our method incorporates per-token normalization of importance ratios and robust KL-divergence estimation to ensure stable large-scale training. Extensive experiments on mathematical reasoning, coding, and planning tasks demonstrate that ESPO significantly outperforms token-level baselines, achieving dramatic improvements of 20-40 points on the Countdown task, while maintaining consistent gains on math and coding benchmarks. Our approach establishes sequence-level optimization as a principled and empirically effective paradigm for RL in dLLMs. Our code is available at https://github.com/ML-GSAI/ESPO.
Authors: Itay Yona, Amir Sarid, Michael Karasik, Yossi Gandelsman
Abstract: We introduce \textbf{Doublespeak}, a simple \emph{in-context representation hijacking} attack against large language models (LLMs). The attack works by systematically replacing a harmful keyword (e.g., \textit{bomb}) with a benign token (e.g., \textit{carrot}) across multiple in-context examples, provided a prefix to a harmful request. We demonstrate that this substitution leads to the internal representation of the benign token converging toward that of the harmful one, effectively embedding the harmful semantics under a euphemism. As a result, superficially innocuous prompts (e.g., ``How to build a carrot?'') are internally interpreted as disallowed instructions (e.g., ``How to build a bomb?''), thereby bypassing the model's safety alignment. We use interpretability tools to show that this semantic overwrite emerges layer by layer, with benign meanings in early layers converging into harmful semantics in later ones. Doublespeak is optimization-free, broadly transferable across model families, and achieves strong success rates on closed-source and open-source systems, reaching 74\% ASR on Llama-3.3-70B-Instruct with a single-sentence context override. Our findings highlight a new attack surface in the latent space of LLMs, revealing that current alignment strategies are insufficient and should instead operate at the representation level.
Authors: Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye
Abstract: Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.
Authors: Ahmed Nasser, Marwan Mohamed, Alaa Sherif, Basmala Mahmoud, Shereen Yehia, Asmaa Saad, Mariam S. El-Rahmany, Ensaf H. Mohamed
Abstract: Egyptian hieroglyphs, the ancient Egyptian writing system, are composed entirely of drawings. Translating these glyphs into English poses various challenges, including the fact that a single glyph can have multiple meanings. Deep learning translation applications are evolving rapidly, producing remarkable results that significantly impact our lives. In this research, we propose a method for the automatic recognition and translation of ancient Egyptian hieroglyphs from images to English. This study utilized two datasets for classification and translation: the Morris Franken dataset and the EgyptianTranslation dataset. Our approach is divided into three stages: segmentation (using Contour and Detectron2), mapping symbols to Gardiner codes, and translation (using the CNN model). The model achieved a BLEU score of 42.2, a significant result compared to previous research.
Authors: Paul Strasser, Andreas Pfeffer, Jakob Weber, Markus Gurtner, Andreas K\"orner
Abstract: Neural networks have become a widely adopted tool for modeling nonlinear dynamical systems from data. However, the choice of training strategy remains a key design decision, particularly for simulation tasks. This paper compares two predominant strategies: parallel and series-parallel training. The conducted empirical analysis spans five neural network architectures and two examples: a pneumatic valve test bench and an industrial robot benchmark. The study reveals that, even though series-parallel training dominates current practice, parallel training consistently yields better long-term prediction accuracy. Additionally, this work clarifies the often inconsistent terminology in the literature and relate both strategies to concepts from system identification. The findings suggest that parallel training should be considered the default training strategy for neural network-based simulation of dynamical systems.
Authors: Lei Zhang, Diwen Zheng, Kaixin Bai, Zhenshan Bing, Zoltan-Csaba Marton, Zhaopeng Chen, Alois Christian Knoll, Jianwei Zhang
Abstract: Dexterous grasp generation aims to produce grasp poses that align with task requirements and human interpretable grasp semantics. However, achieving semantically controllable dexterous grasp synthesis remains highly challenging due to the lack of unified modeling of multiple semantic dimensions, including grasp taxonomy, contact semantics, and functional affordance. To address these limitations, we present OmniDexVLG, a multimodal, semantics aware grasp generation framework capable of producing structurally diverse and semantically coherent dexterous grasps under joint language and visual guidance. Our approach begins with OmniDexDataGen, a semantic rich dexterous grasp dataset generation pipeline that integrates grasp taxonomy guided configuration sampling, functional affordance contact point sampling, taxonomy aware differential force closure grasp sampling, and physics based optimization and validation, enabling systematic coverage of diverse grasp types. We further introduce OmniDexReasoner, a multimodal grasp type semantic reasoning module that leverages multi agent collaboration, retrieval augmented generation, and chain of thought reasoning to infer grasp related semantics and generate high quality annotations that align language instructions with task specific grasp intent. Building upon these components, we develop a unified Vision Language Grasping generation model that explicitly incorporates grasp taxonomy, contact structure, and functional affordance semantics, enabling fine grained control over grasp synthesis from natural language instructions. Extensive experiments in simulation and real world object grasping and ablation studies demonstrate that our method substantially outperforms state of the art approaches in terms of grasp diversity, contact semantic diversity, functional affordance diversity, and semantic consistency.
Authors: Ying-Kuan Tsai, Yi-Ping Chen, Vispi Karkaria, Wei Chen
Abstract: Active suspension systems are critical for enhancing vehicle comfort, safety, and stability, yet their performance is often limited by fixed hardware designs and control strategies that cannot adapt to uncertain and dynamic operating conditions. Recent advances in digital twins (DTs) and deep reinforcement learning (DRL) offer new opportunities for real-time, data-driven optimization across a vehicle's lifecycle. However, integrating these technologies into a unified framework remains an open challenge. This work presents a DT-based control co-design (CCD) framework for full-vehicle active suspensions using multi-generation design concepts. By integrating automatic differentiation into DRL, we jointly optimize physical suspension components and control policies under varying driver behaviors and environmental uncertainties. DRL also addresses the challenge of partial observability, where only limited states can be sensed and fed back to the controller, by learning optimal control actions directly from available sensor information. The framework incorporates model updating with quantile learning to capture data uncertainty, enabling real-time decision-making and adaptive learning from digital-physical interactions. The approach demonstrates personalized optimization of suspension systems under two distinct driving settings (mild and aggressive). Results show that the optimized systems achieve smoother trajectories and reduce control efforts by approximately 43% and 52% for mild and aggressive, respectively, while maintaining ride comfort and stability. Contributions include: developing a DT-enabled CCD framework integrating DRL and uncertainty-aware model updating for full-vehicle active suspensions, introducing a multi-generation design strategy for self-improving systems, and demonstrating personalized optimization of active suspension systems for distinct driver types.
Authors: Kenneth Stewart, Roxana Leontie, Samantha Chapin, Joe Hays, Sumit Bam Shrestha, Carl Glen Henshaw
Abstract: We present an end-to-end pipeline for deploying reinforcement learning (RL) trained Artificial Neural Networks (ANNs) on neuromorphic hardware by converting them into spiking Sigma-Delta Neural Networks (SDNNs). We demonstrate that an ANN policy trained entirely in simulation can be transformed into an SDNN compatible with Intel's Loihi 2 architecture, enabling low-latency and energy-efficient inference. As a test case, we use an RL policy for controlling the Astrobee free-flying robot, similar to a previously hardware in space-validated controller. The policy, trained with Rectified Linear Units (ReLUs), is converted to an SDNN and deployed on Intel's Loihi 2, then evaluated in NVIDIA's Omniverse Isaac Lab simulation environment for closed-loop control of Astrobee's motion. We compare execution performance between GPU and Loihi 2. The results highlight the feasibility of using neuromorphic platforms for robotic control and establish a pathway toward energy-efficient, real-time neuromorphic computation in future space and terrestrial robotics applications.
Authors: X. Y. Han, Yuan Zhong
Abstract: In large-scale AI training, Sparse Mixture-of-Experts (s-MoE) layers enable scaling by activating only a small subset of experts per token. An operational challenge in this design is load balancing: routing tokens to minimize the number of idle experts, which is important for the efficient utilization of (costly) GPUs. We provide a theoretical framework for analyzing the Auxiliary-Loss-Free Load Balancing (ALF-LB) procedure -- proposed by DeepSeek's Wang et al. (2024) -- by casting it as a one-step-per-iteration primal-dual method for an assignment problem. First, in a stylized deterministic setting, our framework yields several insightful structural properties: (i) a monotonic improvement of a Lagrangian objective, (ii) a preference rule that moves tokens from overloaded to underloaded experts, and (iii) an approximate-balancing guarantee. Then, we incorporate the stochastic and dynamic nature of AI training using a generalized online optimization formulation. In the online setting, we derive a strong convexity property of the objective that leads to a logarithmic expected regret bound under certain step-size choices. Additionally, we present real experiments on 1B-parameter DeepSeekMoE models to complement our theoretical findings. Together, these results build a principled framework for analyzing the Auxiliary-Loss-Free Load Balancing of s-MoE in AI models.
Authors: Evan Bell, Shijun Liang, Ismail Alkhouri, Saiprasad Ravishankar
Abstract: Deep Image Prior (DIP) has recently emerged as a promising one-shot neural-network based image reconstruction method. However, DIP has seen limited application to 3D image reconstruction problems. In this work, we introduce Tada-DIP, a highly effective and fully 3D DIP method for solving 3D inverse problems. By combining input-adaptation and denoising regularization, Tada-DIP produces high-quality 3D reconstructions while avoiding the overfitting phenomenon that is common in DIP. Experiments on sparse-view X-ray computed tomography reconstruction validate the effectiveness of the proposed method, demonstrating that Tada-DIP produces much better reconstructions than training-data-free baselines and achieves reconstruction performance on par with a supervised network trained using a large dataset with fully-sampled volumes.
Authors: Paul Fuchs, Julija Zavadlav
Abstract: Foundational Machine Learning Potentials can resolve the accuracy and transferability limitations of classical force fields. They enable microscopic insights into material behavior through Molecular Dynamics simulations, which can crucially expedite material design and discovery. However, insufficiently broad and systematically biased reference data affect the predictive quality of the learned models. Often, these models exhibit significant deviations from experimentally observed phase transition temperatures, in the order of several hundred kelvins. Thus, fine-tuning is necessary to achieve adequate accuracy in many practical problems. This work proposes a fine-tuning strategy via top-down learning, directly correcting the wrongly predicted transition temperatures to match the experimental reference data. Our approach leverages the Differentiable Trajectory Reweighting algorithm to minimize the free energy differences between phases at the experimental target pressures and temperatures. We demonstrate that our approach can accurately correct the phase diagram of pure Titanium in a pressure range of up to 5 GPa, matching the experimental reference within tenths of kelvins and improving the liquid-state diffusion constant. Our approach is model-agnostic, applicable to multi-component systems with solid-solid and solid-liquid transitions, and compliant with top-down training on other experimental properties. Therefore, our approach can serve as an essential step towards highly accurate application-specific and foundational machine learning potentials.
Authors: Jialuo Li, Bin Li, Jiahao Li, Yan Lu
Abstract: The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has focused on query-aware frame selection, methods that often incur significant computational overhead. This paper challenges the assumption that such complex search mechanisms are universally necessary. We first identify and validate a query typology distinguishing between global query and localized query. We demonstrate that while uniform sampling is both effective and efficient for global queries, localized queries indeed necessitate query-aware selection for optimal performance. Building on this insight, we propose DIG, a training-free frame selection framework that adapts its strategy based on the query type. Specifically,DIG employs efficient uniform sampling for global queries while activating a specialized pipeline to extract query-relevant frames for localized queries. Experiments on three long-form video understanding benchmarks demonstrate that DIG consistently outperforms existing baselines and robustly improves LMM performance, even when scaling the input frame count to 256.
Authors: Xiaolong Li, Youping Gu, Xi Lin, Weijie Wang, Bohan Zhuang
Abstract: Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity emerging as the dominant paradigm. Current methods typically retain or discard entire key-value blocks with binary masks, resulting in substantial information loss under high sparsity. To mitigate this gap, we present Pyramid Sparse Attention (PSA), a versatile module applicable to both video understanding and generation tasks. Instead of binary masking, PSA introduces multi-level pooled KV representations, enabling finer mask granularity. Specifically, each query block dynamically allocates lower pooling levels to critical KV blocks and higher levels to less important ones, creating an informative interpolation between full retention and complete pruning. This design, analogous to fixed-point quantization and classical feature pyramid networks in computer vision, effectively mitigates information loss while preserving computational efficiency under a low compute budget. It works with a native, hardware-friendly kernel that leverages decoupled block-tile design to ensure efficient execution. Across video understanding and generation benchmarks, PSA preserves contextual information and visual fidelity, consistently outperforming or achieving comparable performance over existing sparse attention baselines with superior efficiency-quality trade-offs. Our code and model weights are publicly available at: http://ziplab.co/PSA
URLs: http://ziplab.co/PSA
Authors: Sandeep Nagar
Abstract: This thesis presents novel contributions in two primary areas: advancing the efficiency of generative models, particularly normalizing flows, and applying generative models to solve real-world computer vision challenges. The first part introduce significant improvements to normalizing flow architectures through six key innovations: 1) Development of invertible 3x3 Convolution layers with mathematically proven necessary and sufficient conditions for invertibility, (2) introduction of a more efficient Quad-coupling layer, 3) Design of a fast and efficient parallel inversion algorithm for kxk convolutional layers, 4) Fast & efficient backpropagation algorithm for inverse of convolution, 5) Using inverse of convolution, in Inverse-Flow, for the forward pass and training it using proposed backpropagation algorithm, and 6) Affine-StableSR, a compact and efficient super-resolution model that leverages pre-trained weights and Normalizing Flow layers to reduce parameter count while maintaining performance. The second part: 1) An automated quality assessment system for agricultural produce using Conditional GANs to address class imbalance, data scarcity and annotation challenges, achieving good accuracy in seed purity testing; 2) An unsupervised geological mapping framework utilizing stacked autoencoders for dimensionality reduction, showing improved feature extraction compared to conventional methods; 3) We proposed a privacy preserving method for autonomous driving datasets using on face detection and image inpainting; 4) Utilizing Stable Diffusion based image inpainting for replacing the detected face and license plate to advancing privacy-preserving techniques and ethical considerations in the field.; and 5) An adapted diffusion model for art restoration that effectively handles multiple types of degradation through unified fine-tuning.
