Authors: Uday Kumar Nidadala, Venkata Bhumika Guthi
Abstract: Horizon reduction is a common design strategy in offline reinforcement learning (RL), used to mitigate long-horizon credit assignment, improve stability, and enable scalable learning through truncated rollouts, windowed training, or hierarchical decomposition (Levine et al., 2020; Prudencio et al., 2023; Park et al., 2025). Despite recent empirical evidence that horizon reduction can improve scaling on challenging offline RL benchmarks, its theoretical implications remain underdeveloped (Park et al., 2025). In this paper, we show that horizon reduction can induce fundamental and irrecoverable information loss in offline RL. We formalize horizon reduction as learning from fixed-length trajectory segments and prove that, under this paradigm and any learning interface restricted to fixed-length trajectory segments, optimal policies may be statistically indistinguishable from suboptimal ones even with infinite data and perfect function approximation. Through a set of minimal counterexample Markov decision processes (MDPs), we identify three distinct structural failure modes: (i) prefix indistinguishability leading to identifiability failure, (ii) objective misspecification induced by truncated returns, and (iii) offline dataset support and representation aliasing. Our results establish necessary conditions under which horizon reduction can be safe and highlight intrinsic limitations that cannot be overcome by algorithmic improvements alone, complementing algorithmic work on conservative objectives and distribution shift that addresses a different axis of offline RL difficulty (Fujimoto et al., 2019; Kumar et al., 2020; Gulcehre et al., 2020).
Authors: Israk Hasan Jone, D. M. Rafiun Bin Masud, Promit Sarker, Sayed Fuad Al Labib, Nazmul Islam, Farhad Billah
Abstract: Shrimp is one of the most widely consumed aquatic species globally, valued for both its nutritional content and economic importance. Shrimp farming represents a significant source of income in many regions; however, like other forms of aquaculture, it is severely impacted by disease outbreaks. These diseases pose a major challenge to sustainable shrimp production. To address this issue, automated disease classification methods can offer timely and accurate detection. This research proposes a deep learning-based approach for the automated classification of shrimp diseases. A dataset comprising 1,149 images across four disease classes was utilized. Six pretrained deep learning models, ResNet50, EfficientNet, DenseNet201, MobileNet, ConvNeXt-Tiny, and Xception were deployed and evaluated for performance. The images background was removed, followed by standardized preprocessing through the Keras image pipeline. Fast Gradient Sign Method (FGSM) was used for enhancing the model robustness through adversarial training. While advanced augmentation strategies, including CutMix and MixUp, were implemented to mitigate overfitting and improve generalization. To support interpretability, and to visualize regions of model attention, post-hoc explanation methods such as Grad-CAM, Grad-CAM++, and XGrad-CAM were applied. Exploratory results demonstrated that ConvNeXt-Tiny achieved the highest performance, attaining a 96.88% accuracy on the test dataset. After 1000 iterations, the 99% confidence interval for the model is [0.953,0.971].
Authors: Julian Evan Chrisnanto, Salsabila Rahma Alia, Nurfauzi Fadillah, Yulison Herry Chrisnanto
Abstract: Simulating nonlinear reaction-diffusion dynamics on complex, non-Euclidean manifolds remains a fundamental challenge in computational morphogenesis, constrained by high-fidelity mesh generation costs and symplectic drift in discrete time-stepping schemes. This study introduces the Intrinsic-Metric Physics-Informed Neural Network (IM-PINN), a mesh-free geometric deep learning framework that solves partial differential equations directly in the continuous parametric domain. By embedding the Riemannian metric tensor into the automatic differentiation graph, our architecture analytically reconstructs the Laplace-Beltrami operator, decoupling solution complexity from geometric discretization. We validate the framework on a "Stochastic Cloth" manifold with extreme Gaussian curvature fluctuations ($K \in [-2489, 3580]$), where traditional adaptive refinement fails to resolve anisotropic Turing instabilities. Using a dual-stream architecture with Fourier feature embeddings to mitigate spectral bias, the IM-PINN recovers the "splitting spot" and "labyrinthine" regimes of the Gray-Scott model. Benchmarking against the Surface Finite Element Method (SFEM) reveals superior physical rigor: the IM-PINN achieves global mass conservation error of $\mathcal{E}_{mass} \approx 0.157$ versus SFEM's $0.258$, acting as a thermodynamically consistent global solver that eliminates mass drift inherent in semi-implicit integration. The framework offers a memory-efficient, resolution-independent paradigm for simulating biological pattern formation on evolving surfaces, bridging differential geometry and physics-informed machine learning.
Authors: Bharath Nunepalli
Abstract: Retrieval-augmented generation (RAG) introduces a practical control problem: retrieval depth and generation behavior must be chosen per query to satisfy service-level objectives (SLOs) such as cost, refusal rate, and hallucination risk. This work models per-query control as a small discrete action: choose a retrieval depth and a generation mode (guarded vs. auto), or refuse. An offline logged dataset is constructed from SQuAD 2.0 by executing each action and recording accuracy, token cost, hallucination/refusal indicators, and an SLO-weighted reward. Two simple policy-learning objectives are evaluated: supervised classification of the per-state best action (Argmax-CE) and a reward-weighted variant (Argmax-CE-WT). Across the evaluated settings, a strong fixed baseline (low k, guarded prompting) performs competitively; learned policies mainly provide additional cost savings under a quality-focused SLO and can exhibit refusal collapse under a cheap SLO when refusal is heavily rewarded. The contribution is a reproducible case study of SLO-aware control for RAG pipelines, emphasizing failure modes and reporting conventions rather than proposing a new retriever or language model.
Authors: Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec, Jean Ponce, Yann LeCun
Abstract: Building deep learning models that can reason about their environment requires capturing its underlying dynamics. Joint-Embedded Predictive Architectures (JEPA) provide a promising framework to model such dynamics by learning representations and predictors through a self-supervised prediction objective. However, their ability to support effective action planning remains limited. We propose an approach to enhance planning with JEPA world models by shaping their representation space so that the negative goal-conditioned value function for a reaching cost in a given environment is approximated by a distance (or quasi-distance) between state embeddings. We introduce a practical method to enforce this constraint during training and show that it leads to significantly improved planning performance compared to standard JEPA models on simple control tasks.
Authors: Ryan Shamim
Abstract: Modern AI inference systems treat transformer execution as mandatory, conflating model capability with execution necessity. We reframe inference as a control-plane decision problem: determining when execution is necessary versus when correctness can be preserved through alternative pathways. We introduce Meaning-First Execution (MFEE), a control-plane architecture implementing this framework, selectively invoking transformer inference only when required. MFEE operates as a gating layer above existing stacks without modifying models, weights, or parameters. Across 1,000 diverse prompts under deterministic decoding, MFEE achieves 78.1% execution reduction while maintaining 100% exact-match equivalence for invoked executions. Comparative evaluation reveals pattern-based routers achieve at most 53.3% avoidance with correctness failures, while MFEE reaches 100% avoidance with zero failures through semantic analysis. We prove this limitation via Theorem 1: any router operating solely on finite feature maps cannot simultaneously guarantee zero false skips and positive avoidance on feature-collision pairs. These results establish execution governance as a foundational layer in ML systems infrastructure, orthogonal to model-level optimization techniques.
Authors: Aayush Kumar
Abstract: Hallucinations hinder reliable question answering, especially in resource-constrained deployments where frontier-scale models or retrieval pipelines may be impractical. We present EdgeJury, a lightweight ensemble framework that improves truthfulness and robustness using only small instruction-tuned language models (3B-8B) suitable for serverless edge inference. EdgeJury orchestrates four stages: (1) parallel role-specialized generation, (2) anonymized cross-review with structured critiques and rankings, (3) chairman synthesis that integrates the strongest content while addressing flagged issues, and (4) claim-level consistency labeling based on inter-model agreement. On TruthfulQA (MC1), EdgeJury achieves 76.2% accuracy (95% CI: 72.8-79.6%), a +21.4% relative improvement over a single 8B baseline (62.8%), and outperforms standard baselines including self-consistency and majority voting under transparent compute accounting (total tokens and platform cost reported). On a 200-question adversarial EdgeCases set, EdgeJury yields +48.2% relative gains (95% CI: 44.0-52.4%). Manual analysis on 100 incorrect answers shows an approximately 55% reduction in factual hallucination errors versus the single-model baseline. Deployed on Cloudflare Workers AI, EdgeJury achieves 8.4 s median end-to-end latency, demonstrating that coordinated small-model ensembles can improve truthfulness on misconception-heavy QA benchmarks without external retrieval or proprietary large-model APIs.
Authors: Sameer Rahil, Zain Abdullah Ahmad, Talha Asif
Abstract: Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, statistical heterogeneity among clients, often manifested as non-IID label distributions, poses significant challenges to convergence and generalization. While Sharpness-Aware Minimization (SAM) has been introduced to FL to seek flatter, more robust minima, existing approaches typically apply a uniform perturbation radius across all clients, ignoring client-specific heterogeneity. In this work, we propose \textbf{FedSCAM} (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation), a novel algorithm that dynamically adjusts the SAM perturbation radius and aggregation weights based on client-specific heterogeneity scores. By calculating a heterogeneity metric for each client and modulating the perturbation radius inversely to this score, FedSCAM prevents clients with high variance from destabilizing the global model. Furthermore, we introduce a heterogeneity-aware weighted aggregation mechanism that prioritizes updates from clients that align with the global optimization direction. Extensive experiments on CIFAR-10 and Fashion-MNIST under various degrees of Dirichlet-based label skew demonstrate that FedSCAM achieves competitive performance among state-of-the-art baselines, including FedSAM, FedLESAM, etc. in terms of convergence speed and final test accuracy.
Authors: Yuchi Ma, Yawen Shen, Anu Swatantran, David B. Lobell
Abstract: Geospatial foundation models (GFMs) have emerged as a promising approach to overcoming the limitations in existing featurization methods. More recently, Google DeepMind has introduced AlphaEarth Foundation (AEF), a GFM pre-trained using multi-source EOs across continuous time. An annual and global embedding dataset is produced using AEF that is ready for analysis and modeling. The internal experiments show that AEF embeddings have outperformed operational models in 15 EO tasks without re-training. However, those experiments are mostly about land cover and land use classification. Applying AEF and other GFMs to agricultural monitoring require an in-depth evaluation in critical agricultural downstream tasks. There is also a lack of comprehensive comparison between the AEF-based models and traditional remote sensing (RS)-based models under different scenarios, which could offer valuable guidance for researchers and practitioners. This study addresses some of these gaps by evaluating AEF embeddings in three agricultural downstream tasks in the U.S., including crop yield prediction, tillage mapping, and cover crop mapping. Datasets are compiled from both public and private sources to comprehensively evaluate AEF embeddings across tasks at different scales and locations, and RS-based models are trained as comparison models. AEF-based models generally exhibit strong performance on all tasks and are competitive with purpose-built RS-based models in yield prediction and county-level tillage mapping when trained on local data. However, we also find several limitations in current AEF embeddings, such as limited spatial transferability compared to RS-based models, low interpretability, and limited time sensitivity. These limitations recommend caution when applying AEF embeddings in agriculture, where time sensitivity, generalizability, and interpretability is important.