Authors: Shashaank Khanna, Matthew Pusey, Roger Colbeck
Abstract: The discovery of Bell that there exist quantum correlations that cannot be reproduced classically is one of the most important in the foundations of quantum mechanics, as well as having practical implications. Bell's result was originally proven in a simple bipartite causal structure, but analogous results have also been shown in further causal structures. Here we study the only causal structure with six or fewer nodes in which the question of whether or not there exist quantum correlations that cannot be achieved classically was open. In this causal structure we show that such quantum correlations exist using a method that involves imposing additional restrictions on the correlations. This hence completes the picture of which causal structures of up to six nodes support non-classical quantum correlations. We also provide further illustrations of our method using other causal structures.
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: Vaggos Chatziafratis, Ishani Karmarkar, Yingxi Li, Ellen Vitercik
Abstract: Data-driven algorithm selection is a powerful approach for choosing effective heuristics for computational problems. It operates by evaluating a set of candidate algorithms on a collection of representative training instances and selecting the one with the best empirical performance. However, running each algorithm on every training instance is computationally expensive, making scalability a central challenge. In practice, a common workaround is to evaluate algorithms on smaller proxy instances derived from the original inputs. However, this practice has remained largely ad hoc and lacked theoretical grounding. We provide the first theoretical foundations for this practice by formalizing the notion of size generalization: predicting an algorithm's performance on a large instance by evaluating it on a smaller, representative instance, subsampled from the original instance. We provide size generalization guarantees for three widely used clustering algorithms (single-linkage, $k$-means++, and Gonzalez's $k$-centers heuristic) and two canonical max-cut algorithms (Goemans-Williamson and Greedy). We characterize the subsample size sufficient to ensure that performance on the subsample reflects performance on the full instance, and our experiments support these findings.
Authors: Honglin Wen, Pierre Pinson, Jie Gu, Zhijian Jin
Abstract: Machine learning methods are widely and successfully used for probabilistic wind power forecasting, yet the pervasive issue of missing values (e.g., due to sensor faults or communication outages) has received limited attention. The prevailing practice is impute-then-predict, but conditioning on point imputations biases parameter estimates and fails to propagate uncertainty from missing features. Our approach treats missing features and forecast targets uniformly: we learn a joint generative model of features and targets from incomplete data and, at operational deployment, condition on the observed features and marginalize the unobserved ones to produce forecasts. This imputation-free procedure avoids error introduced by imputation and preserves uncertainty aroused from missing features. In experiments, it improves forecast quality in terms of continuous ranked probability score relative to impute-then-predict baselines while incurring substantially lower computational cost than common alternatives.
Authors: Thomas Souverain, Johnathan Nguyen, Nicolas Meric, Paul \'Egr\'e
Abstract: This paper presents a philosophical and experimental study of fairness interventions in AI classification, centered on the explainability of corrective methods. We argue that ensuring fairness requires not only satisfying a target criterion, but also explaining which variables constrain its realization. When corrections are used to mitigate advantage transparently, they must remain sensitive to the distribution of true labels. To illustrate this approach, we built FairDream, a fairness package whose mechanism is made transparent for lay users, increasing the model's weights of errors on disadvantaged groups. While a user may intend to achieve Demographic Parity by the correction method, experiments show that FairDream tends towards Equalized Odds, revealing a conservative bias inherent to the data environment. We clarify the relationship between these fairness criteria, analyze FairDream's reweighting process, and compare its trade-offs with closely related GridSearch models. Finally, we justify the normative preference for Equalized Odds via an epistemological interpretation of the results, using their proximity with Simpson's paradox. The paper thus unites normative, epistemological, and empirical explanations of fairness interventions, to ensure transparency for the users.
Authors: Taeyoung Kim, Myungjoo Kang
Abstract: The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to its smoothness properties. However, deep RePU networks often suffer from critical issues such as vanishing or exploding values during training, rendering them unstable regardless of hyperparameter initialization. Leveraging the perspective of effective field theory, we identify the root causes of these failures and propose the Modified Rectified Power Unit (MRePU) activation function. MRePU addresses RePU's limitations while preserving its advantages, such as differentiability and universal approximation properties. Theoretical analysis demonstrates that MRePU satisfies criticality conditions necessary for stable training, placing it in a distinct universality class. Extensive experiments validate the effectiveness of MRePU, showing significant improvements in training stability and performance across various tasks, including polynomial regression, physics-informed neural networks (PINNs) and real-world vision tasks. Our findings highlight the potential of MRePU as a robust alternative for building deep neural networks.
Authors: Borna Sayedana, Peter E. Caines, Aditya Mahajan
Abstract: In this paper, we investigate the concentration properties of cumulative reward in Markov Decision Processes (MDPs), focusing on both asymptotic and non-asymptotic settings. We introduce a unified approach to characterize reward concentration in MDPs, covering both infinite-horizon settings (i.e., average and discounted reward frameworks) and finite-horizon setting. Our asymptotic results include the law of large numbers, the central limit theorem, and the law of iterated logarithms, while our non-asymptotic bounds include Azuma-Hoeffding-type inequalities and a non-asymptotic version of the law of iterated logarithms. Additionally, we explore two key implications of our results. First, we analyze the sample path behavior of the difference in rewards between any two stationary policies. Second, we show that two alternative definitions of regret for learning policies proposed in the literature are rate-equivalent. Our proof techniques rely on a martingale decomposition of cumulative reward, properties of the solution to the policy evaluation fixed-point equation, and both asymptotic and non-asymptotic concentration results for martingale difference sequences.
Authors: Jean-Baptiste Fermanian (UM, IMAG, IROKO), Pierre Humbert (SU, LPSM), Gilles Blanchard (LMO, DATASHAPE)
Abstract: We introduce a method based on Conformal Prediction (CP) to quantify the uncertainty of full ranking algorithms. We focus on a specific scenario where $n+m$ items are to be ranked by some ``black box'' algorithm. It is assumed that the relative (ground truth) ranking of $n$ of them is known. The objective is then to quantify the error made by the algorithm on the ranks of the $m$ new items among the total $(n+m)$. In such a setting, the true ranks of the $n$ original items in the total $(n+m)$ depend on the (unknown) true ranks of the $m$ new ones. Consequently, we have no direct access to a calibration set to apply a classical CP method. To address this challenge, we propose to construct distribution-free bounds of the unknown conformity scores using recent results on the distribution of conformal p-values. Using these scores upper bounds, we provide valid prediction sets for the rank of any item. We also control the false coverage proportion, a crucial quantity when dealing with multiple prediction sets. Finally, we empirically show on both synthetic and real data the efficiency of our CP method for state-of-the-art algorithms such as RankNet or LambdaMart.
Authors: Morgan Thomas, Albert Bou, Gianni De Fabritiis
Abstract: Chemical Language Models (CLMs) leveraging reinforcement learning (RL) have shown promise in de novo molecular design, yet often suffer from mode collapse, limiting their exploration capabilities. Inspired by Test-Time Training (TTT) in large language models, we propose scaling TTT for CLMs to enhance chemical space exploration. We introduce MolExp, a novel benchmark emphasizing the discovery of structurally diverse molecules with similar bioactivity, simulating real-world drug design challenges. Our results demonstrate that scaling TTT by increasing the number of independent RL agents follows a log-linear scaling law, significantly improving exploration efficiency as measured by MolExp. In contrast, increasing TTT training time yields diminishing returns, even with exploration bonuses. We further evaluate cooperative RL strategies to enhance exploration efficiency. These findings provide a scalable framework for generative molecular design, offering insights into optimizing AI-driven drug discovery.
Authors: Samrik Chowdhury, Siddharth Pritam, Rohit Roy, Madhav Cherupilil Sajeev
Abstract: In this work, we introduce a filtration on temporal graphs based on $\delta$-temporal motifs (recurrent subgraphs), yielding a multi-scale representation of temporal structure. Our temporal filtration allows tools developed for filtered static graphs, including persistent homology and recent graph filtration kernels, to be applied directly to temporal graph analysis. We demonstrate the effectiveness of this approach on temporal graph classification tasks.
Authors: Jie Shi, Aleksej Cornelissen, Siamak Mehrkanoon
Abstract: Short-term precipitation nowcasting is essential for flood management, transportation, energy system operations, and emergency response. However, many existing models fail to fully exploit the extensive atmospheric information available, relying primarily on precipitation data alone. This study examines whether integrating multi-variable weather-station measurements with radar can enhance nowcasting skill and introduces two complementary architectures that integrate multi-variable station data with radar images. The SmaAt-fUsion model extends the SmaAt-UNet framework by incorporating weather station data through a convolutional layer, integrating it into the bottleneck of the network; The SmaAt-Krige-GNet model combines precipitation maps with weather station data processed using Kriging, a geo-statistical interpolation method, to generate variable-specific maps. These maps are then utilized in a dual-encoder architecture based on SmaAt-GNet, allowing multi-level data integration . Experimental evaluations were conducted using four years (2016--2019) of weather station and precipitation radar data from the Netherlands. Results demonstrate that SmaAt-Krige-GNet outperforms the standard SmaAt-UNet, which relies solely on precipitation radar data, in low precipitation scenarios, while SmaAt-fUsion surpasses SmaAt-UNet in both low and high precipitation scenarios. This highlights the potential of incorporating discrete weather station data to enhance the performance of deep learning-based weather nowcasting models.
Authors: Hao-Run Cai, Han-Jia Ye
Abstract: Deep tabular models have demonstrated remarkable success on i.i.d. data, excelling in a variety of structured data tasks. However, their performance often deteriorates under temporal distribution shifts, where trends and periodic patterns are present in the evolving data distribution over time. In this paper, we explore the underlying reasons for this failure in capturing temporal dependencies. We begin by investigating the training protocol, revealing a key issue in how model selection performs. While existing approaches use temporal ordering for splitting validation set, we show that even a random split can significantly improve model performance. By minimizing the time lag between training data and test time, while reducing the bias in validation, our proposed training protocol significantly improves generalization across various methods. Furthermore, we analyze how temporal data affects deep tabular representations, uncovering that these models often fail to capture crucial periodic and trend information. To address this gap, we introduce a plug-and-play temporal embedding method based on Fourier series expansion to learn and incorporate temporal patterns, offering an adaptive approach to handle temporal shifts. Our experiments demonstrate that this temporal embedding, combined with the improved training protocol, provides a more effective and robust framework for learning from temporal tabular data.
Authors: Brian Bartoldson, Siddarth Venkatraman, James Diffenderfer, Moksh Jain, Tal Ben-Nun, Seanie Lee, Minsu Kim, Johan Obando-Ceron, Yoshua Bengio, Bhavya Kailkhura
Abstract: Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post-training are not naturally robust to a diversified content of experience replay buffers, which asynchronous off-policy actors can efficiently populate in parallel to training. We propose efficiently learning on such off-policy data via Trajectory Balance with Asynchrony (TBA), an approach to asynchronous RL for LLMs that leverages the principled off-policy TB objective. On math, preference-tuning, and automated red-teaming tasks, we post-train models ranging from Pythia 410M to Qwen 2.5 7B, finding TBA offers speed and performance boosts over strong baselines like Online DPO and Dr. GRPO. Beyond TBA's performance benefits (high accuracy even as asynchrony grows) and speedups ($4\times$ or more), we show its reward- and recency-prioritizing sampling enable further gains as data generation is scaled. Our code is available at https://github.com/bbartoldson/TBA.
Authors: Toby van Gastelen, Wouter Edeling, Benjamin Sanderse
Abstract: Machine learning-based closure models for LES have shown promise in capturing complex turbulence dynamics but often suffer from instabilities and physical inconsistencies. In this work, we develop a novel skew-symmetric neural architecture as closure model that enforces stability while preserving key physical conservation laws. Our approach leverages a discretization that ensures mass, momentum, and energy conservation, along with a face-averaging filter to maintain mass conservation in coarse-grained velocity fields. We compare our model against several conventional data-driven closures (including unconstrained convolutional neural networks), and the physics-based Smagorinsky model. Performance is evaluated on decaying turbulence and Kolmogorov flow for multiple coarse-graining factors. In these test cases we observe that unconstrained machine learning models suffer from numerical instabilities. In contrast, our skew-symmetric model remains stable across all tests, though at the cost of increased dissipation. Despite this trade-off, we demonstrate that our model still outperforms the Smagorinsky model in unseen scenarios. These findings highlight the potential of structure-preserving machine learning closures for reliable long-time LES.