Authors: Xidi Wang
Abstract: Can purely mechanical systems generate intelligent language? We prove that dissipative quantum dynamics with analytically tractable non-local context aggregation produce coherent text generation, while conservation laws cause fundamental failure. Employing Koopman operators with closed-form path integral propagators, we show irreversible computation fundamentally requires both controlled information dissipation and causal context aggregation. Spectral analysis reveals emergent eigenvalue structure, separating into decay modes (forgetting), growth modes (amplification), and neutral modes (preservation) -- the essential ingredients for directed information flow. Hamiltonian constraints force the elimination of these dissipative modes and degrading performance despite unchanged model capacity. This establishes language generation as dissipative quantum field theory, proving mechanical systems acquire intelligence through the combination of dissipation and non-locality, not through conservation.
Authors: Joey Chan, Huan Wang, Haoyu Pan, Wei Wu, Zirong Wang, Zhen Chen, Ershun Pan, Min Xie, Lifeng Xi
Abstract: Accurate forecasting of battery capacity fade is essential for the safety, reliability, and long-term efficiency of energy storage systems. However, the strong heterogeneity across cell chemistries, form factors, and operating conditions makes it difficult to build a single model that generalizes beyond its training domain. This work proposes a unified capacity forecasting framework that maintains robust performance across diverse chemistries and usage scenarios. We curate 20 public aging datasets into a large-scale corpus covering 1,704 cells and 3,961,195 charge-discharge cycle segments, spanning temperatures from $-5\,^{\circ}\mathrm{C}$ to $45\,^{\circ}\mathrm{C}$, multiple C-rates, and application-oriented profiles such as fast charging and partial cycling. On this corpus, we adopt a Time-Series Foundation Model (TSFM) backbone and apply parameter-efficient Low-Rank Adaptation (LoRA) together with physics-guided contrastive representation learning to capture shared degradation patterns. Experiments on both seen and deliberately held-out unseen datasets show that a single unified model achieves competitive or superior accuracy compared with strong per-dataset baselines, while retaining stable performance on chemistries, capacity scales, and operating conditions excluded from training. These results demonstrate the potential of TSFM-based architectures as a scalable and transferable solution for capacity degradation forecasting in real battery management systems.
Authors: Markus J. Buehler
Abstract: We introduce materiomusic as a generative framework linking the hierarchical structures of matter with the compositional logic of music. Across proteins, spider webs and flame dynamics, vibrational and architectural principles recur as tonal hierarchies, harmonic progressions, and long-range musical form. Using reversible mappings, from molecular spectra to musical tones and from three-dimensional networks to playable instruments, we show how sound functions as a scientific probe, an epistemic inversion where listening becomes a mode of seeing and musical composition becomes a blueprint for matter. These mappings excavate deep time: patterns originating in femtosecond molecular vibrations or billion-year evolutionary histories become audible. We posit that novelty in science and art emerges when constraints cannot be satisfied within existing degrees of freedom, forcing expansion of the space of viable configurations. Selective imperfection provides the mechanism restoring balance between coherence and adaptability. Quantitative support comes from exhaustive enumeration of all 2^12 musical scales, revealing that culturally significant systems cluster in a mid-entropy, mid-defect corridor, directly paralleling the Hall-Petch optimum where intermediate defect densities maximize material strength. Iterating these mappings creates productive collisions between human creativity and physics, generating new information as musical structures encounter evolutionary constraints. We show how swarm-based AI models compose music exhibiting human-like structural signatures such as small-world connectivity, modular integration, long-range coherence, suggesting a route beyond interpolation toward invention. We show that science and art are generative acts of world-building under constraint, with vibration as a shared grammar organizing structure across scales.
Authors: Clemens Damke, Eyke H\"ullermeier
Abstract: Graphs are commonly used in machine learning to model relationships between instances. Consider the task of predicting the political preferences of users in a social network; to solve this task one should consider, both, the features of each individual user and the relationships between them. However, oftentimes one is not interested in the label of a single instance but rather in the distribution of labels over a set of instances; e.g., when predicting the political preferences of users, the overall prevalence of a given opinion might be of higher interest than the opinion of a specific person. This label prevalence estimation task is commonly referred to as quantification learning (QL). Current QL methods for tabular data are typically based on the so-called prior probability shift (PPS) assumption which states that the label-conditional instance distributions should remain equal across the training and test data. In the graph setting, PPS generally does not hold if the shift between training and test data is structural, i.e., if the training data comes from a different region of the graph than the test data. To address such structural shifts, an importance sampling variant of the popular adjusted count quantification approach has previously been proposed. In this work, we extend the idea of structural importance sampling to the state-of-the-art KDEy quantification approach. We show that our proposed method adapts to structural shifts and outperforms standard quantification approaches.
Authors: Shivani Saini, Ramesh Kumar Vats, Arup Kumar Sahoo
Abstract: Recent advancements in physics-informed neural networks (PINNs) and their variants have garnered substantial focus from researchers due to their effectiveness in solving both forward and inverse problems governed by differential equations. In this research, a modified Auxiliary physics-informed neural network (A-PINN) framework with balanced adaptive optimizers is proposed for the analysis of structural vibration problems. In order to accurately represent structural systems, it is critical for capturing vibration phenomena and ensuring reliable predictive analysis. So, our investigations are crucial for gaining deeper insight into the robustness of scientific machine learning models for solving vibration problems. Further, to rigorously evaluate the performance of A-PINN, we conducted different numerical simulations to approximate the Euler-Bernoulli beam equations under the various scenarios. The numerical results substantiate the enhanced performance of our model in terms of both numerical stability and predictive accuracy. Our model shows improvement of at least 40% over the baselines.
Authors: Aditya Sreevatsa K, Arun Kumar Raveendran, Jesrael K Mani, Prakash G Shigli, Rajkumar Rangadore, Narayana Darapaneni, Anwesh Reddy Paduri
Abstract: SmartFlow is a multi-layered framework that integrates Reinforcement Learning and Agentic AI to address the dynamic rebalancing problem in urban bike-sharing services. Its architecture separates strategic, tactical, and communication functions for clarity and scalability. At the strategic level, a Deep Q-Network (DQN) agent, trained in a high-fidelity simulation of New Yorks Citi Bike network, learns robust rebalancing policies by modelling the challenge as a Markov Decision Process. These high-level strategies feed into a deterministic tactical module that optimises multi-leg journeys and schedules just-in-time dispatches to minimise fleet travel. Evaluation across multiple seeded runs demonstrates SmartFlows high efficacy, reducing network imbalance by over 95% while requiring minimal travel distance and achieving strong truck utilisation. A communication layer, powered by a grounded Agentic AI with a Large Language Model (LLM), translates logistical plans into clear, actionable instructions for operational staff, ensuring interpretability and execution readiness. This integration bridges machine intelligence with human operations, offering a scalable solution that reduces idle time, improves bike availability, and lowers operational costs. SmartFlow provides a blueprint for interpretable, AI-driven logistics in complex urban mobility networks.
Authors: Osasumwen Cedric Ogiesoba-Eguakun, Suman Rath
Abstract: Coordinated stealth attacks are a serious cybersecurity threat to distributed generation systems because they modify control and measurement signals while remaining close to normal behavior, making them difficult to detect using standard intrusion detection methods. This study investigates quantum machine learning approaches for detecting coordinated stealth attacks on a distributed generation unit in a microgrid. High-quality simulated measurements were used to create a balanced binary classification dataset using three features: reactive power at DG1, frequency deviation relative to the nominal value, and terminal voltage magnitude. Classical machine learning baselines, fully quantum variational classifiers, and hybrid quantum classical models were evaluated. The results show that a hybrid quantum classical model combining quantum feature embeddings with a classical RBF support vector machine achieves the best overall performance on this low dimensional dataset, with a modest improvement in accuracy and F1 score over a strong classical SVM baseline. Fully quantum models perform worse due to training instability and limitations of current NISQ hardware. In contrast, hybrid models train more reliably and demonstrate that quantum feature mapping can enhance intrusion detection even when fully quantum learning is not yet practical.
Authors: M. Rizki Oktavian
Abstract: Large language models (LLMs) have recently shown strong reasoning capabilities beyond traditional language tasks, motivating their use for numerical optimization. This paper presents LLMize, an open-source Python framework that enables LLM-driven optimization through iterative prompting and in-context learning. LLMize formulates optimization as a black-box process in which candidate solutions are generated in natural language, evaluated by an external objective function, and refined over successive iterations using solution-score feedback. The framework supports multiple optimization strategies, including Optimization by Prompting (OPRO) and hybrid LLM-based methods inspired by evolutionary algorithms and simulated annealing. A key advantage of LLMize is the ability to inject constraints, rules, and domain knowledge directly through natural language descriptions, allowing practitioners to define complex optimization problems without requiring expertise in mathematical programming or metaheuristic design. LLMize is evaluated on convex optimization, linear programming, the Traveling Salesman Problem, neural network hyperparameter tuning, and nuclear fuel lattice optimization. Results show that while LLM-based optimization is not competitive with classical solvers for simple problems, it provides a practical and accessible approach for complex, domain-specific tasks where constraints and heuristics are difficult to formalize.
Authors: Thomas Andrews, Mark Law, Sara Ahmadi-Abhari, Alessandra Russo
Abstract: We introduce LearnAD, a neuro-symbolic method for predicting Alzheimer's disease from brain magnetic resonance imaging data, learning fully interpretable rules. LearnAD applies statistical models, Decision Trees, Random Forests, or GNNs to identify relevant brain connections, and then employs FastLAS to learn global rules. Our best instance outperforms Decision Trees, matches Support Vector Machine accuracy, and performs only slightly below Random Forests and GNNs trained on all features, all while remaining fully interpretable. Ablation studies show that our neuro-symbolic approach improves interpretability with comparable performance to pure statistical models. LearnAD demonstrates how symbolic learning can deepen our understanding of GNN behaviour in clinical neuroscience.
Authors: Zhongyang Shen
Abstract: We propose a new outlier detection method for multi-dimensional data. The method detects outliers based on vector cosine similarity, using a new dataset constructed by adding a dimension with zero values to the original data. When a point in the new dataset is selected as the measured point, an observation point is created as the origin, differing only in the new dimension by having a non-zero value compared to the measured point. Vectors are then formed from the observation point to the measured point and to other points in the dataset. By comparing the cosine similarities of these vectors, abnormal data can be identified. An optimized implementation (MDOD) is available on PyPI: https://pypi.org/project/mdod/.
Authors: Nalin Dhiman
Abstract: We study a physics-inspired optimizer, \emph{FANoS} (Friction-Adaptive Nos\'e--Hoover Symplectic momentum), which combines (i) a momentum update written as a discretized second-order dynamical system, (ii) a Nos\'e--Hoover-like thermostat variable that adapts a scalar friction coefficient using kinetic-energy feedback, and (iii) a semi-implicit (symplectic-Euler) integrator, optionally with a diagonal RMS preconditioner. The method is motivated by structure-preserving integration and thermostat ideas from molecular dynamics, but is used here purely as an optimization heuristic. We provide the algorithm and limited theoretical observations in idealized settings. On the deterministic Rosenbrock-100D benchmark with 3000 gradient evaluations, FANoS-RMS attains a mean final objective value of $1.74\times 10^{-2}$, improving substantially over unclipped AdamW ($48.50$) and SGD+momentum ($90.76$) in this protocol. However, AdamW with gradient clipping is stronger, reaching $1.87\times 10^{-3}$, and L-BFGS reaches $\approx 4.4\times 10^{-10}$. On ill-conditioned convex quadratics and in a small PINN warm-start suite (Burgers and Allen--Cahn), the default FANoS configuration underperforms AdamW and can be unstable or high-variance. Overall, the evidence supports a conservative conclusion: FANoS is an interpretable synthesis of existing ideas that can help on some stiff nonconvex valleys, but it is not a generally superior replacement for modern baselines, and its behavior is sensitive to temperature-schedule and hyperparameter choices.
Authors: Ana Carpio, Gema Duro
Abstract: Topological methods have the potential of exploring data clouds without making assumptions on their the structure. Here we propose a hierarchical topological clustering algorithm that can be implemented with any distance choice. The persistence of outliers and clusters of arbitrary shape is inferred from the resulting hierarchy. We demonstrate the potential of the algorithm on selected datasets in which outliers play relevant roles, consisting of images, medical and economic data. These methods can provide meaningful clusters in situations in which other techniques fail to do so.
Authors: Gihyeon Sim
Abstract: Large language models apply uniform computation to all inputs, regardless of difficulty. We propose PonderTTT, a gating strategy using the TTT layer's self-supervised reconstruction loss to selectively trigger Test-Time Training (TTT) updates. The gating decision itself is training-free--requiring no learned classifier or auxiliary networks; only a single scalar threshold is initially calibrated on unlabeled data and continuously adapted via EMA to maintain target update rates. Our experiments with GPT-2 models (124M to 1.5B) on code language modeling (The Stack v2, teacher-forced perplexity) demonstrate that this signal is inference-compatible, requiring no ground-truth labels. Our Reconstruction Gating achieves 82-89% Oracle Recovery while being fully training-free, significantly outperforming Random Skip baselines (up to 16% lower loss on OOD languages).
Authors: Ruiming Liang, Yinan Zheng, Kexin Zheng, Tianyi Tan, Jianxiong Li, Liyuan Mao, Zhihao Wang, Guang Chen, Hangjun Ye, Jingjing Liu, Jinqiao Wang, Xianyuan Zhan
Abstract: Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion policies using reinforcement learning (RL) remains challenging. Existing methods either suffer from unstable training due to directly maximizing value objectives, or face computational issues due to relying on crude Gaussian likelihood approximation, which requires a large amount of sufficiently small denoising steps. In this work, we propose DIPOLE (Dichotomous diffusion Policy improvement), a novel RL algorithm designed for stable and controllable diffusion policy optimization. We begin by revisiting the KL-regularized objective in RL, which offers a desirable weighted regression objective for diffusion policy extraction, but often struggles to balance greediness and stability. We then formulate a greedified policy regularization scheme, which naturally enables decomposing the optimal policy into a pair of stably learned dichotomous policies: one aims at reward maximization, and the other focuses on reward minimization. Under such a design, optimized actions can be generated by linearly combining the scores of dichotomous policies during inference, thereby enabling flexible control over the level of greediness.Evaluations in offline and offline-to-online RL settings on ExORL and OGBench demonstrate the effectiveness of our approach. We also use DIPOLE to train a large vision-language-action (VLA) model for end-to-end autonomous driving (AD) and evaluate it on the large-scale real-world AD benchmark NAVSIM, highlighting its potential for complex real-world applications.
Authors: Chorok Lee
Abstract: Conformal prediction guarantees degrade under distribution shift. We study this using COVID-19 as a natural experiment across 8 supply chain tasks. Despite identical severe feature turnover (Jaccard approximately 0), coverage drops vary from 0% to 86.7%, spanning two orders of magnitude. Using SHapley Additive exPlanations (SHAP) analysis, we find catastrophic failures correlate with single-feature dependence (rho = 0.714, p = 0.047). Catastrophic tasks concentrate importance in one feature (4.5x increase), while robust tasks redistribute across many (10-20x). Quarterly retraining restores catastrophic task coverage from 22% to 41% (+19 pp, p = 0.04), but provides no benefit for robust tasks (99.8% coverage). Exploratory analysis of 4 additional tasks with moderate feature stability (Jaccard 0.13-0.86) reveals feature stability, not concentration, determines robustness, suggesting concentration effects apply specifically to severe shifts. We provide a decision framework: monitor SHAP concentration before deployment; retrain quarterly if vulnerable (>40% concentration); skip retraining if robust.
Authors: Jacquelyn Shelton, Przemyslaw Polewski, Alexander Robel, Matthew Hoffman, Stephen Price
Abstract: Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We study a generative modeling approach for producing new realizations from a limited set of available runs by transferring structure learned across an ensemble. Using monthly near-surface temperature time series from ten independent reanalysis realizations (ERA5), we find that a vanilla conditional variational autoencoder (CVAE) trained jointly across realizations yields a fragmented latent space that fails to generalize to unseen ensemble members. To address this, we introduce a latent-constrained CVAE (LC-CVAE) that enforces cross-realization homogeneity of latent embeddings at a small set of shared geographic 'anchor' locations. We then use multi-output Gaussian process regression in the latent space to predict latent coordinates at unsampled locations in a new realization, followed by decoding to generate full time series fields. Experiments and ablations demonstrate (i) instability when training on a single realization, (ii) diminishing returns after incorporating roughly five realizations, and (iii) a trade-off between spatial coverage and reconstruction quality that is closely linked to the average neighbor distance in latent space.
Authors: Zichuan Fu, Wentao Song, Guojing Li, Yejing Wang, Xian Wu, Yimin Deng, Hanyu Yan, Yefeng Zheng, Xiangyu Zhao
Abstract: The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention mechanism is plagued by well-documented issues: representational collapse and attention sink. Although prior work has proposed approaches for these issues, they are often studied in isolation, obscuring their deeper connection. In this paper, we present a unified perspective, arguing that both can be traced to a common root -- improper attention allocation. We identify two failure modes: 1) Attention Overload, where tokens receive comparable high weights, blurring semantic features that lead to representational collapse; 2) Attention Underload, where no token is semantically relevant, yet attention is still forced to distribute, resulting in spurious focus such as attention sink. Building on this insight, we introduce Lazy Attention, a novel mechanism designed for a more focused attention distribution. To mitigate overload, it employs positional discrimination across both heads and dimensions to sharpen token distinctions. To counteract underload, it incorporates Elastic-Softmax, a modified normalization function that relaxes the standard softmax constraint to suppress attention on irrelevant tokens. Experiments on the FineWeb-Edu corpus, evaluated across nine diverse benchmarks, demonstrate that Lazy Attention successfully mitigates attention sink and achieves competitive performance compared to both standard attention and modern architectures, while reaching up to 59.58% attention sparsity.
Authors: Xingsheng Chen, Regina Zhang, Bo Gao, Xingwei He, Xiaofeng Liu, Pietro Lio, Kwok-Yan Lam, Siu-Ming Yiu
Abstract: Time series prediction plays a pivotal role across diverse domains such as finance, healthcare, energy systems, and environmental modeling. However, existing approaches often struggle to balance efficiency, scalability, and accuracy, particularly when handling long-range dependencies and irregularly sampled data. To address these challenges, we propose MODE, a unified framework that integrates Low-Rank Neural Ordinary Differential Equations (Neural ODEs) with an Enhanced Mamba architecture. As illustrated in our framework, the input sequence is first transformed by a Linear Tokenization Layer and then processed through multiple Mamba Encoder blocks, each equipped with an Enhanced Mamba Layer that employs Causal Convolution, SiLU activation, and a Low-Rank Neural ODE enhancement to efficiently capture temporal dynamics. This low-rank formulation reduces computational overhead while maintaining expressive power. Furthermore, a segmented selective scanning mechanism, inspired by pseudo-ODE dynamics, adaptively focuses on salient subsequences to improve scalability and long-range sequence modeling. Extensive experiments on benchmark datasets demonstrate that MODE surpasses existing baselines in both predictive accuracy and computational efficiency. Overall, our contributions include: (1) a unified and efficient architecture for long-term time series modeling, (2) integration of Mamba's selective scanning with low-rank Neural ODEs for enhanced temporal representation, and (3) substantial improvements in efficiency and scalability enabled by low-rank approximation and dynamic selective scanning.