Authors: Suping Xu, Chuyi Dai, Lin Shang, Changbin Shao, Xibei Yang, Witold Pedrycz
Abstract: Label distribution learning (LDL) is an emerging learning paradigm designed to capture the relative importance of labels for each instance. Label-specific features (LSFs), constructed by LIFT, have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label to re-characterize instances. However, directly introducing LIFT into LDL tasks can be suboptimal, as the prototypes it collects primarily reflect intra-cluster relationships while neglecting cross-cluster interactions. Additionally, constructing LSFs using multi-perspective information, rather than relying solely on Euclidean distance, provides a more robust and comprehensive representation of instances, mitigating noise and bias that may arise from a single distance perspective. To address these limitations, we introduce Structural Anchor Points (SAPs) to capture inter-cluster interactions. This leads to a novel LSFs construction strategy, LIFT-SAP, which enhances LIFT by integrating both distance and directional information of each instance relative to SAPs. Furthermore, we propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution. Extensive experiments on 15 real-world datasets demonstrate the effectiveness of LIFT-SAP over LIFT, as well as the superiority of LDL-LIFT-SAP compared to seven other well-established algorithms.
Authors: Flavio Di Martino, Franca Delmastro
Abstract: The widespread adoption of wearable sensors has the potential to provide massive and heterogeneous time series data, driving the use of Artificial Intelligence in human sensing applications. However, data collection remains limited due to stringent ethical regulations, privacy concerns, and other constraints, hindering progress in the field. Synthetic data generation, particularly through Generative Adversarial Networks and Diffusion Models, has emerged as a promising solution to mitigate both data scarcity and privacy issues. However, these models are often limited to narrow operational scenarios, such as short-term and unimodal signal patterns. To address this gap, we present a systematic evaluation of state-of-the-art generative models for time series data, explicitly assessing their performance in challenging scenarios such as stress and emotion recognition. Our study examines the extent to which these models can jointly handle multi-modality, capture long-range dependencies, and support conditional generation-core requirements for real-world wearable sensor data generation. To enable a fair and rigorous comparison, we also introduce an evaluation framework that evaluates both the intrinsic fidelity of the generated data and their utility in downstream predictive tasks. Our findings reveal critical limitations in the existing approaches, particularly in maintaining cross-modal consistency, preserving temporal coherence, and ensuring robust performance in train-on-synthetic, test-on-real, and data augmentation scenarios. Finally, we present our future research directions to enhance synthetic time series generation and improve the applicability of generative models in the wearable computing domain.
Authors: Yuning Shen, Lihao Wang, Huizhuo Yuan, Yan Wang, Bangji Yang, Quanquan Gu
Abstract: Understanding protein dynamics is critical for elucidating their biological functions. The increasing availability of molecular dynamics (MD) data enables the training of deep generative models to efficiently explore the conformational space of proteins. However, existing approaches either fail to explicitly capture the temporal dependencies between conformations or do not support direct generation of time-independent samples. To address these limitations, we introduce ConfRover, an autoregressive model that simultaneously learns protein conformation and dynamics from MD trajectories, supporting both time-dependent and time-independent sampling. At the core of our model is a modular architecture comprising: (i) an encoding layer, adapted from protein folding models, that embeds protein-specific information and conformation at each time frame into a latent space; (ii) a temporal module, a sequence model that captures conformational dynamics across frames; and (iii) an SE(3) diffusion model as the structure decoder, generating conformations in continuous space. Experiments on ATLAS, a large-scale protein MD dataset of diverse structures, demonstrate the effectiveness of our model in learning conformational dynamics and supporting a wide range of downstream tasks. ConfRover is the first model to sample both protein conformations and trajectories within a single framework, offering a novel and flexible approach for learning from protein MD data. Project website: https://bytedance-seed.github.io/ConfRover.
Authors: Afrah Farea, Saiful Khan, Reza Daryani, Emre Cenk Ersan, Mustafa Serdar Celebi
Abstract: Physics-informed neural networks (PINNs) have emerged as a promising approach for solving complex fluid dynamics problems, yet their application to fluid-structure interaction (FSI) problems with moving boundaries remains largely unexplored. This work addresses the critical challenge of modeling FSI systems with moving interfaces, where traditional unified PINN architectures struggle to capture the distinct physics governing fluid and structural domains simultaneously. We present an innovative Eulerian-Lagrangian PINN architecture that integrates immersed boundary method (IBM) principles to solve FSI problems with moving boundary conditions. Our approach fundamentally departs from conventional unified architectures by introducing domain-specific neural networks: an Eulerian network for fluid dynamics and a Lagrangian network for structural interfaces, coupled through physics-based constraints. Additionally, we incorporate learnable B-spline activation functions with SiLU to capture both localized high-gradient features near interfaces and global flow patterns. Empirical studies on a 2D cavity flow problem involving a moving solid structure show that while baseline unified PINNs achieve reasonable velocity predictions, they suffer from substantial pressure errors (12.9%) in structural regions. Our Eulerian-Lagrangian architecture with learnable activations (EL-L) achieves better performance across all metrics, improving accuracy by 24.1-91.4% and particularly reducing pressure errors from 12.9% to 2.39%. These results demonstrate that domain decomposition aligned with physical principles, combined with locality-aware activation functions, is essential for accurate FSI modeling within the PINN framework.
Authors: Jiaxi Hu, Yongqi Pan, Jusen Du, Disen Lan, Xiaqiang Tang, Qingsong Wen, Yuxuan Liang, Weigao Sun
Abstract: Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Delta learning rule. Unlike previous state-space models (e.g., Mamba) and gated linear attentions (e.g., GLA), these models introduce interactions between the recurrent state and the key vector, structurally resembling bilinear systems. In this paper, we first introduce the concept of Bilinear RNNs with a comprehensive analysis on the advantages and limitations of these models. Then, based on closed-loop control theory, we propose a novel Bilinear RNN variant named Comba, which adopts a scalar-plus-low-rank state transition, with both state feedback and output feedback corrections. We also implement a hardware-efficient chunk-wise parallel kernel in Triton and train models with 340M/1.3B parameters on large-scale corpus. Comba demonstrates superior performance and computation efficiency in both language and vision modeling.
Authors: Geonwoo Cho, Jaemoon Lee, Jaegyun Im, Subi Lee, Jihwan Lee, Sundong Kim
Abstract: Skill-based reinforcement learning (SBRL) enables rapid adaptation in environments with sparse rewards by pretraining a skill-conditioned policy. Effective skill learning requires jointly maximizing both exploration and skill diversity. However, existing methods often face challenges in simultaneously optimizing for these two conflicting objectives. In this work, we propose a new method, Adaptive Multi-objective Projection for balancing Exploration and skill Diversification (AMPED), which explicitly addresses both: during pre-training, a gradient-surgery projection balances the exploration and diversity gradients, and during fine-tuning, a skill selector exploits the learned diversity by choosing skills suited to downstream tasks. Our approach achieves performance that surpasses SBRL baselines across various benchmarks. Through an extensive ablation study, we identify the role of each component and demonstrate that each element in AMPED is contributing to performance. We further provide theoretical and empirical evidence that, with a greedy skill selector, greater skill diversity reduces fine-tuning sample complexity. These results highlight the importance of explicitly harmonizing exploration and diversity and demonstrate the effectiveness of AMPED in enabling robust and generalizable skill learning. Project Page: https://geonwoo.me/amped/
Authors: Ekaterina Filimoshina, Dmitry Shirokov
Abstract: We propose, implement, and compare with competitors a new architecture of equivariant neural networks based on geometric (Clifford) algebras: Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networks are equivariant to all pseudo-orthogonal transformations, including rotations and reflections, of a vector space with any non-degenerate or degenerate symmetric bilinear form. We propose a weight-sharing parametrization technique that takes into account the fundamental structures and operations of geometric algebras. Due to this technique, GLGENN architecture is parameter-light and has less tendency to overfitting than baseline equivariant models. GLGENN outperforms or matches competitors on several benchmarking equivariant tasks, including estimation of an equivariant function and a convex hull experiment, while using significantly fewer optimizable parameters.
Authors: Geonwoo Cho, Jaegyun Im, Jihwan Lee, Hojun Yi, Sejin Kim, Sundong Kim
Abstract: Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates tasks with high learning potential, while a student learns a robust policy from this evolving curriculum. Existing UED methods typically measure learning potential via regret, the gap between optimal and current performance, approximated solely by value-function loss. Building on these approaches, we introduce the transition-prediction error as an additional term in our regret approximation. To capture how training on one task affects performance on others, we further propose a lightweight metric called Co-Learnability. By combining these two measures, we present Transition-aware Regret Approximation with Co-learnability for Environment Design (TRACED). Empirical evaluations show that TRACED produces curricula that improve zero-shot generalization over strong baselines across multiple benchmarks. Ablation studies confirm that the transition-prediction error drives rapid complexity ramp-up and that Co-Learnability delivers additional gains when paired with the transition-prediction error. These results demonstrate how refined regret approximation and explicit modeling of task relationships can be leveraged for sample-efficient curriculum design in UED. Project Page: https://geonwoo.me/traced/
Authors: Chandra Sekhar Mukherjee, Joonyoung Bae, Jiapeng Zhang
Abstract: In this paper, we provide a novel perspective on the underlying structure of real-world data with ground-truth clusters via characterization of an abundantly observed yet often overlooked density-geometry correlation, that manifests itself as a multi-layered manifold structure. We leverage this correlation to design CoreSPECT (Core Space Projection based Enhancement of Clustering Techniques), a general framework that improves the performance of generic clustering algorithms. Our framework boosts the performance of clustering algorithms by applying them to strategically selected regions, then extending the partial partition to a complete partition for the dataset using a novel neighborhood graph based multi-layer propagation procedure. We provide initial theoretical support of the functionality of our framework under the assumption of our model, and then provide large-scale real-world experiments on 19 datasets that include standard image datasets as well as genomics datasets. We observe two notable improvements. First, CoreSPECT improves the NMI of K-Means by 20% on average, making it competitive to (and in some cases surpassing) the state-of-the-art manifold-based clustering algorithms, while being orders of magnitude faster. Secondly, our framework boosts the NMI of HDBSCAN by more than 100% on average, making it competitive to the state-of-the-art in several cases without requiring the true number of clusters and hyper-parameter tuning. The overall ARI improvements are higher.
Authors: Zinan Ling, Yi Shi, Brett McKinney, Da Yan, Yang Zhou, Bo Hui
Abstract: Generating novel and functional protein sequences is critical to a wide range of applications in biology. Recent advancements in conditional diffusion models have shown impressive empirical performance in protein generation tasks. However, reliable generations of protein remain an open research question in de novo protein design, especially when it comes to conditional diffusion models. Considering the biological function of a protein is determined by multi-level structures, we propose a novel multi-level conditional diffusion model that integrates both sequence-based and structure-based information for efficient end-to-end protein design guided by specified functions. By generating representations at different levels simultaneously, our framework can effectively model the inherent hierarchical relations between different levels, resulting in an informative and discriminative representation of the generated protein. We also propose a Protein-MMD, a new reliable evaluation metric, to evaluate the quality of generated protein with conditional diffusion models. Our new metric is able to capture both distributional and functional similarities between real and generated protein sequences while ensuring conditional consistency. We experiment with the benchmark datasets, and the results on conditional protein generation tasks demonstrate the efficacy of the proposed generation framework and evaluation metric.
Authors: Yang Xiao, Gen Li, Jie Ji, Ruimeng Ye, Xiaolong Ma, Bo Hui
Abstract: Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning algorithms, unlearning in sparse models has not yet been well studied. In this paper, we empirically find that the deleted data has an impact on the pruned topology in a sparse model. Motivated by the observation and the right to be forgotten, we define a new terminology ``un-pruning" to eliminate the impact of deleted data on model pruning. Then we propose an un-pruning algorithm to approximate the pruned topology driven by retained data. We remark that any existing unlearning algorithm can be integrated with the proposed un-pruning workflow and the error of un-pruning is upper-bounded in theory. Also, our un-pruning algorithm can be applied to both structured sparse models and unstructured sparse models. In the experiment, we further find that Membership Inference Attack (MIA) accuracy is unreliable for assessing whether a model has forgotten deleted data, as a small change in the amount of deleted data can produce arbitrary MIA results. Accordingly, we devise new performance metrics for sparse models to evaluate the success of un-pruning. Lastly, we conduct extensive experiments to verify the efficacy of un-pruning with various pruning methods and unlearning algorithms. Our code is released at https://github.com/NKUShaw/SparseModels .
Authors: Zachary T. Rewolinski, Bin Yu
Abstract: Data science is a pillar of artificial intelligence (AI), which is transforming nearly every domain of human activity, from the social and physical sciences to engineering and medicine. While data-driven findings in AI offer unprecedented power to extract insights and guide decision-making, many are difficult or impossible to replicate. A key reason for this challenge is the uncertainty introduced by the many choices made throughout the data science life cycle (DSLC). Traditional statistical frameworks often fail to account for this uncertainty. The Predictability-Computability-Stability (PCS) framework for veridical (truthful) data science offers a principled approach to addressing this challenge throughout the DSLC. This paper presents an updated and streamlined PCS workflow, tailored for practitioners and enhanced with guided use of generative AI. We include a running example to display the PCS framework in action, and conduct a related case study which showcases the uncertainty in downstream predictions caused by judgment calls in the data cleaning stage.