Authors: Azadeh Alavi, Hamidreza Khalili, Stanley H. Chan, Fatemeh Kouchmeshki, Ross Vlahos
Abstract: Skeletal muscle dysfunction is a clinically relevant extra-pulmonary manifestation of chronic obstructive pulmonary disease (COPD) and is closely linked to systemic and airway inflammation. This motivates predictive modelling of muscle outcomes from minimally invasive biomarkers that can be acquired longitudinally. We study a small-sample preclinical dataset comprising 213 animals across two conditions (Sham versus cigarette-smoke exposure), with blood and bronchoalveolar lavage fluid measurements and three continuous targets: tibialis anterior muscle weight (milligram: mg), specific force (millinewton: mN), and a derived muscle quality index (mN per mg). We benchmark tuned classical baselines, geometry-aware symmetric positive definite (SPD) descriptors with Stein divergence, and quantum kernel models designed for low-dimensional tabular data. In the muscle-weight setting, quantum kernel ridge regression using four interpretable inputs (blood C-reactive protein, neutrophil count, bronchoalveolar lavage cellularity, and condition) attains a test root mean squared error of 4.41 mg and coefficient of determination of 0.605, improving over a matched ridge baseline on the same feature set (4.70 mg and 0.553). Geometry-informed Stein-divergence prototype distances yield a smaller but consistent gain in the biomarker-only setting (4.55 mg versus 4.79 mg). Screening-style evaluation, obtained by thresholding the continuous outcome at 0.8 times the training Sham mean, achieves an area under the receiver operating characteristic curve (ROC-AUC) of up to 0.90 for detecting low muscle weight. These results indicate that geometric and quantum kernel lifts can provide measurable benefits in low-data, low-feature biomedical prediction problems, while preserving interpretability and transparent model selection.
Authors: Rares Folea, Radu Iacob, Emil Slusanschi, Traian Rebedea
Abstract: This paper presents a generic method for transforming the source code of various algorithms to numerical embeddings, by dynamically analysing the behaviour of computer programs against different inputs and by tailoring multiple generic complexity functions for the analysed metrics. The used algorithms embeddings are based on r-Complexity . Using the proposed code embeddings, we present an implementation of the XGBoost algorithm that achieves an average F1-score on a multi-label dataset with 11 classes, built using real-world code snippets submitted for programming competitions on the Codeforces platform.
Authors: Andrea Thomas Nava, Lijo Johny, Fabio Azzalini, Johannes Schneider, Arianna Casanova
Abstract: Data-Driven Product Development (DDPD) leverages data to learn the relationship between product design specifications and resulting properties. To discover improved designs, we train a neural network on past experiments and apply Projected Gradient Descent to identify optimal input features that maximize performance. Since many products require simultaneous optimization of multiple correlated properties, our framework employs joint neural networks to capture interdependencies among targets. Furthermore, we integrate uncertainty estimation via \emph{Conformalised Monte Carlo Dropout} (ConfMC), a novel method combining Nested Conformal Prediction with Monte Carlo dropout to provide model-agnostic, finite-sample coverage guarantees under data exchangeability. Extensive experiments on five real-world datasets show that our method matches state-of-the-art performance while offering adaptive, non-uniform prediction intervals and eliminating the need for retraining when adjusting coverage levels.
Authors: Jinyu Xu, Abhishek K. Umrawal
Abstract: We study the problem of influence maximization (IM) in an online setting, where the goal is to select a subset of nodes$\unicode{x2014}$called the seed set$\unicode{x2014}$at each time step over a fixed time horizon, subject to a cardinality budget constraint, to maximize the expected cumulative influence. We operate under a full-bandit feedback model, where only the influence of the chosen seed set at each time step is observed, with no additional structural information about the network or diffusion process. It is well-established that the influence function is submodular, and existing algorithms exploit this property to achieve low regret. In this work, we leverage this property further and propose the Lazy Online Forward Algorithm (LOFA), which achieves a lower empirical regret. We conduct experiments on a real-world social network to demonstrate that LOFA achieves superior performance compared to existing bandit algorithms in terms of cumulative regret and instantaneous reward.
Authors: Kabir Grover
Abstract: The increasing prevalence of sparse Mixture-of-Experts (MoE) architectures in large language models raises important questions regarding their reliability under stochastic decoding. While conditional computation enables substantial gains in computational efficiency, it remains unclear whether the interaction between sparse routing and temperature-based sampling compromises output stability relative to dense architectures. This work investigates whether conditional computation in MoE models amplifies decoding-induced randomness, leading to reduced reliability as temperature increases. We evaluate three representative models: OLMoE-7B (sparse base), Mixtral-8x7B (sparse instruction-tuned), and Qwen2.5-3B (dense instruction-tuned) on deterministic arithmetic reasoning tasks with objectively verifiable answers. Experiments span four decoding configurations, ranging from greedy decoding to T=1.0. Our evaluation encompasses accuracy, format compliance, output consistency across repeated generations, and confidence metrics, totaling 9,360 model generations. Results demonstrate that the sparse instruction-tuned model exhibits stability comparable to the dense instruction-tuned model across all decoding temperatures, while the sparse base model shows systematic degradation as temperature increases. These findings indicate that instruction tuning, rather than architectural sparsity, is the primary determinant of robustness to decoding randomness on deterministic tasks. We discuss the implications of these results for deploying sparse language models in reliability-critical applications, highlighting scenarios in which sparse architectures can be safely adopted without sacrificing output stability.
Authors: Tianshuo Yang, Ryan Rabinowitz, Terrance E. Boult, Jugal Kalita
Abstract: Transformer classifiers such as BERT deliver impressive closed-set accuracy, yet they remain brittle when confronted with inputs from unseen categories--a common scenario for deployed NLP systems. We investigate Open-Set Recognition (OSR) for text by porting the feature attenuation hypothesis from computer vision to transformers and by benchmarking it against state-of-the-art baselines. Concretely, we adapt the COSTARR framework--originally designed for classification in computer vision--to two modest language models (BERT (base) and GPT-2) trained to label 176 arXiv subject areas. Alongside COSTARR, we evaluate Maximum Softmax Probability (MSP), MaxLogit, and the temperature-scaled free-energy score under the OOSA and AUOSCR metrics. Our results show (i) COSTARR extends to NLP without retraining but yields no statistically significant gain over MaxLogit or MSP, and (ii) free-energy lags behind all other scores in this high-class-count setting. The study highlights both the promise and the current limitations of transplanting vision-centric OSR ideas to language models, and points toward the need for larger backbones and task-tailored attenuation strategies.
Authors: Longwei Wang, Mohammad Navid Nayyem, Abdullah Al Rakin, KC Santosh, Chaowei Zhang, Yang Zhou
Abstract: The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their decision-making. In this paper, we identify a connection between interpretability and robustness that can be directly leveraged during training. Specifically, we observe that spurious, unstable, or semantically irrelevant features identified through Local Interpretable Model-Agnostic Explanations (LIME) contribute disproportionately to adversarial vulnerability. Building on this insight, we introduce an attribution-guided refinement framework that transforms LIME from a passive diagnostic into an active training signal. Our method systematically suppresses spurious features using feature masking, sensitivity-aware regularization, and adversarial augmentation in a closed-loop refinement pipeline. This approach does not require additional datasets or model architectures and integrates seamlessly into standard adversarial training. Theoretically, we derive an attribution-aware lower bound on adversarial distortion that formalizes the link between explanation alignment and robustness. Empirical evaluations on CIFAR-10, CIFAR-10-C, and CIFAR-100 demonstrate substantial improvements in adversarial robustness and out-of-distribution generalization.
Authors: Boris N. Oreshkin, Mayank Jauhari, Ravi Kiran Selvam, Malcolm Wolff, Wenhao Pan, Shankar Ramasubramanian, Kin G. Olivares, Tatiana Konstantinova, Andres Potapczynski, Mengfei Cao, Dmitry Efimov, Michael W. Mahoney, Andrew G. Wilson
Abstract: Zero-shot time-series forecasting holds great promise, but is still in its infancy, hindered by limited and biased data corpora, leakage-prone evaluation, and privacy and licensing constraints. Motivated by these challenges, we propose the first practical univariate time series simulation pipeline which is simultaneously fast enough for on-the-fly data generation and enables notable zero-shot forecasting performance on M-Series and GiftEval benchmarks that capture trend/seasonality/intermittency patterns, typical of industrial forecasting applications across a variety of domains. Our simulator, which we call SarSim0 (SARIMA Simulator for Zero-Shot Forecasting), is based off of a seasonal autoregressive integrated moving average (SARIMA) model as its core data source. Due to instability in the autoregressive component, naive SARIMA simulation often leads to unusable paths. Instead, we follow a three-step procedure: (1) we sample well-behaved trajectories from its characteristic polynomial stability region; (2) we introduce a superposition scheme that combines multiple paths into rich multi-seasonality traces; and (3) we add rate-based heavy-tailed noise models to capture burstiness and intermittency alongside seasonalities and trends. SarSim0 is orders of magnitude faster than kernel-based generators, and it enables training on circa 1B unique purely simulated series, generated on the fly; after which well-established neural network backbones exhibit strong zero-shot generalization, surpassing strong statistical forecasters and recent foundation baselines, while operating under strict zero-shot protocol. Notably, on GiftEval we observe a "student-beats-teacher" effect: models trained on our simulations exceed the forecasting accuracy of the AutoARIMA generating processes.
Authors: Amin Abyaneh, Charlotte Morissette, Mohamad H. Danesh, Anas El Houssaini, David Meger, Gregory Dudek, Hsiu-Chin Lin
Abstract: Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a Stochastic Differential Equation (SDE). However, the same score-based SDE modeling that grants diffusion policies the flexibility to learn diverse behavior also incurs solver and score-matching errors, large data requirements, and inconsistencies in action generation. While less critical in image generation, these inaccuracies compound and lead to failure in continuous control settings. We introduce Contractive Diffusion Policies (CDPs) to induce contractive behavior in the diffusion sampling dynamics. Contraction pulls nearby flows closer to enhance robustness against solver and score-matching errors while reducing unwanted action variance. We develop an in-depth theoretical analysis along with a practical implementation recipe to incorporate CDPs into existing diffusion policy architectures with minimal modification and computational cost. We evaluate CDPs for offline learning by conducting extensive experiments in simulation and real-world settings. Across benchmarks, CDPs often outperform baseline policies, with pronounced benefits under data scarcity.
Authors: Mojtaba Aliasghar-Mamaghani, Mohammadreza Khalafi
Abstract: This paper employs a data-driven approach to determine the impact of concrete mixture compositions on the temporal evolution of chloride in concrete structures. This is critical for assessing the service life of civil infrastructure subjected to aggressive environments. The adopted methodology relies on several simple and complex standalone machine learning (ML) algorithms, with the primary objective of establishing confidence in the unbiased prediction of the underlying hidden correlations. The simple algorithms include linear regression (LR), k-nearest neighbors (KNN) regression, and kernel ridge regression (KRR). The complex algorithms entail support vector regression (SVR), Gaussian process regression (GPR), and two families of artificial neural networks, including a feedforward network (multilayer perceptron, MLP) and a gated recurrent unit (GRU). The MLP architecture cannot explicitly handle sequential data, a limitation addressed by the GRU. A comprehensive dataset is considered. The performance of ML algorithms is evaluated, with KRR, GPR, and MLP exhibiting high accuracy. Given the diversity of the adopted concrete mixture proportions, the GRU was unable to accurately reproduce the response in the test set. Further analyses elucidate the contributions of mixture compositions to the temporal evolution of chloride. The results obtained from the GPR model unravel latent correlations through clear and explainable trends. The MLP, SVR, and KRR also provide acceptable estimates of the overall trends. The majority of mixture components exhibit an inverse relation with chloride content, while a few components demonstrate a direct correlation. These findings highlight the potential of surrogate approaches for describing the physical processes involved in chloride ingress and the associated correlations, toward the ultimate goal of enhancing the service life of civil infrastructure.
Authors: Haoran Su, Chenyu You
Abstract: Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely attribute this phenomenon to optimization instability or vanishing gradients, yet such accounts fail to explain why collapse persists even under modern normalization and initialization schemes. In this paper, we argue that the collapse of deep Transformers is fundamentally a geometric problem. Standard residual updates implicitly assume that feature accumulation is always beneficial, but offer no mechanism to constrain update directions or to erase outdated information. As depth increases, this leads to systematic drift off the semantic manifold and monotonic feature accumulation, causing representational degeneracy. We propose a unified geometric framework that addresses these failures through two orthogonal principles. First, manifold-constrained hyper-connections restrict residual updates to valid local tangent directions, preventing uncontrolled manifold drift. Second, deep delta learning introduces data-dependent, non-monotonic updates that enable reflection and erasure of redundant features rather than their unconditional accumulation. Together, these mechanisms decouple the direction and sign of feature updates, yielding a stable geometric evolution across depth. We term the resulting architecture the Manifold-Geometric Transformer (MGT). Our analysis predicts that enforcing geometric validity while allowing dynamic erasure is essential for avoiding rank collapse in ultra-deep networks. We outline an evaluation protocol for Transformers exceeding 100 layers to test the hypothesis that geometry, rather than depth itself, is the key limiting factor in deep representation learning.
Authors: Ata Akbari Asanjan, Milad Memarzadeh, Bryan Matthews, Nikunj Oza
Abstract: In this study, we focus on the training process and inference improvements of deep neural networks (DNNs), specifically Autoencoders (AEs) and Variational Autoencoders (VAEs), using Random Fourier Transformation (RFT). We further explore the role of RFT in model training behavior using Frequency Principle (F-Principle) analysis and show that models with RFT turn to learn low frequency and high frequency at the same time, whereas conventional DNNs start from low frequency and gradually learn (if successful) high-frequency features. We focus on reconstruction-based anomaly detection using autoencoder and variational autoencoder and investigate the RFT's role. We also introduced a trainable variant of RFT that uses the existing computation graph to train the expansion of RFT instead of it being random. We showcase our findings with two low-dimensional synthetic datasets for data representation, and an aviation safety dataset, called Dashlink, for high-dimensional reconstruction-based anomaly detection. The results indicate the superiority of models with Fourier transformation compared to the conventional counterpart and remain inconclusive regarding the benefits of using trainable Fourier transformation in contrast to the Random variant.
Authors: Dai Shi, Lequan Lin, Andi Han, Luke Thompson, Jos\'e Miguel Hern\'andez-Lobato, Zhiyong Wang, Junbin Gao
Abstract: Stochastic differential equations (SDEs) and stochastic partial differential equations (SPDEs) are fundamental tools for modeling stochastic dynamics across the natural sciences and modern machine learning. Developing deep learning models for approximating their solution operators promises not only fast, practical solvers, but may also inspire models that resolve classical learning tasks from a new perspective. In this work, we build on classical Wiener chaos expansions (WCE) to design neural operator (NO) architectures for SPDEs and SDEs: we project the driving noise paths onto orthonormal Wick Hermite features and parameterize the resulting deterministic chaos coefficients with neural operators, so that full solution trajectories can be reconstructed from noise in a single forward pass. On the theoretical side, we investigate the classical WCE results for the class of multi-dimensional SDEs and semilinear SPDEs considered here by explicitly writing down the associated coupled ODE/PDE systems for their chaos coefficients, which makes the separation between stochastic forcing and deterministic dynamics fully explicit and directly motivates our model designs. On the empirical side, we validate our models on a diverse suite of problems: classical SPDE benchmarks, diffusion one-step sampling on images, topological interpolation on graphs, financial extrapolation, parameter estimation, and manifold SDEs for flood prediction, demonstrating competitive accuracy and broad applicability. Overall, our results indicate that WCE-based neural operators provide a practical and scalable way to learn SDE/SPDE solution operators across diverse domains.
Authors: Jo\~ao Morais, Sadjad Alikhani, Akshay Malhotra, Shahab Hamidi-Rad, Ahmed Alkhateeb
Abstract: This paper introduces a task- and model-aware framework for measuring similarity between wireless datasets, enabling applications such as dataset selection/augmentation, simulation-to-real (sim2real) comparison, task-specific synthetic data generation, and informing decisions on model training/adaptation to new deployments. We evaluate candidate dataset distance metrics by how well they predict cross-dataset transferability: if two datasets have a small distance, a model trained on one should perform well on the other. We apply the framework on an unsupervised task, channel state information (CSI) compression, using autoencoders. Using metrics based on UMAP embeddings, combined with Wasserstein and Euclidean distances, we achieve Pearson correlations exceeding 0.85 between dataset distances and train-on-one/test-on-another task performance. We also apply the framework to a supervised beam prediction in the downlink using convolutional neural networks. For this task, we derive a label-aware distance by integrating supervised UMAP and penalties for dataset imbalance. Across both tasks, the resulting distances outperform traditional baselines and consistently exhibit stronger correlations with model transferability, supporting task-relevant comparisons between wireless datasets.
Authors: Tatsuaki Tsuruyama
Abstract: Diffusion models and score-based generative models provide a powerful framework for synthesizing high-quality images from noise. However, there is still no satisfactory theory that describes how coarse-grained quantities, such as blockwise intensity or class proportions after partitioning an image into spatial blocks, are preserved and evolve along the reverse diffusion dynamics. In previous work, the author introduced an information-theoretic Lyapunov function V for non-ergodic Markov processes on a state space partitioned into blocks, defined as the minimal Kullback-Leibler divergence to the set of stationary distributions reachable from a given initial condition, and showed that a leak-tolerant potential V-delta with a prescribed tolerance for block masses admits a closed-form expression as a scaling-and-clipping operation on block masses. In this paper, I transplant this framework to the reverse diffusion process in generative models and propose a reverse diffusion scheme that is projected by the potential V-delta (referred to as the V-delta projected reverse diffusion). I extend the monotonicity of V to time-inhomogeneous block-preserving Markov kernels and show that, under small leakage and the V-delta projection, V-delta acts as an approximate Lyapunov function. Furthermore, using a toy model consisting of block-constant images and a simplified reverse kernel, I numerically demonstrate that the proposed method keeps the block-mass error and the leak-tolerant potential within the prescribed tolerance, while achieving pixel-wise accuracy and visual quality comparable to the non-projected dynamics. This study reinterprets generative sampling as a decrease of an information potential from noise to data, and provides a design principle for reverse diffusion processes with explicit control of coarse-grained quantities.
Authors: Yajing Liu, Erkao Bao, Linqi Song
Abstract: We present ML-UCB, a generalized upper confidence bound algorithm that integrates arbitrary machine learning models into multi-armed bandit frameworks. A fundamental challenge in deploying sophisticated ML models for sequential decision-making is the lack of tractable concentration inequalities required for principled exploration. We overcome this limitation by directly modeling the learning curve behavior of the underlying estimator. Specifically, assuming the Mean Squared Error decreases as a power law in the number of training samples, we derive a generalized concentration inequality and prove that ML-UCB achieves sublinear regret. This framework enables the principled integration of any ML model whose learning curve can be empirically characterized, eliminating the need for model-specific theoretical analysis. We validate our approach through experiments on a collaborative filtering recommendation system using online matrix factorization with synthetic data designed to simulate a simplified two-tower model, demonstrating substantial improvements over LinUCB
Authors: Yunlin Zeng
Abstract: Vision-Language Models (VLMs) have achieved remarkable success in descriptive tasks such as image captioning and visual question answering (VQA). However, their ability to generate engaging, long-form narratives -- specifically multi-speaker podcast dialogues -- remains under-explored and difficult to evaluate. Standard metrics like BLEU and ROUGE fail to capture the nuances of conversational naturalness, personality, and narrative flow, often rewarding safe, repetitive outputs over engaging storytelling. In this work, we present a novel pipeline for end-to-end visual podcast generation, and fine-tune a Qwen3-VL-32B model on a curated dataset of 4,000 image-dialogue pairs. Crucially, we use a synthetic-to-real training strategy: we train on high-quality podcast dialogues from the Structured Podcast Research Corpus (SPoRC) paired with synthetically generated imagery, and evaluate on real-world photo sequences from the Visual Storytelling Dataset (VIST). This rigorous setup tests the model's ability to generalize from synthetic training data to real-world visual domains. We propose a comprehensive evaluation framework that moves beyond textual overlap, and use AI-as-a-judge (Gemini 3 Pro, Claude Opus 4.5, GPT 5.2) and novel style metrics (average turn length, speaker switch rate) to assess quality. Our experiments demonstrate that our fine-tuned 32B model significantly outperforms a 235B base model in conversational naturalness ($>$80\% win rate) and narrative depth (+50\% turn length), while maintaining identical visual grounding capabilities (CLIPScore: 20.39).
Authors: Achraf Hsain, Yahya Zaki, Othman Abaakil, Hibat-allah Bekkar, Yousra Chtouki
Abstract: Aquaculture, the farming of aquatic organisms, is a rapidly growing industry facing challenges such as water quality fluctuations, disease outbreaks, and inefficient feed management. Traditional monitoring methods often rely on manual labor and are time consuming, leading to potential delays in addressing issues. This paper proposes the integration of low-power edge devices using Tiny Machine Learning (TinyML) into aquaculture systems to enable real-time automated monitoring and control, such as collecting data and triggering alarms, and reducing labor requirements. The system provides real-time data on the required parameters such as pH levels, temperature, dissolved oxygen, and ammonia levels to control water quality, nutrient levels, and environmental conditions enabling better maintenance, efficient resource utilization, and optimal management of the enclosed aquaculture space. The system enables alerts in case of anomaly detection. The data collected by the sensors over time can serve for important decision-making regarding optimizing water treatment processes, feed distribution, feed pattern analysis and improve feed efficiency, reducing operational costs. This research explores the feasibility of developing TinyML-based solutions for aquaculture monitoring, considering factors such as sensor selection, algorithm design, hardware constraints, and ethical considerations. By demonstrating the potential benefits of TinyML in aquaculture, our aim is to contribute to the development of more sustainable and efficient farming practices.