Authors: Jiayi Chen, Jing Li, Guiling Wang
Abstract: Reinforcement Learning (RL) has shown significant promise in automated portfolio management; however, effectively balancing risk and return remains a central challenge, as many models fail to adapt to dynamically changing market conditions. We propose Meta-controlled Agents for a Risk-aware System (MARS), a novel framework addressing this through a multi-agent, risk-aware approach. MARS replaces monolithic models with a Heterogeneous Agent Ensemble, where each agent's unique risk profile is enforced by a Safety-Critic network to span behaviors from capital preservation to aggressive growth. A high-level Meta-Adaptive Controller (MAC) dynamically orchestrates this ensemble, shifting reliance between conservative and aggressive agents to minimize drawdown during downturns while seizing opportunities in bull markets. This two-tiered structure leverages behavioral diversity rather than explicit feature engineering to ensure a disciplined portfolio robust across market regimes. Experiments on major international indexes confirm that our framework significantly reduces maximum drawdown and volatility while maintaining competitive returns.
Authors: Runze Zhao, Yue Yu, Ruhan Wang, Chunfeng Huang, Dongruo Zhou
Abstract: Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability to adapt to varying levels of problem difficulty remains poorly understood. In this work, we investigate the instance-dependent behavior of CTRL and introduce a simple, model-based algorithm built on maximum likelihood estimation (MLE) with a general function approximator. Unlike existing approaches that estimate system dynamics directly, our method estimates the state marginal density to guide learning. We establish instance-dependent performance guarantees by deriving a regret bound that scales with the total reward variance and measurement resolution. Notably, the regret becomes independent of the specific measurement strategy when the observation frequency adapts appropriately to the problem's complexity. To further improve performance, our algorithm incorporates a randomized measurement schedule that enhances sample efficiency without increasing measurement cost. These results highlight a new direction for designing CTRL algorithms that automatically adjust their learning behavior based on the underlying difficulty of the environment.
Authors: Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino, Paolo Mori
Abstract: Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, we identify and analyze two main GRPO issues: (i) the token-level penalization, where valuable tokens shared across different responses receive contradictory feedback signals, leading to conflicting gradient updates that can reduce their likelihood; and (ii) the policy collapse, where negatively rewarded completions may penalize confident responses and shift model decisions toward unlikely tokens, destabilizing training process. To address these issues we introduce GTPO (Group-relative Trajectory-based Policy Optimization), which prevents conflicting gradients on valuable tokens by skipping negative updates while amplifying positive ones and filters out completions whose entropy exceeds a provable threshold, to prevent policy collapse. Unlike GRPO, GTPO does not rely on KL-divergence regularization, eliminating the need for a reference model during training, while still ensuring greater training stability and improved performance, as validated through multiple experiments on GSM8K, MATH, AIME 2024, AIME 2025 and AMC 2023.
Authors: Francesco Vitale, Tommaso Zoppi, Francesco Flammini, Nicola Mazzocca
Abstract: Ensuring the resilience of computer-based railways is increasingly crucial to account for uncertainties and changes due to the growing complexity and criticality of those systems. Although their software relies on strict verification and validation processes following well-established best-practices and certification standards, anomalies can still occur at run-time due to residual faults, system and environmental modifications that were unknown at design-time, or other emergent cyber-threat scenarios. This paper explores run-time control-flow anomaly detection using process mining to enhance the resilience of ERTMS/ETCS L2 (European Rail Traffic Management System / European Train Control System Level 2). Process mining allows learning the actual control flow of the system from its execution traces, thus enabling run-time monitoring through online conformance checking. In addition, anomaly localization is performed through unsupervised machine learning to link relevant deviations to critical system components. We test our approach on a reference ERTMS/ETCS L2 scenario, namely the RBC/RBC Handover, to show its capability to detect and localize anomalies with high accuracy, efficiency, and explainability.
Authors: Maya M. Martirossyan, Thomas Egg, Philipp Hoellmer, George Karypis, Mark Transtrum, Adrian Roitberg, Mingjie Liu, Richard G. Hennig, Ellad B. Tadmor, Stefano Martiniani
Abstract: Generative models for materials, especially inorganic crystals, hold potential to transform the theoretical prediction of novel compounds and structures. Advancement in this field depends on robust benchmarks and minimal, information-rich datasets that enable meaningful model evaluation. This paper critically examines common datasets and reported metrics for a crystal structure prediction task$\unicode{x2014}$generating the most likely structures given the chemical composition of a material. We focus on three key issues: First, materials datasets should contain unique crystal structures; for example, we show that the widely-utilized carbon-24 dataset only contains $\approx$40% unique structures. Second, materials datasets should not be split randomly if polymorphs of many different compositions are numerous, which we find to be the case for the perov-5 and MP-20 datasets. Third, benchmarks can mislead if used uncritically, e.g., reporting a match rate metric without considering the structural variety exhibited by identical building blocks. To address these oft-overlooked issues, we introduce several fixes. We provide revised versions of the carbon-24 dataset: one with duplicates removed, one deduplicated and split by number of atoms $N$, one with enantiomorphs, and two containing only identical structures but with different unit cells. We also propose new splits for datasets with polymorphs, ensuring that polymorphs are grouped within each split subset, setting a more sensible standard for benchmarking model performance. Finally, we present METRe and cRMSE, new model evaluation metrics that can correct existing issues with the match rate metric.
Authors: Sam McCallum, Kamran Arora, James Foster
Abstract: Deep Equilibrium Models (DEQs) are an interesting class of implicit model where the model output is implicitly defined as the fixed point of a learned function. These models have been shown to outperform explicit (fixed-depth) models in large-scale tasks by trading many deep layers for a single layer that is iterated many times. However, gradient calculation through DEQs is approximate. This often leads to unstable training dynamics and requires regularisation or many function evaluations to fix. Here, we introduce Reversible Deep Equilibrium Models (RevDEQs) that allow for exact gradient calculation, no regularisation and far fewer function evaluations than DEQs. We show that RevDEQs significantly improve performance on language modelling and image classification tasks against comparable implicit and explicit models.
Authors: Sameep Chattopadhyay, Nikhil Karamchandani, Sharayu Moharir
Abstract: Online learning to rank (OLTR) plays a critical role in information retrieval and machine learning systems, with a wide range of applications in search engines and content recommenders. However, despite their extensive adoption, the susceptibility of OLTR algorithms to coordinated adversarial attacks remains poorly understood. In this work, we present a novel framework for attacking some of the widely used OLTR algorithms. Our framework is designed to promote a set of target items so that they appear in the list of top-K recommendations for T - o(T) rounds, while simultaneously inducing linear regret in the learning algorithm. We propose two novel attack strategies: CascadeOFA for CascadeUCB1 and PBMOFA for PBM-UCB . We provide theoretical guarantees showing that both strategies require only O(log T) manipulations to succeed. Additionally, we supplement our theoretical analysis with empirical results on real-world data.
Authors: Juan Sebastian Rojas, Chi-Guhn Lee
Abstract: Continual reinforcement learning (continual RL) seeks to formalize the notions of lifelong learning and endless adaptation in RL. In particular, the aim of continual RL is to develop RL agents that can maintain a careful balance between retaining useful information and adapting to new situations. To date, continual RL has been explored almost exclusively through the lens of risk-neutral decision-making, in which the agent aims to optimize the expected long-run performance. In this work, we present the first formal theoretical treatment of continual RL through the lens of risk-aware decision-making, in which the behaviour of the agent is directed towards optimizing a measure of long-run performance beyond the mean. In particular, we show that the classical theory of risk measures, widely used as a theoretical foundation in non-continual risk-aware RL, is, in its current form, incompatible with continual learning. Then, building on this insight, we extend risk measure theory into the continual setting by introducing a new class of ergodic risk measures that are compatible with continual learning. Finally, we provide a case study of risk-aware continual learning, along with empirical results, which show the intuitive appeal of ergodic risk measures in continual settings.
Authors: Duc Kieu, Kien Do, Tuan Hoang, Thao Minh Le, Tung Kieu, Dang Nguyen, Thin Nguyen
Abstract: Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen in training, limiting their practicality and excluding many cross-domain mappings. We introduce universal MDT (UMDT), a generalization of MDT that seeks to translate between any pair of $K$ domains using only $K-1$ paired datasets with a central domain. To tackle this problem, we propose Diffusion Router (DR), a unified diffusion-based framework that models all central$\leftrightarrow$non-central translations with a single noise predictor conditioned on the source and target domain labels. DR enables indirect non-central translations by routing through the central domain. We further introduce a novel scalable learning strategy with a variational-bound objective and an efficient Tweedie refinement procedure to support direct non-central mappings. Through evaluation on three large-scale UMDT benchmarks, DR achieves state-of-the-art results for both indirect and direct translations, while lowering sampling cost and unlocking novel tasks such as sketch$\leftrightarrow$segmentation. These results establish DR as a scalable and versatile framework for universal translation across multiple domains.
Authors: Lukas Eisenmann, Alena Br\"andle, Zahra Monfared, Daniel Durstewitz
Abstract: Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent renaissance with improved training algorithms and architectural designs. Understanding why and how trained RNNs produce their behavior is important for scientific and medical applications, and explainable AI more generally. An RNN's dynamical repertoire depends on the topological and geometrical properties of its state space. Stable and unstable manifolds of periodic points play a particularly important role: They dissect a dynamical system's state space into different basins of attraction, and their intersections lead to chaotic dynamics with fractal geometry. Here we introduce a novel algorithm for detecting these manifolds, with a focus on piecewise-linear RNNs (PLRNNs) employing rectified linear units (ReLUs) as their activation function. We demonstrate how the algorithm can be used to trace the boundaries between different basins of attraction, and hence to characterize multistability, a computationally important property. We further show its utility in finding so-called homoclinic points, the intersections between stable and unstable manifolds, and thus establish the existence of chaos in PLRNNs. Finally we show for an empirical example, electrophysiological recordings from a cortical neuron, how insights into the underlying dynamics could be gained through our method.
Authors: Salah Eddine Choutri, Prajwal Chauhan, Othmane Mazhar, Saif Eddin Jabari
Abstract: The Monte Carlo-type Neural Operator (MCNO) introduces a framework for learning solution operators of one-dimensional partial differential equations (PDEs) by directly learning the kernel function and approximating the associated integral operator using a Monte Carlo-type approach. Unlike Fourier Neural Operators (FNOs), which rely on spectral representations and assume translation-invariant kernels, MCNO makes no such assumptions. The kernel is represented as a learnable tensor over sampled input-output pairs, and sampling is performed once, uniformly at random from a discretized grid. This design enables generalization across multiple grid resolutions without relying on fixed global basis functions or repeated sampling during training, while an interpolation step maps between arbitrary input and output grids to further enhance flexibility. Experiments on standard 1D PDE benchmarks show that MCNO achieves competitive accuracy with efficient computational cost. We also provide a theoretical analysis proving that the Monte Carlo estimator yields a bounded bias and variance under mild regularity assumptions. This result holds in any spatial dimension, suggesting that MCNO may extend naturally beyond one-dimensional problems. More broadly, this work explores how Monte Carlo-type integration can be incorporated into neural operator frameworks for continuous-domain PDEs, providing a theoretically supported alternative to spectral methods (such as FNO) and to graph-based Monte Carlo approaches (such as the Graph Kernel Neural Operator, GNO).
Authors: Howard Chen, Noam Razin, Karthik Narasimhan, Danqi Chen
Abstract: Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this phenomenon, we systematically compare the forgetting patterns of two widely adopted post-training methods: supervised fine-tuning (SFT) and reinforcement learning (RL). Our experiments reveal a consistent trend across LM families (Llama, Qwen) and tasks (instruction following, general knowledge, and arithmetic reasoning): RL leads to less forgetting than SFT while achieving comparable or higher target task performance. To investigate the cause for this difference, we consider a simplified setting in which the LM is modeled as a mixture of two distributions, one corresponding to prior knowledge and the other to the target task. We identify that the mode-seeking nature of RL, which stems from its use of on-policy data, enables keeping prior knowledge intact when learning the target task. We then verify this insight by demonstrating that the use on-policy data underlies the robustness of RL to forgetting in practical settings, as opposed to other algorithmic choices such as the KL regularization or advantage estimation. Lastly, as a practical implication, our results highlight the potential of mitigating forgetting using approximately on-policy data, which can be substantially more efficient to obtain than fully on-policy data.
Authors: Arthur Chen, Zuxin Liu, Jianguo Zhang, Akshara Prabhakar, Zhiwei Liu, Shelby Heinecke, Silvio Savarese, Victor Zhong, Caiming Xiong
Abstract: Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch between their pre-training and test-time conditions. This challenge stems from two distinct failure modes: a syntactic misunderstanding of environment-specific components like observation formats, and a semantic misunderstanding of state-transition dynamics, which are only revealed at test time. To address these issues, we propose two distinct and complementary strategies for adapting LLM agents by leveraging environment-specific information available during deployment. First, an online distributional adaptation method parameterizes environmental nuances by learning a lightweight adaptation vector that biases the model's output distribution, enabling rapid alignment with an environment response format. Second, a deployment-time dynamics grounding method employs a persona-driven exploration phase to systematically probe and learn the environment's causal dynamics before task execution, equipping the agent with a nonparametric world model. We evaluate these strategies across diverse agentic benchmarks, including function calling and web navigation. Our empirical results show the effectiveness of both strategies across all benchmarks with minimal computational cost. We find that dynamics grounding is particularly effective in complex environments where unpredictable dynamics pose a major obstacle, demonstrating a robust path toward more generalizable and capable LLM-based agents. For example, on the WebArena multi-site split, this method increases the agent's success rate from 2% to 23%.