Authors: Jing Wang, Peng Zhao, Zhi-Hua Zhou
Abstract: Non-stationary parametric bandits have attracted much attention recently. There are three principled ways to deal with non-stationarity, including sliding-window, weighted, and restart strategies. As many non-stationary environments exhibit gradual drifting patterns, the weighted strategy is commonly adopted in real-world applications. However, previous theoretical studies show that its analysis is more involved and the algorithms are either computationally less efficient or statistically suboptimal. This paper revisits the weighted strategy for non-stationary parametric bandits. In linear bandits (LB), we discover that this undesirable feature is due to an inadequate regret analysis, which results in an overly complex algorithm design. We propose a \emph{refined analysis framework}, which simplifies the derivation and, importantly, produces a simpler weight-based algorithm that is as efficient as window/restart-based algorithms while retaining the same regret as previous studies. Furthermore, our new framework can be used to improve regret bounds of other parametric bandits, including Generalized Linear Bandits (GLB) and Self-Concordant Bandits (SCB). For example, we develop a simple weighted GLB algorithm with an $\tilde{O}(k_\mu^{5/4} c_\mu^{-3/4} d^{3/4} P_T^{1/4}T^{3/4})$ regret, improving the $\tilde{O}(k_\mu^{2} c_\mu^{-1}d^{9/10} P_T^{1/5}T^{4/5})$ bound in prior work, where $k_\mu$ and $c_\mu$ characterize the reward model's nonlinearity, $P_T$ measures the non-stationarity, $d$ and $T$ denote the dimension and time horizon. Moreover, we extend our framework to non-stationary Markov Decision Processes (MDPs) with function approximation, focusing on Linear Mixture MDP and Multinomial Logit (MNL) Mixture MDP. For both classes, we propose algorithms based on the weighted strategy and establish dynamic regret guarantees using our analysis framework.
Authors: Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan, Yilun Du, Thomas Anderson Keller
Abstract: Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of external objects. These streams obey smooth, time-parameterized symmetries, which combine through a precisely structured algebra; yet most neural network world models ignore this structure and instead repeatedly re-learn the same transformations from data. In this work, we introduce 'Flow Equivariant World Models', a framework in which both self-motion and external object motion are unified as one-parameter Lie group 'flows'. We leverage this unification to implement group equivariance with respect to these transformations, thereby providing a stable latent world representation over hundreds of timesteps. On both 2D and 3D partially observed video world modeling benchmarks, we demonstrate that Flow Equivariant World Models significantly outperform comparable state-of-the-art diffusion-based and memory-augmented world modeling architectures -- particularly when there are predictable world dynamics outside the agent's current field of view. We show that flow equivariance is particularly beneficial for long rollouts, generalizing far beyond the training horizon. By structuring world model representations with respect to internal and external motion, flow equivariance charts a scalable route to data efficient, symmetry-guided, embodied intelligence. Project link: https://flowequivariantworldmodels.github.io.
Authors: Bryon Tjanaka, Henry Chen, Matthew C. Fontaine, Stefanos Nikolaidis
Abstract: Quality diversity (QD) optimization searches for a collection of solutions that optimize an objective while attaining diverse outputs of a user-specified, vector-valued measure function. Contemporary QD algorithms focus on low-dimensional measures because high-dimensional measures are prone to distortion, where many solutions found by the QD algorithm map to similar measures. For example, the CMA-MAE algorithm guides measure space exploration with a histogram in measure space that records so-called discount values. However, CMA-MAE stagnates in domains with high-dimensional measure spaces because solutions with similar measures fall into the same histogram cell and thus receive identical discount values. To address these limitations, we propose Discount Model Search (DMS), which guides exploration with a model that provides a smooth, continuous representation of discount values. In high-dimensional measure spaces, this model enables DMS to distinguish between solutions with similar measures and thus continue exploration. We show that DMS facilitates new QD applications by introducing two domains where the measure space is the high-dimensional space of images, which enables users to specify their desired measures by providing a dataset of images rather than hand-designing the measure function. Results in these domains and on high-dimensional benchmarks show that DMS outperforms CMA-MAE and other black-box QD algorithms.
Authors: Nobuyuki Ota
Abstract: Understanding cellular mechanisms requires integrating information across DNA, RNA, and protein - the three molecular systems linked by the Central Dogma of molecular biology. While domain-specific foundation models have achieved success for each modality individually, they remain isolated, limiting our ability to model integrated cellular processes. Here we present the Central Dogma Transformer (CDT), an architecture that integrates pre-trained language models for DNA, RNA, and protein following the directional logic of the Central Dogma. CDT employs directional cross-attention mechanisms - DNA-to-RNA attention models transcriptional regulation, while RNA-to-Protein attention models translational relationships - producing a unified Virtual Cell Embedding that integrates all three modalities. We validate CDT v1 - a proof-of-concept implementation using fixed (non-cell-specific) RNA and protein embeddings - on CRISPRi enhancer perturbation data from K562 cells, achieving a Pearson correlation of 0.503, representing 63% of the theoretical ceiling set by cross-experiment variability (r = 0.797). Attention and gradient analyses provide complementary interpretive windows: in detailed case studies, these approaches highlight largely distinct genomic regions, with gradient analysis identifying a CTCF binding site that Hi-C data showed as physically contacting both enhancer and target gene. These results suggest that AI architectures aligned with biological information flow can achieve both predictive accuracy and mechanistic interpretability.
Authors: Muhammad Ashad Kabir, Sirajam Munira, Dewan Tasnia Azad, Saleh Mohammed Ikram, Mohammad Habibur Rahman Sarker, Syed Manzoor Ahmed Hanifi
Abstract: Early detection of chronic kidney disease (CKD) is essential for preventing progression to end-stage renal disease. However, existing screening tools - primarily developed using populations from high-income countries - often underperform in Bangladesh and South Asia, where risk profiles differ. Most of these tools rely on simple additive scoring functions and are based on data from patients with advanced-stage CKD. Consequently, they fail to capture complex interactions among risk factors and are limited in predicting early-stage CKD. Our objective was to develop and evaluate an explainable machine learning (ML) framework for community-based early-stage CKD screening for low-resource settings, tailored to the Bangladeshi and South Asian population context. We used a community-based dataset from Bangladesh, the first such CKD dataset in South and South Asia, and evaluated twelve ML classifiers across multiple feature domains. Ten complementary feature selection techniques were applied to identify robust, generalizable predictors. The final models were assessed using 10-fold cross-validation. External validation was conducted on three independent datasets from India, the UAE, and Bangladesh. SHAP (SHapley Additive exPlanations) was used to provide model explainability. An ML model trained on an RFECV-selected feature subset achieved a balanced accuracy of 90.40%, whereas minimal non-pathology-test features demonstrated excellent predictive capability with a balanced accuracy of 89.23%, often outperforming larger or full feature sets. Compared with existing screening tools, the proposed models achieved substantially higher accuracy and sensitivity while requiring fewer and more accessible inputs. External validation confirmed strong generalizability with 78% to 98% sensitivity. SHAP interpretation identified clinically meaningful predictors consistent with established CKD risk factors.
Authors: Yaniv Galron, Hadar Sinai, Haggai Maron, Moshe Eliasof
Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pooling procedure, in which the node features calculated by the model are combined to form an informative final descriptor to be used for the downstream task. However, previous graph pooling schemes rely on the last GNN layer features as an input to the pooling or classifier layers, potentially under-utilizing important activations of previous layers produced during the forward pass of the model, which we regard as historical graph activations. This gap is particularly pronounced in cases where a node's representation can shift significantly over the course of many graph neural layers, and worsened by graph-specific challenges such as over-smoothing in deep architectures. To bridge this gap, we introduce HISTOGRAPH, a novel two-stage attention-based final aggregation layer that first applies a unified layer-wise attention over intermediate activations, followed by node-wise attention. By modeling the evolution of node representations across layers, our HISTOGRAPH leverages both the activation history of nodes and the graph structure to refine features used for final prediction. Empirical results on multiple graph classification benchmarks demonstrate that HISTOGRAPH offers strong performance that consistently improves traditional techniques, with particularly strong robustness in deep GNNs.
Authors: Golbahar Amanpour, Benyamin Ghojogh
Abstract: This paper, introducing a novel method in philomatics, draws on Wittgenstein's concept of family resemblance from analytic philosophy to develop a clustering algorithm for machine learning. According to Wittgenstein's Philosophical Investigations (1953), family resemblance holds that members of a concept or category are connected by overlapping similarities rather than a single defining property. Consequently, a family of entities forms a chain of items sharing overlapping traits. This philosophical idea naturally lends itself to a graph-based approach in machine learning. Accordingly, we propose the Wittgenstein's Family Resemblance (WFR) clustering algorithm and its kernel variant, kernel WFR. This algorithm computes resemblance scores between neighboring data instances, and after thresholding these scores, a resemblance graph is constructed. The connected components of this graph define the resulting clusters. Simulations on benchmark datasets demonstrate that WFR is an effective nonlinear clustering algorithm that does not require prior knowledge of the number of clusters or assumptions about their shapes.
Authors: Anusree M, Akhila Henry, Pramod P Nair
Abstract: In numerous practical applications, acquiring substantial quantities of labelled data is challenging and expensive, but unlabelled data is readily accessible. Conventional supervised learning methods frequently underperform in scenarios characterised by little labelled data or imbalanced datasets. This study introduces a hybrid semi-supervised learning (SSL) architecture that integrates Neurochaos Learning (NL) with a threshold-based Self-Training (ST) method to overcome this constraint. The NL architecture converts input characteristics into chaos-based ring-rate representations that encapsulate nonlinear relationships within the data, whereas ST progressively enlarges the labelled set utilising high-confidence pseudo-labelled samples. The model's performance is assessed using ten benchmark datasets and five machine learning classifiers, with 85% of the training data considered unlabelled and just 15% utilised as labelled data. The proposed Self-Training Neurochaos Learning (NL+ST) architecture consistently attains superior performance gain relative to standalone ST models, especially on limited, nonlinear and imbalanced datasets like Iris (188.66%), Wine (158.58%) and Glass Identification (110.48%). The results indicate that using chaos-based feature extraction with SSL improves generalisation, resilience, and classification accuracy in low-data contexts.