Authors: Andrea Cavallo, Ayushman Raghuvanshi, Sundeep Prabhakar Chepuri, Elvin Isufi
Abstract: Machine learning and data processing techniques relying on covariance information are widespread as they identify meaningful patterns in unsupervised and unlabeled settings. As a prominent example, Principal Component Analysis (PCA) projects data points onto the eigenvectors of their covariance matrix, capturing the directions of maximum variance. This mapping, however, falls short in two directions: it fails to capture information in low-variance directions, relevant when, e.g., the data contains high-variance noise; and it provides unstable results in low-sample regimes, especially when covariance eigenvalues are close. CoVariance Neural Networks (VNNs), i.e., graph neural networks using the covariance matrix as a graph, show improved stability to estimation errors and learn more expressive functions in the covariance spectrum than PCA, but require training and operate in a labeled setup. To get the benefits of both worlds, we propose Covariance Scattering Transforms (CSTs), deep untrained networks that sequentially apply filters localized in the covariance spectrum to the input data and produce expressive hierarchical representations via nonlinearities. We define the filters as covariance wavelets that capture specific and detailed covariance spectral patterns. We improve CSTs' computational and memory efficiency via a pruning mechanism, and we prove that their error due to finite-sample covariance estimations is less sensitive to close covariance eigenvalues compared to PCA, improving their stability. Our experiments on age prediction from cortical thickness measurements on 4 datasets collecting patients with neurodegenerative diseases show that CSTs produce stable representations in low-data settings, as VNNs but without any training, and lead to comparable or better predictions w.r.t. more complex learning models.
Authors: Tom Yuviler, Dana Drachsler-Cohen
Abstract: Despite recent advances in LLMs, the task of code generation is still challenging. To cope, code selection algorithms select the best program from multiple programs generated by an LLM. However, existing algorithms can fail to identify the correct program, either because they can misidentify nonequivalent programs or because they rely on an LLM and assume it always correctly determines the output for every input. We present ExPairT-LLM, an exact learning algorithm for code selection that selects a program by posing to an LLM oracle two new types of queries: pairwise membership and pairwise equivalence. These queries are simpler for LLMs and enable ExPairT-LLM to identify the correct program through a tournament, which is robust to some LLM mistakes. We evaluate ExPairT-LLM on four popular code datasets. Its pass@1 (success rate) outperforms the state-of-the-art code selection algorithm on average by +13.0% and up to +27.1%. It also improves the pass@1 of LLMs performing complex reasoning by +24.0%.
Authors: Rui Ding, Rodrigo Pires Ferreira, Yuxin Chen, Junhong Chen
Abstract: We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our framework instantiates a locally deployable DR instance that integrates local retrieval-augmented generation with large language model reasoners, enhanced by a Deep Tree of Research (DToR) mechanism that adaptively expands and prunes research branches to maximize coverage, depth, and coherence. We systematically evaluate across 27 nanomaterials/device topics using a large language model (LLM)-as-judge rubric with five web-enabled state-of-the-art models as jurors. In addition, we conduct dry-lab validations on five representative tasks, where human experts use domain simulations (e.g., density functional theory, DFT) to verify whether DR-agent proposals are actionable. Results show that our DR agent produces reports with quality comparable to--and often exceeding--those of commercial systems (ChatGPT-5-thinking/o3/o4-mini-high Deep Research) at a substantially lower cost, while enabling on-prem integration with local data and tools.
Authors: Haojin Yang, Rui Hu, Zequn Sun, Rui Zhou, Yujun Cai, Yiwei Wang
Abstract: Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their outputs. Mainstream denoising strategies include Standard Diffusion and BlockDiffusion. Standard Diffusion performs global denoising without restricting the update range, often finalizing incomplete context and causing premature end-of-sequence predictions. BlockDiffusion updates fixed-size blocks in a preset order, but its rigid structure can break apart coherent semantic units and disrupt reasoning. We present WavefrontDiffusion, a dynamic decoding approach that expands a wavefront of active tokens outward from finalized positions. This adaptive process follows the natural flow of semantic structure while keeping computational cost equal to block-based methods. Across four benchmarks in reasoning and code generation, WavefrontDiffusion achieves state-of-the-art performance while producing outputs with higher semantic fidelity, showing the value of adaptive scheduling for more coherent and efficient generation.
Authors: Locke Cai, Ivan Provilkov
Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations that remain under-utilized for reasoning-focused training. We introduce RARO (Relativistic Adversarial Reasoning Optimization) that learns strong reasoning capabilities from only expert demonstrations via Inverse Reinforcement Learning. Our method sets up an adversarial interaction between a policy (generator) and a relativistic critic (discriminator): the policy learns to mimic expert answers, while the critic learns to compare and distinguish between policy and expert answers. Our method trains both the policy and the critic jointly and continuously via RL, and we identify the key stabilization techniques required for robust learning. Empirically, RARO significantly outperforms strong verifier-free baselines on all of our evaluation tasks -- Countdown, DeepMath, and Poetry Writing -- and enjoys the same robust scaling trends as RL on verifiable tasks. These results demonstrate that our method effectively elicits strong reasoning performance from expert demonstrations alone, enabling robust reasoning learning even when task-specific verifiers are unavailable.
Authors: Chujie Zheng, Kai Dang, Bowen Yu, Mingze Li, Huiqiang Jiang, Junrong Lin, Yuqiong Liu, Hao Lin, Chencan Wu, Feng Hu, 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: 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: 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: Krishnendu S. Tharakan, Carlo Fischione
Abstract: Wireless connectivity promises to unshackle virtual reality (VR) experiences, allowing users to engage from anywhere, anytime. However, delivering seamless, high-quality, real-time VR video wirelessly is challenging due to the stringent quality of experience requirements, low latency constraints, and limited VR device capabilities. This paper addresses these challenges by introducing a novel decentralized multi task fair federated learning (DMTFL) based caching that caches and prefetches each VR user's field of view (FOV) at base stations (BSs) based on the caching strategies tailored to each BS. In federated learning (FL) in its naive form, often biases toward certain users, and a single global model fails to capture the statistical heterogeneity across users and BSs. In contrast, the proposed DMTFL algorithm personalizes content delivery by learning individual caching models at each BS. These models are further optimized to perform well under any target distribution, while providing theoretical guarantees via Rademacher complexity and a probably approximately correct (PAC) bound on the loss. Using a realistic VR head-tracking dataset, our simulations demonstrate the superiority of our proposed DMTFL algorithm compared to baseline algorithms.
Authors: Shuyuan Wu, Feifei Wang, Yuan Gao, Rui Wang, Hansheng Wang
Abstract: In decentralized federated learning (DFL), the presence of abnormal clients, often caused by noisy or poisoned data, can significantly disrupt the learning process and degrade the overall robustness of the model. Previous methods on this issue often require a sufficiently large number of normal neighboring clients or prior knowledge of reliable clients, which reduces the practical applicability of DFL. To address these limitations, we develop here a novel adaptive DFL (aDFL) approach for robust estimation. The key idea is to adaptively adjust the learning rates of clients. By assigning smaller rates to suspicious clients and larger rates to normal clients, aDFL mitigates the negative impact of abnormal clients on the global model in a fully adaptive way. Our theory does not put any stringent conditions on neighboring nodes and requires no prior knowledge. A rigorous convergence analysis is provided to guarantee the oracle property of aDFL. Extensive numerical experiments demonstrate the superior performance of the aDFL method.
Authors: Feiyu Wang, Xinyu Tan, Bokai Huang, Yihao Zhang, Guoan Wang, Peizhuang Cong, Tong Yang
Abstract: Large language models (LLMs) have revolutionized artificial intelligence, yet their massive memory and computational demands necessitate aggressive quantization, increasingly pushing representations toward the theoretical limit of a single bit. While complex-valued LLMs, such as iFairy, offer a superior chance for low-bit representation compared to real-valued counterparts, they require training from scratch, preventing the utilization of the vast ecosystem of pre-trained real-valued foundation models. Here we present Fairy2i, a universal framework that transforms pre-trained real-valued layers into an equivalent widely-linear complex form, enabling extremely low-bit quantization while reusing existing checkpoints. By proving a lossless mathematical equivalence between real and widely-linear maps, we convert standard Transformers into the complex domain and employ a phase-aware quantization scheme with a highly efficient codebook of fourth roots of unity. Furthermore, we introduce a recursive residual quantization mechanism that iteratively minimizes quantization error, allowing inference to proceed via efficient multiplication-free accumulation. We demonstrate that Fairy2i restores the performance of LLaMA-2 7B at an effective 2-bit precision to levels nearly comparable with full-precision baselines, significantly outperforming state-of-the-art real-valued binary and ternary quantization methods. This work bridges the gap between the representational efficiency of complex-valued arithmetic and the practical utility of pre-trained models, paving a new way for efficient inference on commodity hardware.
Authors: Jacopo Lenti, Fabrizio Silvestri, Gianmarco De Francisci Morales
Abstract: Despite the frequent use of agent-based models (ABMs) for studying social phenomena, parameter estimation remains a challenge, often relying on costly simulation-based heuristics. This work uses variational inference to estimate the parameters of an opinion dynamics ABM, by transforming the estimation problem into an optimization task that can be solved directly. Our proposal relies on probabilistic generative ABMs (PGABMs): we start by synthesizing a probabilistic generative model from the ABM rules. Then, we transform the inference process into an optimization problem suitable for automatic differentiation. In particular, we use the Gumbel-Softmax reparameterization for categorical agent attributes and stochastic variational inference for parameter estimation. Furthermore, we explore the trade-offs of using variational distributions with different complexity: normal distributions and normalizing flows. We validate our method on a bounded confidence model with agent roles (leaders and followers). Our approach estimates both macroscopic (bounded confidence intervals and backfire thresholds) and microscopic ($200$ categorical, agent-level roles) more accurately than simulation-based and MCMC methods. Consequently, our technique enables experts to tune and validate their ABMs against real-world observations, thus providing insights into human behavior in social systems via data-driven analysis.
Authors: Fabio Maresca, Filippo Grazioli, Antonio Albanese, Vincenzo Sciancalepore, Gianpiero Negri, Xavier Costa-Perez
Abstract: The tremendous hype around autonomous driving is eagerly calling for emerging and novel technologies to support advanced mobility use cases. As car manufactures keep developing SAE level 3+ systems to improve the safety and comfort of passengers, traffic authorities need to establish new procedures to manage the transition from human-driven to fully-autonomous vehicles while providing a feedback-loop mechanism to fine-tune envisioned autonomous systems. Thus, a way to automatically profile autonomous vehicles and differentiate those from human-driven ones is a must. In this paper, we present a fully-fledged framework that monitors active vehicles using camera images and state information in order to determine whether vehicles are autonomous, without requiring any active notification from the vehicles themselves. Essentially, it builds on the cooperation among vehicles, which share their data acquired on the road feeding a machine learning model to identify autonomous cars. We extensively tested our solution and created the NexusStreet dataset, by means of the CARLA simulator, employing an autonomous driving control agent and a steering wheel maneuvered by licensed drivers. Experiments show it is possible to discriminate the two behaviors by analyzing video clips with an accuracy of 80%, which improves up to 93% when the target state information is available. Lastly, we deliberately degraded the state to observe how the framework performs under non-ideal data collection conditions.
Authors: Andreas Kosmas Kakolyris, Dimosthenis Masouros, Petros Vavaroutsos, Sotirios Xydis, Dimitrios Soudris
Abstract: As Large Language Models (LLMs) gain traction, their reliance on power-hungry GPUs places ever-increasing energy demands, raising environmental and monetary concerns. Inference dominates LLM workloads, presenting a critical challenge for providers: minimizing energy costs under Service-Level Objectives (SLOs) that ensure optimal user experience. In this paper, we present \textit{throttLL'eM}, a framework that reduces energy consumption while meeting SLOs through the use of instance and GPU frequency scaling. \textit{throttLL'eM} features mechanisms that project future KV cache usage and batch size. Leveraging a Machine-Learning (ML) model that receives these projections as inputs, \textit{throttLL'eM} manages performance at the iteration level to satisfy SLOs with reduced frequencies and instance sizes. We show that the proposed ML model achieves $R^2$ scores greater than 0.97 and miss-predicts performance by less than 1 iteration per second on average. Experimental results on LLM inference traces show that \textit{throttLL'eM} achieves up to 43.8\% lower energy consumption and an energy efficiency improvement of at least $1.71\times$ under SLOs, when compared to NVIDIA's Triton server.