Authors: Wenbin Pei, Ruohao Dai, Bing Xue, Mengjie Zhang, Qiang Zhang, Yiu-Ming Cheung
Abstract: Time series classification is a fundamental machine learning task with broad real-world applications. Although many deep learning methods have proven effective in learning time-series data for classification, they were originally developed under the assumption of balanced data distributions. Once data distribution is uneven, these methods tend to ignore the minority class that is typically of higher practical significance. Oversampling methods have been designed to address this by generating minority-class samples, but their reliance on linear interpolation often hampers the preservation of temporal dynamics and the generation of diverse samples. Therefore, in this paper, we propose Evo-TFS, a novel evolutionary oversampling method that integrates both time- and frequency-domain characteristics. In Evo-TFS, strongly typed genetic programming is employed to evolve diverse, high-quality time series, guided by a fitness function that incorporates both time-domain and frequency-domain characteristics. Experiments conducted on imbalanced time series datasets demonstrate that Evo-TFS outperforms existing oversampling methods, significantly enhancing the performance of time-domain and frequency-domain classifiers.
Authors: Zihua Yang, Xin Liao, Yiqun Zhang, Yiu-ming Cheung
Abstract: Categorical data are prevalent in domains such as healthcare, marketing, and bioinformatics, where clustering serves as a fundamental tool for pattern discovery. A core challenge in categorical data clustering lies in measuring similarity among attribute values that lack inherent ordering or distance. Without appropriate similarity measures, values are often treated as equidistant, creating a semantic gap that obscures latent structures and degrades clustering quality. Although existing methods infer value relationships from within-dataset co-occurrence patterns, such inference becomes unreliable when samples are limited, leaving the semantic context of the data underexplored. To bridge this gap, we present ARISE (Attention-weighted Representation with Integrated Semantic Embeddings), which draws on external semantic knowledge from Large Language Models (LLMs) to construct semantic-aware representations that complement the metric space of categorical data for accurate clustering. That is, LLM is adopted to describe attribute values for representation enhancement, and the LLM-enhanced embeddings are combined with the original data to explore semantically prominent clusters. Experiments on eight benchmark datasets demonstrate consistent improvements over seven representative counterparts, with gains of 19-27%. Code is available at https://github.com/develop-yang/ARISE
Authors: Soroush Elyasi, Arya VarastehNezhad, Fattaneh Taghiyareh
Abstract: Personality assessment in career guidance and personnel selection traditionally relies on self-report questionnaires, which are susceptible to response bias, fatigue, and intentional distortion. Game-based assessment offers a promising alternative by capturing implicit behavioral signals during gameplay. This study proposes a multi-genre serious-game framework combined with machine-learning techniques to predict suitability for software development roles. Developer-relevant personality and behavioral traits were identified through a systematic literature review and an empirical study of professional software engineers. A custom mobile game was designed to elicit behaviors related to problem solving, planning, adaptability, persistence, time management, and information seeking. Fine-grained gameplay event data were collected and analyzed using a two-phase modeling strategy where suitability was predicted exclusively from gameplay-derived behavioral features. Results show that our model achieved up to 97% precision and 94% accuracy. Behavioral analysis revealed that proper candidates exhibited distinct gameplay patterns, such as more wins in puzzle-based games, more side challenges, navigating menus more frequently, and exhibiting fewer pauses, retries, and surrender actions. These findings demonstrate that implicit behavioral traces captured during gameplay is promising in predicting software-development suitability without explicit personality testing, supporting serious games as a scalable, engaging, and less biased alternative for career assessment.
Authors: Yoonhyuk Choi, Jiho Choi, Chanran Kim, Yumin Lee, Hawon Shin, Yeowon Jeon, Minjeong Kim, Jiwoo Kang
Abstract: Semi-supervised learning on real-world graphs is frequently challenged by heterophily, where the observed graph is unreliable or label-disassortative. Many existing graph neural networks either rely on a fixed adjacency structure or attempt to handle structural noise through regularization. In this work, we explicitly capture structural uncertainty by modeling a posterior distribution over signed adjacency matrices, allowing each edge to be positive, negative, or absent. We propose a sparse signed message passing network that is naturally robust to edge noise and heterophily, which can be interpreted from a Bayesian perspective. By combining (i) posterior marginalization over signed graph structures with (ii) sparse signed message aggregation, our approach offers a principled way to handle both edge noise and heterophily. Experimental results demonstrate that our method outperforms strong baseline models on heterophilic benchmarks under both synthetic and real-world structural noise.
Authors: Marzieh Amiri Shahbazi, Ali Baheri, Nasibeh Azadeh-Fard
Abstract: Clinical decision-making demands uncertainty quantification that provides both distribution-free coverage guarantees and risk-adaptive precision, requirements that existing methods fail to jointly satisfy. We present a hybrid Bayesian-conformal framework that addresses this fundamental limitation in healthcare predictions. Our approach integrates Bayesian hierarchical random forests with group-aware conformal calibration, using posterior uncertainties to weight conformity scores while maintaining rigorous coverage validity. Evaluated on 61,538 admissions across 3,793 U.S. hospitals and 4 regions, our method achieves target coverage (94.3% vs 95% target) with adaptive precision: 21% narrower intervals for low-uncertainty cases while appropriately widening for high-risk predictions. Critically, we demonstrate that well-calibrated Bayesian uncertainties alone severely under-cover (14.1%), highlighting the necessity of our hybrid approach. This framework enables risk-stratified clinical protocols, efficient resource planning for high-confidence predictions, and conservative allocation with enhanced oversight for uncertain cases, providing uncertainty-aware decision support across diverse healthcare settings.
Authors: Md Muhtasim Munif Fahim, Humyra Ankona, Md Monimul Huq, Md Rezaul Karim
Abstract: Background: While digital access has expanded rapidly in resource-constrained contexts, satisfaction with digital learning platforms varies significantly among students with seemingly equal connectivity. Traditional digital divide frameworks fail to explain these variations. Purpose: This study introduces the "Dependency Divide", a novel framework proposing that highly engaged students become conditionally vulnerable to infrastructure failures, challenging assumptions that engagement uniformly benefits learners in post-access environments. Methods: We conducted a cross-sectional study of 396 university students in Bangladesh using a three-stage analytical approach: (1) stability-validated K-prototypes clustering to identify student profiles, (2) profile-specific Random Forest models with SHAP and ALE analysis to determine satisfaction drivers, and (3) formal interaction analysis with propensity score matching to test the Dependency Divide hypothesis. Results: Three distinct profiles emerged: Casually Engaged (58%), Efficient Learners (35%), and Hyper-Engaged (7%). A significant interaction between educational device time and internet reliability (\b{eta} = 0.033, p = 0.028) confirmed the Dependency Divide: engagement increased satisfaction only when infrastructure remained reliable. Hyper-Engaged students showed greatest vulnerability despite or because of their sophisticated digital workflows. Policy simulations demonstrated that targeted reliability improvements for high-dependency users yielded 2.06 times greater returns than uniform interventions. Conclusions: In fragile infrastructure contexts, capability can become liability. Digital transformation policies must prioritize reliability for dependency-prone users, establish contingency systems, and educate students about dependency risks rather than uniformly promoting engagement.
Authors: Abidemi Koledoye, Chinemerem Unachukwu, Gold Nwobu, Hasin Rana
Abstract: State Space Models (SSMs) have emerged as a promising alternative to Transformers for long-context sequence modeling, offering linear $O(N)$ computational complexity compared to the Transformer's quadratic $O(N^2)$ scaling. This paper presents a comprehensive benchmarking study comparing the Mamba SSM against the LLaMA Transformer on long-context sequences, using dyadic therapy sessions as a representative test case. We evaluate both architectures across two dimensions: (1) computational efficiency, where we measure memory usage and inference speed from 512 to 8,192 tokens, and (2) representational efficiency, where we analyze hidden state dynamics and attention patterns. Our findings provide actionable insights for practitioners working with long-context applications, establishing precise conditions under which SSMs offer advantages over Transformers.
Authors: Maayan Gelboim, Amir Adler, Mauricio Araya-Polo
Abstract: We propose and test a method to reduce the dimensionality of Full Waveform Inversion (FWI) inputs as computational cost mitigation approach. Given modern seismic acquisition systems, the data (as input for FWI) required for an industrial-strength case is in the teraflop level of storage, therefore solving complex subsurface cases or exploring multiple scenarios with FWI become prohibitive. The proposed method utilizes a deep neural network with a binarized sensing layer that learns by compressed learning a succinct but consequential seismic acquisition layout from a large corpus of subsurface models. Thus, given a large seismic data set to invert, the trained network selects a smaller subset of the data, then by using representation learning, an autoencoder computes latent representations of the data, followed by K-means clustering of the latent representations to further select the most relevant data for FWI. Effectively, this approach can be seen as a hierarchical selection. The proposed approach consistently outperforms random data sampling, even when utilizing only 10% of the data for 2D FWI, these results pave the way to accelerating FWI in large scale 3D inversion.
Authors: Harshita Narnoli, Mihai Surdeanu
Abstract: In-context learning (ICL) has become a prominent paradigm to rapidly customize LLMs to new tasks without fine-tuning. However, despite the empirical evidence of its usefulness, we still do not truly understand how ICL works. In this paper, we compare the behavior of in-context learning with supervised classifiers trained on ICL demonstrations to investigate three research questions: (1) Do LLMs with ICL behave similarly to classifiers trained on the same examples? (2) If so, which classifiers are closer, those based on gradient descent (GD) or those based on k-nearest neighbors (kNN)? (3) When they do not behave similarly, what conditions are associated with differences in behavior? Using text classification as a use case, with six datasets and three LLMs, we observe that LLMs behave similarly to these classifiers when the relevance of demonstrations is high. On average, ICL is closer to kNN than logistic regression, giving empirical evidence that the attention mechanism behaves more similarly to kNN than GD. However, when demonstration relevance is low, LLMs perform better than these classifiers, likely because LLMs can back off to their parametric memory, a luxury these classifiers do not have.