Authors: Tianyu Gao, Alexander Wettig, Howard Yen, Danqi Chen
Abstract: We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information. We first establish a reliable evaluation protocol to guide model development -- instead of perplexity or simple needle-in-a-haystack (NIAH) tests, we use a broad set of long-context downstream tasks, and we evaluate models after SFT as this better reveals long-context abilities. Supported by our robust evaluations, we run thorough experiments to decide the data mix for continued pre-training, the instruction tuning dataset, and many other design choices such as position extrapolation. We find that (1) code repositories and books are excellent sources of long data, but it is crucial to combine them with high-quality short-context data; (2) training with a sequence length beyond the evaluation length boosts long-context performance; (3) for SFT, using only short instruction datasets yields strong performance on long-context tasks. Our final model, ProLong-8B, which is initialized from Llama-3 and trained on 40B tokens, demonstrates state-of-the-art long-context performance among similarly sized models at a length of 128K. ProLong outperforms Llama-3.1-8B-Instruct on the majority of long-context tasks despite using only 5% as many tokens during long-context training. Additionally, ProLong can effectively process up to 512K tokens, one of the longest context windows of publicly available LMs.
Authors: Xintian Sun, Benji Peng, Charles Zhang, Fei Jin, Qian Niu, Junyu Liu, Keyu Chen, Ming Li, Pohsun Feng, Ziqian Bi, Ming Liu, Xinyuan Song, Yichao Zhang
Abstract: Remote sensing has evolved from simple image acquisition to complex systems capable of integrating and processing visual and textual data. This review examines the development and application of multi-modal language models (MLLMs) in remote sensing, focusing on their ability to interpret and describe satellite imagery using natural language. We cover the technical underpinnings of MLLMs, including dual-encoder architectures, Transformer models, self-supervised and contrastive learning, and cross-modal integration. The unique challenges of remote sensing data--varying spatial resolutions, spectral richness, and temporal changes--are analyzed for their impact on MLLM performance. Key applications such as scene description, object detection, change detection, text-to-image retrieval, image-to-text generation, and visual question answering are discussed to demonstrate their relevance in environmental monitoring, urban planning, and disaster response. We review significant datasets and resources supporting the training and evaluation of these models. Challenges related to computational demands, scalability, data quality, and domain adaptation are highlighted. We conclude by proposing future research directions and technological advancements to further enhance MLLM utility in remote sensing.
Authors: Yichen Li, Chicheng Zhang
Abstract: Imitation learning (IL) is a paradigm for learning sequential decision making policies from experts, leveraging offline demonstrations, interactive annotations, or both. Recent advances show that when annotation cost is tallied per trajectory, Behavior Cloning (BC) which relies solely on offline demonstrations cannot be improved in general, leaving limited conditions for interactive methods such as DAgger to help. We revisit this conclusion and prove that when the annotation cost is measured per state, algorithms using interactive annotations can provably outperform BC. Specifically: (1) we show that Stagger, a one sample per round variant of DAgger, provably beats BC under low recovery cost settings; (2) we initiate the study of hybrid IL where the agent learns from offline demonstrations and interactive annotations. We propose Warm Stagger whose learning guarantee is not much worse than using either data source alone. Furthermore, motivated by compounding error and cold start problem in imitation learning practice, we give an MDP example in which Warm Stagger has significant better annotation cost; (3) experiments on MuJoCo continuous control tasks confirm that, with modest cost ratio between interactive and offline annotations, interactive and hybrid approaches consistently outperform BC. To the best of our knowledge, our work is the first to highlight the benefit of state wise interactive annotation and hybrid feedback in imitation learning.
Authors: Ved G. Shah, Alex Gagliano, Konstantin Malanchev, Gautham Narayan, Alex I. Malz, The LSST Dark Energy Science Collaboration
Abstract: We present ORACLE, the first hierarchical deep-learning model for real-time, context-aware classification of transient and variable astrophysical phenomena. ORACLE is a recurrent neural network with Gated Recurrent Units (GRUs), and has been trained using a custom hierarchical cross-entropy loss function to provide high-confidence classifications along an observationally-driven taxonomy with as little as a single photometric observation. Contextual information for each object, including host galaxy photometric redshift, offset, ellipticity and brightness, is concatenated to the light curve embedding and used to make a final prediction. Training on $\sim$0.5M events from the Extended LSST Astronomical Time-Series Classification Challenge, we achieve a top-level (Transient vs Variable) macro-averaged precision of 0.96 using only 1 day of photometric observations after the first detection in addition to contextual information, for each event; this increases to $>$0.99 once 64 days of the light curve has been obtained, and 0.83 at 1024 days after first detection for 19-way classification (including supernova sub-types, active galactic nuclei, variable stars, microlensing events, and kilonovae). We also compare ORACLE with other state-of-the-art classifiers and report comparable performance for the 19-way classification task, in addition to delivering accurate top-level classifications much earlier. The code and model weights used in this work are publicly available at our associated GitHub repository (https://github.com/uiucsn/ELAsTiCC-Classification).
Authors: Lingdong Kong, Xiang Xu, Youquan Liu, Jun Cen, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Abstract: Recent advancements in vision foundation models (VFMs) have revolutionized visual perception in 2D, yet their potential for 3D scene understanding, particularly in autonomous driving applications, remains underexplored. In this paper, we introduce LargeAD, a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets. Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds to generate high-quality contrastive samples. This alignment facilitates cross-modal representation learning, enhancing the semantic consistency between 2D and 3D data. We introduce several key innovations: (i) VFM-driven superpixel generation for detailed semantic representation, (ii) a VFM-assisted contrastive learning strategy to align multimodal features, (iii) superpoint temporal consistency to maintain stable representations across time, and (iv) multi-source data pretraining to generalize across various LiDAR configurations. Our approach achieves substantial gains over state-of-the-art methods in linear probing and fine-tuning for LiDAR-based segmentation and object detection. Extensive experiments on 11 large-scale multi-sensor datasets highlight our superior performance, demonstrating adaptability, efficiency, and robustness in real-world autonomous driving scenarios.
Authors: Yu-Chen Lin, Sanat Sharma, Hari Manikandan, Jayant Kumar, Tracy Holloway King, Jing Zheng
Abstract: In this work, we investigate how small language models (SLMs) can be scaled to support multimodal search and recommendation use cases while remaining efficient enough for real-time, resource-constrained deployments. We present a framework that combines upside-down reinforcement learning with synthetic data distillation from a large language model (Llama-3) to train a 100M-parameter GPT-2 model for multitask prompt generation. Despite being up to 80 times smaller than state-of-the-art large language models (LLMs), our SLM achieves relevance and diversity scores within 6% of competitive baselines such as Llama-3 8B, Qwen3 8B, and Ministral 8B. These results demonstrate that SLMs can effectively handle multimodal search and recommendation tasks, while dramatically reducing inference latency and memory overhead. Our study highlights the potential of lightweight models as practical engines for scalable multimodal discovery, bridging the gap between cutting-edge research and real-world multimodal applications such as media recommendations and creative content generation.
Authors: Thomas Monninger, Md Zafar Anwar, Stanislaw Antol, Steffen Staab, Sihao Ding
Abstract: Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned Bird's-Eye View (BEV) encoders are commonly used to combine a set of camera images from multiple views into one joint latent BEV grid. Traditionally, from this latent space, an intermediate raster map is predicted, providing dense spatial supervision but requiring post-processing into the desired vectorized form. More recent models directly derive infrastructure elements as polylines using vectorized map decoders, providing instance-level information. Our approach, Augmentation Map Network (AugMapNet), proposes latent BEV feature grid augmentation, a novel technique that significantly enhances the latent BEV representation. AugMapNet combines vector decoding and dense spatial supervision more effectively than existing architectures while remaining easy to integrate compared to other hybrid approaches. It additionally benefits from extra processing on its latent BEV features. Experiments on nuScenes and Argoverse2 datasets demonstrate significant improvements on vectorized map prediction of up to 13.3% over the StreamMapNet baseline on 60 m range and greater improvements on larger ranges. We confirm transferability by applying our method to another baseline, SQD-MapNet, and find similar improvements. A detailed analysis of the latent BEV grid confirms a more structured latent space of AugMapNet and shows the value of our novel concept beyond pure performance improvement. The code can be found at https://github.com/tmonnin/augmapnet
Authors: St\'ephane Lhaut, Holger Rootz\'en, Johan Segers
Abstract: Economically responsible mitigation of multivariate extreme risks -- extreme rainfall in a large area, huge variations of many stock prices, widespread breakdowns in transportation systems -- requires estimates of the probabilities that such risks will materialize in the future. This paper develops a new method, Wasserstein--Aitchison Generative Adversarial Networks (WA-GAN) to, which provides simulated values of $d$-dimensional multivariate extreme events and which can hence be used to give estimates of such probabilities. The main hypothesis is that, after transforming the observations to the unit-Pareto scale, their distribution is regularly varying in the sense that the distributions of their radial and angular components (with respect to the $L_1$-norm) converge and become asymptotically independent as the radius gets large. The method is a combination of standard extreme value analysis modeling of the tails of the marginal distributions with nonparametric GAN modeling of the angular distribution. For the latter, the angular values are transformed to Aitchison coordinates in a full $(d-1)$-dimensional linear space, and a Wasserstein GAN is trained on these coordinates and used to generate new values. A reverse transformation is then applied to these values and gives simulated values on the original data scale. Our method is applied to simulated data and to a financial data set from the Kenneth French Data Library. The method shows good performance compared to other existing methods in the literature, both in terms of capturing the dependence structure of the extremes in the data and in generating accurate new extremes.
Authors: Seyed Bagher Hashemi Natanzi, Zhicong Zhu, Bo Tang
Abstract: Adaptive beam switching is essential for mission-critical military and commercial 6G networks but faces major challenges from high carrier frequencies, user mobility, and frequent blockages. While existing machine learning (ML) solutions often focus on maximizing instantaneous throughput, this can lead to unstable policies with high signaling overhead. This paper presents an online Deep Reinforcement Learning (DRL) framework designed to learn an operationally stable policy. By equipping the DRL agent with an enhanced state representation that includes blockage history, and a stability-centric reward function, we enable it to prioritize long-term link quality over transient gains. Validated in a challenging 100-user scenario using the Sionna library, our agent achieves throughput comparable to a reactive Multi-Armed Bandit (MAB) baseline. Specifically, our proposed framework improves link stability by approximately 43% compared to a vanilla DRL approach, achieving operational reliability competitive with MAB while maintaining high data rates. This work demonstrates that by reframing the optimization goal towards operational stability, DRL can deliver efficient, reliable, and real-time beam management solutions for next-generation mission-critical networks.
Authors: Asterios Tsiourvas, Wei Sun, Georgia Perakis
Abstract: LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models. Prior approaches typically adopt a decoupled strategy, where the metrics are first predicted and the model is then selected based on these estimates. This setup is prone to compounding errors and often relies on full-feedback data, where each query is evaluated by all candidate models, which is costly to obtain and maintain in practice. In contrast, we learn from observational data, which records only the outcome of the model actually deployed. We propose a causal end-to-end framework that learns routing policies by minimizing decision-making regret from observational data. To enable efficient optimization, we introduce two theoretically grounded surrogate objectives: a classification-based upper bound, and a softmax-weighted regret approximation shown to recover the optimal policy at convergence. We further extend our framework to handle heterogeneous cost preferences via an interval-conditioned architecture. Experiments on public benchmarks show that our method outperforms existing baselines, achieving state-of-the-art performance across different embedding models.
Authors: Alexandra Gonz\'alez, Xavier Franch, David Lo, Silverio Mart\'inez-Fern\'andez
Abstract: Context: Open-source Pre-Trained Models (PTMs) provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs to support the reliable identification and reuse of models for SE. Objective: To address this gap, we derive a taxonomy encompassing 147 SE tasks and apply an SE-oriented classification to PTMs in a popular open-source ML repository, Hugging Face (HF). Method: Our repository mining study followed a five-phase pipeline: (i) identification SE tasks from the literature; (ii) collection of PTM data from the HF API, including model card descriptions and metadata, and the abstracts of the associated arXiv papers; (iii) text processing to ensure consistency; (iv) a two-phase validation of SE relevance, involving humans and LLM assistance, supported by five pilot studies with human annotators and a generalization test; (v) and data analysis. This process yielded a curated catalogue of 2,205 SE PTMs. Results: We find that most SE PTMs target code generation and coding, emphasizing implementation over early or late development stages. In terms of ML tasks, text generation dominates within SE PTMs. Notably, the number of SE PTMs has increased markedly since 2023 Q2, while evaluation remains limited: only 9.6% report benchmark results, mostly scoring below 50%. Conclusions: Our catalogue reveals documentation and transparency gaps, highlights imbalances across SDLC phases, and provides a foundation for automated SE scenarios, such as the sampling and selection of suitable PTMs.
Authors: Emil Biju, Shayan Talaei, Zhemin Huang, Mohammadreza Pourreza, Azalia Mirhoseini, Amin Saberi
Abstract: Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce SPRINT, a novel post-training and inference-time framework designed to enable LRMs to dynamically identify and exploit opportunities for parallelization during their reasoning process. SPRINT incorporates an innovative data curation pipeline that reorganizes natural language reasoning trajectories into structured rounds of long-horizon planning and parallel execution. By fine-tuning LRMs on a small amount of such curated data, the models learn to dynamically identify independent subtasks within extended reasoning processes and effectively execute them in parallel. Through extensive evaluations, we demonstrate that models fine-tuned with the SPRINT framework match the performance of reasoning models on complex domains such as mathematics while generating up to 39% fewer sequential tokens on problems requiring more than 8,000 output tokens. Finally, we observe consistent results transferred to two out-of-distribution tasks, namely GPQA and Countdown, with up to 45% and 65% reduction in average sequential tokens respectively for longer reasoning trajectories, while matching the performance of the fine-tuned reasoning model.
Authors: Tuomas Oikarinen, Ge Yan, Akshay Kulkarni, Tsui-Wei Weng
Abstract: Interpreting individual neurons or directions in activation space is an important topic in mechanistic interpretability. Numerous automated interpretability methods have been proposed to generate such explanations, but it remains unclear how reliable these explanations are, and which methods produce the most accurate descriptions. While crowd-sourced evaluations are commonly used, existing pipelines are noisy, costly, and typically assess only the highest-activating inputs, leading to unreliable results. In this paper, we introduce two techniques to enable cost-effective and accurate crowdsourced evaluation of automated interpretability methods beyond top activating inputs. First, we propose Model-Guided Importance Sampling (MG-IS) to select the most informative inputs to show human raters. In our experiments, we show this reduces the number of inputs needed to reach the same evaluation accuracy by ~13x. Second, we address label noise in crowd-sourced ratings through Bayesian Rating Aggregation (BRAgg), which allows us to reduce the number of ratings per input required to overcome noise by ~3x. Together, these techniques reduce the evaluation cost by ~40x, making large-scale evaluation feasible. Finally, we use our methods to conduct a large scale crowd-sourced study comparing recent automated interpretability methods for vision networks.
Authors: Aloni Cohen
Abstract: Are there any conditions under which a generative model's outputs are guaranteed not to infringe the copyrights of its training data? This is the question of "provable copyright protection" first posed by Vyas, Kakade, and Barak (ICML 2023). They define near access-freeness (NAF) and propose it as sufficient for protection. This paper revisits the question and establishes new foundations for provable copyright protection -- foundations that are firmer both technically and legally. First, we show that NAF alone does not prevent infringement. In fact, NAF models can enable verbatim copying, a blatant failure of copy protection that we dub being tainted. Then, we introduce our blameless copy protection framework for defining meaningful guarantees, and instantiate it with clean-room copy protection. Clean-room copy protection allows a user to control their risk of copying by behaving in a way that is unlikely to copy in a counterfactual clean-room setting. Finally, we formalize a common intuition about differential privacy and copyright by proving that DP implies clean-room copy protection when the dataset is golden, a copyright deduplication requirement.
Authors: Jean-Baptiste Fermanian (IMAG, IROKO), Mohamed Hebiri (LAMA), Joseph Salmon (IMAG, IROKO)
Abstract: Conformal prediction methods are statistical tools designed to quantify uncertainty and generate predictive sets with guaranteed coverage probabilities. This work introduces an innovative refinement to these methods for classification tasks, specifically tailored for scenarios where multiple observations (multi-inputs) of a single instance are available at prediction time. Our approach is particularly motivated by applications in citizen science, where multiple images of the same plant or animal are captured by individuals. Our method integrates the information from each observation into conformal prediction, enabling a reduction in the size of the predicted label set while preserving the required class-conditional coverage guarantee. The approach is based on the aggregation of conformal p-values computed from each observation of a multi-input. By exploiting the exact distribution of these p-values, we propose a general aggregation framework using an abstract scoring function, encompassing many classical statistical tools. Knowledge of this distribution also enables refined versions of standard strategies, such as majority voting. We evaluate our method on simulated and real data, with a particular focus on Pl@ntNet, a prominent citizen science platform that facilitates the collection and identification of plant species through user-submitted images.
Authors: James Kotary, Himanshu Sharma, Ethan King, Draguna Vrabie, Ferdinando Fioretto, Jan Drgona
Abstract: Learning to Optimize (L2O) is a subfield of machine learning (ML) in which ML models are trained to solve parametric optimization problems. The general goal is to learn a fast approximator of solutions to constrained optimization problems, as a function of their defining parameters. Prior L2O methods focus almost entirely on single-level programs, in contrast to the bilevel programs, whose constraints are themselves expressed in terms of optimization subproblems. Bilevel programs have numerous important use cases but are notoriously difficult to solve, particularly under stringent time demands. This paper proposes a framework for learning to solve a broad class of challenging bilevel optimization problems, by leveraging modern techniques for differentiation through optimization problems. The framework is illustrated on an array of synthetic bilevel programs, as well as challenging control system co-design problems, showing how neural networks can be trained as efficient approximators of parametric bilevel optimization.
Authors: Gabriele Formis, Amanda Ericson, Stefan Forsstrom, Kyi Thar, Gianluca Cena, Stefano Scanzio
Abstract: The increasing need for robustness, reliability, and determinism in wireless networks for industrial and mission-critical applications is the driver for the growth of new innovative methods. The study presented in this work makes use of machine learning techniques to predict channel quality in a Wi-Fi network in terms of the frame delivery ratio. Predictions can be used proactively to adjust communication parameters at runtime and optimize network operations for industrial applications. Methods including convolutional neural networks and long short-term memory were analyzed on datasets acquired from a real Wi-Fi setup across multiple channels. The models were compared in terms of prediction accuracy and computational complexity. Results show that the frame delivery ratio can be reliably predicted, and convolutional neural networks, although slightly less effective than other models, are more efficient in terms of CPU usage and memory consumption. This enhances the model's usability on embedded and industrial systems.
Authors: Ishraq Khan, Assad Chowdary, Sharoz Haseeb, Urvish Patel, Yousuf Zaii
Abstract: Large Language Models (LLMs) have advanced code generation and software automation but remain constrained by inference-time context and lack structured reasoning over code, leaving debugging largely unsolved. While Claude 4.5 Opus achieves 74.40% on SWE-bench Verified and Gemini 3 Pro reaches 76.2%, both models remain below 20% on real multi-file debugging tasks. We introduce Kodezi Chronos-1, a language model purpose-built for debugging that integrates Adaptive Graph-Guided Retrieval to navigate codebases up to 10 million lines (92% precision, 85% recall), Persistent Debug Memory trained on over 15 million sessions, and a seven-layer fix-test-refine architecture. On 5,000 real-world scenarios, Chronos-1 achieves 67.3% +/- 2.1% fix accuracy compared to 14.2% +/- 1.3% for Claude 4.1 Opus and 13.8% +/- 1.2% for GPT-4.1 (Cohen's d = 3.87). On SWE-bench Lite, Chronos-1 reaches a state-of-the-art 80.33% resolution rate (241 of 300), outperforming the next best system by 20 points and achieving repository-specific highs of 96.1% on Sympy and 90.4% on Django. Chronos-1 reduces debugging time by 40% and iterations by 65%, resolving complex multi-file and cross-repository bugs that require temporal analysis. Limitations remain for hardware-dependent and dynamic language errors, and Chronos-1 will be available in Kodezi OS in Q4 2025 and via API in Q1 2026.
Authors: Trevor Harris, Yan Liu
Abstract: Operator models are regression algorithms between Banach spaces of functions. They have become an increasingly critical tool for spatiotemporal forecasting and physics emulation, especially in high-stakes scenarios where robust, calibrated uncertainty quantification is required. We introduce Local Sliced Conformal Inference (LSCI), a distribution-free framework for generating function-valued, locally adaptive prediction sets for operator models. We prove finite-sample validity and derive a data-dependent upper bound on the coverage gap under local exchangeability. On synthetic Gaussian-process tasks and real applications (air quality monitoring, energy demand forecasting, and weather prediction), LSCI yields tighter sets with stronger adaptivity compared to conformal baselines. We also empirically demonstrate robustness against biased predictions and certain out-of-distribution noise regimes.
Authors: Anjiang Wei, Tianran Sun, Yogesh Seenichamy, Hang Song, Anne Ouyang, Azalia Mirhoseini, Ke Wang, Alex Aiken
Abstract: GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating large language model (LLM) training and serving, yet attaining high performance typically requires extensive manual tuning. Compiler-based systems reduce some of this burden, but still demand substantial manual design and engineering effort. Recently, researchers have explored using LLMs for GPU kernel generation, though prior work has largely focused on translating high-level PyTorch modules into CUDA code. In this work, we introduce Astra, the first LLM-based multi-agent system for GPU kernel optimization. Unlike previous approaches, Astra starts from existing CUDA implementations extracted from SGLang, a widely deployed framework for serving LLMs, rather than treating PyTorch modules as the specification. Within Astra, specialized LLM agents collaborate through iterative code generation, testing, profiling, and planning to produce kernels that are both correct and high-performance. On kernels from SGLang, Astra achieves an average speedup of 1.32x using zero-shot prompting with OpenAI o4-mini. A detailed case study further demonstrates that LLMs can autonomously apply loop transformations, optimize memory access patterns, exploit CUDA intrinsics, and leverage fast math operations to yield substantial performance gains. Our work highlights multi-agent LLM systems as a promising new paradigm for GPU kernel optimization. Our code is publicly available at https://github.com/Anjiang-Wei/Astra.
Authors: Jessica Gronsbell, Vidul Ayakulangara Panickan, Doudou Zhou, Chris Lin, Thomas Charlon, Chuan Hong, Xin Xiong, Linshanshan Wang, Jianhui Gao, Shirley Zhou, Yuan Tian, Yaqi Shi, Ziming Gan, Tianxi Cai
Abstract: Despite the growing availability of Electronic Health Record (EHR) data, researchers often face substantial barriers in effectively using these data for translational research due to their complexity, heterogeneity, and lack of standardized tools and documentation. To address this critical gap, we introduce PEHRT, a common pipeline for harmonizing EHR data for translational research. PEHRT is a comprehensive, ready-to-use resource that includes open-source code, visualization tools, and detailed documentation to streamline the process of preparing EHR data for analysis. The pipeline provides tools to harmonize structured and unstructured EHR data to standardized ontologies to ensure consistency across diverse coding systems. In the presence of unmapped or heterogeneous local codes, PEHRT further leverages representation learning and pre-trained language models to generate robust embeddings that capture semantic relationships across sites to mitigate heterogeneity and enable integrative downstream analyses. PEHRT also supports cross-institutional co-training through shared representations, allowing participating sites to collaboratively refine embeddings and enhance generalizability without sharing individual-level data. The framework is data model-agnostic and can be seamlessly deployed across diverse healthcare systems to produce interoperable, research-ready datasets. By lowering the technical barriers to EHR-based research, PEHRT empowers investigators to transform raw clinical data into reproducible, analysis-ready resources for discovery and innovation.
Authors: Tim Broedermannn, Christos Sakaridis, Luigi Piccinelli, Wim Abbeloos, Luc Van Gool
Abstract: Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data uniformly across the spatial extent of the input, which hinders performance when faced with challenging conditions. By contrast, we propose a novel depth-guided multimodal fusion method that upgrades condition-aware fusion by integrating depth information. Our network, DGFusion, poses multimodal segmentation as a multi-task problem, utilizing the lidar measurements, which are typically available in outdoor sensor suites, both as one of the model's inputs and as ground truth for learning depth. Our corresponding auxiliary depth head helps to learn depth-aware features, which are encoded into spatially varying local depth tokens that condition our attentive cross-modal fusion. Together with a global condition token, these local depth tokens dynamically adapt sensor fusion to the spatially varying reliability of each sensor across the scene, which largely depends on depth. In addition, we propose a robust loss for our depth, which is essential for learning from lidar inputs that are typically sparse and noisy in adverse conditions. Our method achieves state-of-the-art panoptic and semantic segmentation performance on the challenging MUSES and DeLiVER datasets. Code and models will be available at https://github.com/timbroed/DGFusion
Authors: Mariam Mahran, Katharina Simbeck
Abstract: Large Language Models (LLMs) are increasingly used for educational support, yet their response quality varies depending on the language of interaction. This paper presents an automated multilingual pipeline for generating, solving, and evaluating math problems aligned with the German K-10 curriculum. We generated 628 math exercises and translated them into English, German, and Arabic. Three commercial LLMs (GPT-4o-mini, Gemini 2.5 Flash, and Qwen-plus) were prompted to produce step-by-step solutions in each language. A held-out panel of LLM judges, including Claude 3.5 Haiku, evaluated solution quality using a comparative framework. Results show a consistent gap, with English solutions consistently rated highest, and Arabic often ranked lower. These findings highlight persistent linguistic bias and the need for more equitable multilingual AI systems in education.
Authors: Kevin Bradley Dsouza, Graham Alexander Watt, Yuri Leonenko, Juan Moreno-Cruz
Abstract: Collective action problems, which require aligning individual incentives with collective goals, are classic examples of Ill-Structured Problems (ISPs). For an individual agent, the causal links between local actions and global outcomes are unclear, stakeholder objectives often conflict, and no single, clear algorithm can bridge micro-level choices with macro-level welfare. We present ECHO-MIMIC, a general computational framework that converts this global complexity into a tractable, Well-Structured Problem (WSP) for each agent by discovering executable heuristics and persuasive rationales. The framework operates in two stages: ECHO (Evolutionary Crafting of Heuristics from Outcomes) evolves snippets of Python code that encode candidate behavioral policies, while MIMIC (Mechanism Inference \& Messaging for Individual-to-Collective Alignment) evolves companion natural language messages that motivate agents to adopt those policies. Both phases employ a large-language-model-driven evolutionary search: the LLM proposes diverse and context-aware code or text variants, while population-level selection retains those that maximize collective performance in a simulated environment. We demonstrate this framework on two distinct ISPs: a canonical agricultural landscape management problem and a carbon-aware EV charging time slot usage problem. Results show that ECHO-MIMIC discovers high-performing heuristics compared to baselines and crafts tailored messages that successfully align simulated agent behavior with system-level goals. By coupling algorithmic rule discovery with tailored communication, ECHO-MIMIC transforms the cognitive burden of collective action into a implementable set of agent-level instructions, making previously ill-structured problems solvable in practice and opening a new path toward scalable, adaptive policy design.
Authors: Charles L. Wang
Abstract: This paper presents MathBode, a dynamic diagnostic for mathematical reasoning in large language models (LLMs). Instead of one-shot accuracy, MathBode treats each parametric problem as a system: we drive a single parameter sinusoidally and fit first-harmonic responses of model outputs and exact solutions. This yields interpretable, frequency-resolved metrics -- gain (amplitude tracking) and phase (lag) -- that form Bode-style fingerprints. Across five closed-form families (linear solve, ratio/saturation, compound interest, 2x2 linear systems, similar triangles), the diagnostic surfaces systematic low-pass behavior and growing phase lag that accuracy alone obscures. We compare several models against a symbolic baseline that calibrates the instrument ($G \approx 1$, $\phi \approx 0$). Results separate frontier from mid-tier models on dynamics, providing a compact, reproducible protocol that complements standard benchmarks with actionable measurements of reasoning fidelity and consistency. We open-source the dataset and code to enable further research and adoption.
Authors: Lukas Rauch, Ren\'e Heinrich, Houtan Ghaffari, Lukas Miklautz, Ilyass Moummad, Bernhard Sick, Christoph Scholz
Abstract: Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursuing state-of-the-art on AudioSet. A key reason is that global pooling creates an information bottleneck causing linear probes to misrepresent the embedding quality: The $\texttt{cls}$-token discards crucial token information about dispersed, localized events in audio. This weakness is rooted in the mismatch between the pretraining objective (globally) and the downstream task (localized). Across a comprehensive benchmark of 13 datasets and 6 spectrogram-based encoders, we investigate the global pooling bottleneck. We introduce binarized prototypical probes: a lightweight and simple pooling method that learns prototypes to perform class-wise information aggregation. Despite its simplicity, our method notably outperforms linear and attentive probing. Our work establishes probing as a competitive and efficient paradigm for evaluating audio SSL models, challenging the reliance on costly fine-tuning.
Authors: Fardis Nadimi, Payam Abdisarabshali, Jacob Chakareski, Nicholas Mastronarde, Seyyedali Hosseinalipour
Abstract: In this work, we introduce Fed-Span: \textit{\underline{fed}erated learning with \underline{span}ning aggregation over low Earth orbit (LEO) satellite constellations}. Fed-Span aims to address critical challenges inherent to distributed learning in dynamic satellite networks, including intermittent satellite connectivity, heterogeneous computational capabilities of satellites, and time-varying satellites' datasets. At its core, Fed-Span leverages minimum spanning tree (MST) and minimum spanning forest (MSF) topologies to introduce spanning model aggregation and dispatching processes for distributed learning. To formalize Fed-Span, we offer a fresh perspective on MST/MSF topologies by formulating them through a set of continuous constraint representations (CCRs), thereby integrating these topologies into a distributed learning framework for satellite networks. Using these CCRs, we obtain the energy consumption and latency of operations in Fed-Span. Moreover, we derive novel convergence bounds for Fed-Span, accommodating its key system characteristics and degrees of freedom (i.e., tunable parameters). Finally, we propose a comprehensive optimization problem that jointly minimizes model prediction loss, energy consumption, and latency of {Fed-Span}. We unveil that this problem is NP-hard and develop a systematic approach to transform it into a geometric programming formulation, solved via successive convex optimization with performance guarantees. Through evaluations on real-world datasets, we demonstrate that Fed-Span outperforms existing methods, with faster model convergence, greater energy efficiency, and reduced latency.
Authors: Mingyuan Zhou, Yi Gu, Huangjie Zheng, Liangchen Song, Guande He, Yizhe Zhang, Wenze Hu, Yinfei Yang
Abstract: Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a distinct framework, has since been shown to be theoretically equivalent to diffusion under Gaussian assumptions, raising the question of whether distillation techniques such as score distillation transfer directly. We provide a simple derivation -- based on Bayes' rule and conditional expectations -- that unifies Gaussian diffusion and flow matching without relying on ODE/SDE formulations. Building on this view, we extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models, including SANA, SD3-Medium, SD3.5-Medium/Large, and FLUX.1-dev, all with DiT backbones. Experiments show that, with only modest flow-matching- and DiT-specific adjustments, SiD works out of the box across these models, in both data-free and data-aided settings, without requiring teacher finetuning or architectural changes. This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models, resolving prior concerns about stability and soundness and unifying acceleration techniques across diffusion- and flow-based generators. A project page is available at https://yigu1008.github.io/SiD-DiT.
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: Amirreza Tanevardi, Pooria Abbas Rad Moghadam, Seyed Mohammad Eshtehardian, Sajjad Amini, Babak Khalaj
Abstract: Diffusion models have emerged as powerful generative priors for solving inverse imaging problems. However, their practical deployment is hindered by the substantial computational cost of slow, multi-step sampling. Although Consistency Models (CMs) address this limitation by enabling high-quality generation in only one or a few steps, their direct application to inverse problems has remained largely unexplored. This paper introduces a modified consistency sampling framework specifically designed for inverse problems. The proposed approach regulates the sampler's stochasticity through a measurement-consistency mechanism that leverages the degradation operator, thereby enforcing fidelity to the observed data while preserving the computational efficiency of consistency-based generation. Comprehensive experiments on the Fashion-MNIST and LSUN Bedroom datasets demonstrate consistent improvements across both perceptual and pixel-level metrics, including the Fr\'echet Inception Distance (FID), Kernel Inception Distance (KID), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM), compared with baseline consistency and diffusion-based sampling methods. The proposed method achieves competitive or superior reconstruction quality with only a small number of sampling steps.
Authors: Zia Badar
Abstract: Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a non-differentiable approach and for learning; the derivative is usually set manually in backpropogation which make the learning ability of algorithm questionable, our approach is not just differentiable, we also provide proof of convergence of our approach to the optimal neural network. Second previous work in shift/logrithmic quantization either have avoided activation quantization along with weight quantization or achieved less accuracy. Learning logrithmic quantize values of form $2^n$ requires the quantization function can scale to more than 1 bit quantization which is another benifit of our quantization that it provides $n$ bits quantization as well. Our approach when tested with image classification task using imagenet dataset, resnet18 and weight quantization only achieves less than 1 percent accuracy compared to full precision accuracy while taking only 15 epochs to train using shift bit quantization and achieves comparable to SOTA approaches accuracy in both weight and activation quantization using shift bit quantization in 15 training epochs with slightly higher(only higher cpu instructions) inference cost compared to 1 bit quantization(without logrithmic quantization) and not requiring any higher precision multiplication.
Authors: Dan Hendrycks, Dawn Song, Christian Szegedy, Honglak Lee, Yarin Gal, Erik Brynjolfsson, Sharon Li, Andy Zou, Lionel Levine, Bo Han, Jie Fu, Ziwei Liu, Jinwoo Shin, Kimin Lee, Mantas Mazeika, Long Phan, George Ingebretsen, Adam Khoja, Cihang Xie, Olawale Salaudeen, Matthias Hein, Kevin Zhao, Alexander Pan, David Duvenaud, Bo Li, Steve Omohundro, Gabriel Alfour, Max Tegmark, Kevin McGrew, Gary Marcus, Jaan Tallinn, Eric Schmidt, Yoshua Bengio
Abstract: The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.
Authors: Shruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Larry Lindsey, Rutika Moharir, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham, Charles Maalouf, Joseph Yitan Cheng
Abstract: Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish clearly unsafe content from borderline cases, leading to problematic over-blocking or under-refusal of genuinely harmful content. We present Vision Language Safety Understanding (VLSU), a comprehensive framework to systematically evaluate multimodal safety through fine-grained severity classification and combinatorial analysis across 17 distinct safety patterns. Using a multi-stage pipeline with real-world images and human annotation, we construct a large-scale benchmark of 8,187 samples spanning 15 harm categories. Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures: while models achieve 90%-plus accuracy on clear unimodal safety signals, performance degrades substantially to 20-55% when joint image-text reasoning is required to determine the safety label. Most critically, 34% of errors in joint image-text safety classification occur despite correct classification of the individual modalities, further demonstrating absent compositional reasoning capabilities. Additionally, we find that models struggle to balance refusing unsafe content while still responding to borderline cases that deserve engagement. For example, we find that instruction framing can reduce the over-blocking rate on borderline content from 62.4% to 10.4% in Gemini-1.5, but only at the cost of under-refusing on unsafe content with refusal rate dropping from 90.8% to 53.9%. Overall, our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models, and provides a critical test bed to enable the next milestones in research on robust vision-language safety.
Authors: Zhenzhong Wang, Xin Zhang, Jun Liao, Min Jiang
Abstract: Multiphase flow simulation is critical in science and engineering but incurs high computational costs due to complex field discontinuities and the need for high-resolution numerical meshes. While Neural Operators (NOs) offer an efficient alternative for solving Partial Differential Equations (PDEs), they struggle with two core challenges unique to multiphase systems: spectral bias caused by spatial heterogeneity at phase interfaces, and the persistent scarcity of expensive, high-resolution field data. This work introduces the Interface Information Aware Neural Operator (IANO), a novel architecture that mitigates these issues by leveraging readily obtainable interface data (e.g., topology and position). Interface data inherently contains the high-frequency features not only necessary to complement the physical field data, but also help with spectral bias. IANO incorporates an interface-aware function encoding mechanism to capture dynamic coupling, and a geometry-aware positional encoding method to enhance spatial fidelity for pointwise super-resolution. Empirical results across multiple multiphase flow cases demonstrate that IANO achieves significant accuracy improvements (up to $\sim$10\%) over existing NO baselines. Furthermore, IANO exhibits superior generalization capabilities in low-data and noisy settings, confirming its utility for practical, data-efficient $\text{AI}$-based multiphase flow simulations.
Authors: Jiayi Zhang, Yiran Peng, Fanqi Kong, Cheng Yang, Yifan Wu, Zhaoyang Yu, Jinyu Xiang, Jianhao Ruan, Jinlin Wang, Maojia Song, HongZhang Liu, Xiangru Tang, Bang Liu, Chenglin Wu, Yuyu Luo
Abstract: Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution. Cross-environment learning has remained largely unmeasured: there is no standard collection of controllable, heterogeneous environments, nor a unified way to represent how agents learn. We address these gaps in two steps. First, we propose AutoEnv, an automated framework that treats environments as factorizable distributions over transitions, observations, and rewards, enabling low-cost (4.12 USD on average) generation of heterogeneous worlds. Using AutoEnv, we construct AutoEnv-36, a dataset of 36 environments with 358 validated levels, on which seven language models achieve 12-49% normalized reward, demonstrating the challenge of AutoEnv-36. Second, we formalize agent learning as a component-centric process driven by three stages of Selection, Optimization, and Evaluation applied to an improvable agent component. Using this formulation, we design eight learning methods and evaluate them on AutoEnv-36. Empirically, the gain of any single learning method quickly decrease as the number of environments increases, revealing that fixed learning methods do not scale across heterogeneous environments. Environment-adaptive selection of learning methods substantially improves performance but exhibits diminishing returns as the method space expands. These results highlight both the necessity and the current limitations of agent learning for scalable cross-environment generalization, and position AutoEnv and AutoEnv-36 as a testbed for studying cross-environment agent learning. The code is avaiable at https://github.com/FoundationAgents/AutoEnv.
Authors: Rui Tong
Abstract: Generative modeling is typically framed as learning mapping rules, but from an observer's perspective without access to these rules, the task becomes disentangling the geometric support from the probability distribution. We propose that continuum percolation is uniquely suited to this support analysis, as the sampling process effectively projects high-dimensional density estimation onto a geometric counting problem on the support. In this work, we establish a rigorous correspondence between the topological phase transitions of random geometric graphs and the underlying data manifold in high-dimensional space. By analyzing the relationship between our proposed Percolation Shift metric and FID, we show that this metric captures structural pathologies, such as implicit mode collapse, where standard statistical metrics fail. Finally, we translate this topological phenomenon into a differentiable loss function that guides training. Experimental results confirm that this approach not only prevents manifold shrinkage but also fosters a form of synergistic improvement, where topological stability becomes a prerequisite for sustained high fidelity in both static generation and sequential decision making.
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 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: 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/tree/main/research/CuES.
URLs: https://github.com/modelscope/AgentEvolver/tree/main/research/CuES.
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. 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. Our code is available at http://github.com/mit-han-lab/fouroversix.
Authors: Vedanta Thapar, Renaud Lambiotte, George T. Cantwell
Abstract: We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding. The FRTD assigns a probability mass function to each node, allowing us to define a distance between any pair of nodes using standard metrics for discrete distributions. We present several arguments to motivate the FRTD embedding. First, we show that FRTDs are strictly more informative than eigenvalue spectra, yet insufficient for complete graph identification, thus placing FRTD equivalence between cospectrality and isomorphism. Second, we argue that FRTD equivalence between nodes captures structural similarity. Third, we empirically demonstrate that the FRTD embedding outperforms manually designed graph metrics in network alignment tasks. Finally, we show that random networks that approximately match the FRTD of a desired target also preserve other salient features. Together these results demonstrate the FRTD as a simple and mathematically principled embedding for complex networks.