Authors: Changhoon Song, Seungchan Ko, Youngjoon Hong
Abstract: Universal approximation theorems show that neural networks can approximate any continuous function; however, the number of parameters may grow exponentially with the ambient dimension, so these results do not fully explain the practical success of deep models on high-dimensional data. Barron space theory addresses this: if a target function belongs to a Barron space, a two-layer network with $n$ parameters achieves an $O(n^{-1/2})$ approximation error in $L^2$. Yet classical Barron spaces $\mathscr{B}^{s+1}$ still require stronger regularity than Sobolev spaces $H^s$, and existing depth-sensitive results often assume constraints such as $sL \le 1/2$. In this paper, we introduce a log-weighted Barron space $\mathscr{B}^{\log}$, which requires a strictly weaker assumption than $\mathscr{B}^s$ for any $s>0$. For this new function space, we first study embedding properties and carry out a statistical analysis via the Rademacher complexity. Then we prove that functions in $\mathscr{B}^{\log}$ can be approximated by deep ReLU networks with explicit depth dependence. We then define a family $\mathscr{B}^{s,\log}$, establish approximation bounds in the $H^1$ norm, and identify maximal depth scales under which these rates are preserved. Our results clarify how depth reduces regularity requirements for efficient representation, offering a more precise explanation for the performance of deep architectures beyond the classical Barron setting, and for their stable use in high-dimensional problems used today.
Authors: Anantha Sharma
Abstract: Detecting distributional drift in high-dimensional data streams presents fundamental challenges: global comparison methods scale poorly, projection-based approaches lose geometric structure, and re-clustering methods suffer from identity instability. This paper introduces Argus, A framework that reconceptualizes drift detection as tracking local statistics over a fixed spatial partition of the data manifold. The key contributions are fourfold. First, it is proved that Voronoi tessellations over canonical orthonormal frames yield drift metrics that are invariant to orthogonal transformations. The rotations and reflections that preserve Euclidean geometry. Second, it is established that this framework achieves O(N) complexity per snapshot while providing cell-level spatial localization of distributional change. Third, a graph-theoretic characterization of drift propagation is developed that distinguishes coherent distributional shifts from isolated perturbations. Fourth, product quantization tessellation is introduced for scaling to very high dimensions (d>500) by decomposing the space into independent subspaces and aggregating drift signals across subspaces. This paper formalizes the theoretical foundations, proves invariance properties, and presents experimental validation demonstrating that the framework correctly identifies drift under coordinate rotation while existing methods produce false positives. The tessellated approach offers a principled geometric foundation for distribution monitoring that preserves high-dimensional structure without the computational burden of pairwise comparisons.
Authors: Jorge L. Ruiz Williams
Abstract: Current multi-agent Large Language Model (LLM) frameworks suffer from linear memory scaling, rendering "System 2" parallel reasoning impractical on consumer hardware. We present Warp Cortex, an asynchronous architecture that theoretically enables million-agent cognitive scaling by decoupling agent logic from physical memory. Through Singleton Weight Sharing and a novel Topological Synapse--inspired by hybrid landmarking techniques from Topological Data Analysis (TDA)--we reduce memory complexity from O(N * L) to O(1) for weights and O(N * k) for context, where k << L. By treating the KV-cache as a point cloud in latent space, we apply witness-complex-inspired sparsification to preserve persistent homological features of the context manifold. On a single NVIDIA RTX 4090, we empirically demonstrate 100 concurrent agents at 2.2 GB total VRAM, with theoretical capacity exceeding 1,000 agents before compute latency becomes the bottleneck. We further introduce Referential Injection, a non-intrusive KV-cache update mechanism that allows asynchronous sub-agents to influence primary generation without stream disruption.
Authors: John Zhao
Abstract: The $\mu$-parameterization ($\mu$P) provides a principled foundation for large language model (LLM) training by prescribing width-independent learning dynamics, which in turn enables predictable scaling behavior and robust hyperparameter transfer across model sizes. A central requirement of $\mu$P is the satisfaction of certain spectral conditions on weight matrices, which ensure consistent feature learning and optimization behavior as model width grows. While these conditions are well understood in theory, guaranteeing their validity in practical training for matrix-based optimizers such as Muon is still under studied. Existing works that study Muon under $\mu$P exhibit important limitations: they either do not ensure that the spectral conditions hold throughout the entire training horizon, or require repeated spectral normalization (or Newton-Schulz iterations) applied to both weights and updates, leading to significant computational overhead and reduced practicality. In this work, we show how to reliably guarantee the spectral conditions required by $\mu$P for Muon during the entire training process. Our key insight is that for moderately large models, maintaining spectral control at the level of optimizer updates alone is sufficient to preserve $\mu$P-compatible scaling, eliminating the need for explicit spectral normalization of the weights. Based on this principle, we develop a variant of Muon, namely Muon++, that satisfies spectral condition throughout the training process. Our results bridge the gap between the theoretical promises of $\mu$P and the practical deployment of matrix-based optimizers in long-horizon training. We also take the first step towards an adaptive spectral condition by incorporating data-dependent effects, making it better suited for long-horizon LLM training.
Authors: Vladimer Khasia
Abstract: Scaling sequence modeling to extreme contexts requires balancing computational efficiency with representational expressivity. While Transformers provide precise retrieval via the attention mechanism, their quadratic $\mathcal{O}(T^2)$ complexity limits their application to long-horizon tasks. In this work, we propose the \textbf{Spectral-Window Hybrid (SWH)}, an architecture that decouples sequence modeling into two \textit{parallel} streams: a global branch utilizing the Convolution Theorem to model long-range decay dynamics in $\mathcal{O}(T \log T)$ time, and a local branch employing sliding-window attention for token interactions within a bounded context. By aggregating these representations, SWH avoids the computational bottleneck of global attention while retaining local precision. We demonstrate that SWH matches the perplexity of standard Transformers on short contexts while enabling efficient linear scaling to extended sequences. The code is available at https://github.com/VladimerKhasia/SWH
Authors: Yuyan Pi, Min Jin, Wentao Xie, Xinhua Liu
Abstract: Computational biology offers immense potential for reducing the high costs and protracted cycles of new drug development through adverse drug reaction (ADR) prediction. However, current methods remain impeded by drug data scarcity-induced cold-start challenge, closed label sets, and inadequate modeling of label dependencies. Here we propose an open-ended ADR prediction paradigm based on Graph-Motif feature fusion and Multi-Label Generation (GM-MLG). Leveraging molecular structure as an intrinsic and inherent feature, GM-MLG constructs a dual-graph representation architecture spanning the atomic level, the local molecular level (utilizing fine-grained motifs dynamically extracted via the BRICS algorithm combined with additional fragmentation rules), and the global molecular level. Uniquely, GM-MLG pioneers transforming ADR prediction from multi-label classification into Transformer Decoder-based multi-label generation. By treating ADR labels as discrete token sequences, it employs positional embeddings to explicitly capture dependencies and co-occurrence relationships within large-scale label spaces, generating predictions via autoregressive decoding to dynamically expand the prediction space. Experiments demonstrate GM-MLG achieves up to 38% improvement and an average gain of 20%, expanding the prediction space from 200 to over 10,000 types. Furthermore, it elucidates non-linear structure-activity relationships between ADRs and motifs via retrosynthetic motif analysis, providing interpretable and innovative support for systematic risk reduction in drug safety.
Authors: Ke Xiao, Haoze Zhang, Runze Mao, Han Li, Zhi X. Chen
Abstract: The rapid evolution of large language models (LLMs) is transforming artificial intelligence into autonomous research partners, yet a critical gap persists in complex scientific domains such as combustion modeling. Here, practical AI assistance requires the seamless integration of domain literature knowledge with robust execution capabilities for expertise-intensive tools such as computational fluid dynamics (CFD) codes. To bridge this gap, we introduce FlamePilot, an LLM agent designed to empower combustion modeling research through automated and self-corrective CFD workflows. FlamePilot differentiates itself through an architecture that leverages atomic tools to ensure the robust setup and execution of complex simulations in both OpenFOAM and extended frameworks such as DeepFlame. The system is also capable of learning from scientific articles, extracting key information to guide the simulation from initial setup to optimized results. Validation on a public benchmark shows FlamePilot achieved a perfect 1.0 executability score and a 0.438 success rate, surpassing the prior best reported agent scores of 0.625 and 0.250, respectively. Furthermore, a detailed case study on Moderate or Intense Low-oxygen Dilution (MILD) combustion simulation demonstrates its efficacy as a collaborative research copilot, where FlamePilot autonomously translated a research paper into a configured simulation, conducted the simulation, post-processed the results, proposed evidence-based refinements, and managed a multi-step parameter study to convergence under minimal human intervention. By adopting a transparent and interpretable paradigm, FlamePilot establishes a foundational framework for AI-empowered combustion modeling, fostering a collaborative partnership where the agent manages workflow orchestration, freeing the researcher for high-level analysis.
Authors: Mujin Zhou, Junzhe Zhang
Abstract: Causal discovery from data with unmeasured confounding factors is a challenging problem. This paper proposes an approach based on the f-GAN framework, learning the binary causal structure independent of specific weight values. We reformulate the structure learning problem as minimizing Bayesian free energy and prove that this problem is equivalent to minimizing the f-divergence between the true data distribution and the model-generated distribution. Using the f-GAN framework, we transform this objective into a min-max adversarial optimization problem. We implement the gradient search in the discrete graph space using Gumbel-Softmax relaxation.
Authors: Yen-Chia Chen, Hsing-Kuo Pao, Hanjuan Huang
Abstract: Deep learning models are widely used across computer vision and other domains. When working on the model induction, selecting the right architecture for a given dataset often relies on repetitive trial-and-error procedures. This procedure is time-consuming, resource-intensive, and difficult to automate. While previous work has explored performance prediction using partial training or complex simulations, these methods often require significant computational overhead or lack generalizability. In this work, we propose an alternative approach: a lightweight, two-stage framework that can estimate model performance before training given the understanding of the dataset and the focused deep model structures. The first stage predicts a baseline based on the analysis of some measurable properties of the dataset, while the second stage adjusts the estimation with additional information on the model's architectural and hyperparameter details. The setup allows the framework to generalize across datasets and model types. Moreover, we find that some of the underlying features used for prediction - such as dataset variance - can offer practical guidance for model selection, and can serve as early indicators of data quality. As a result, the framework can be used not only to forecast model performance, but also to guide architecture choices, inform necessary preprocessing procedures, and detect potentially problematic datasets before training begins.
Authors: Yongzhe Li, Lin Guan, Zihan Cai, Zuxian Lin, Jiyu Huang, Liukai Chen
Abstract: Developing deep learning models with strong adaptability to topological variations is of great practical significance for power flow analysis. To enhance model performance under variable system scales and improve robustness in branch power prediction, this paper proposes a Scale-adaptive Multi-task Power Flow Analysis (SaMPFA) framework. SaMPFA introduces a Local Topology Slicing (LTS) sampling technique that extracts subgraphs of different scales from the complete power network to strengthen the model's cross-scale learning capability. Furthermore, a Reference-free Multi-task Graph Learning (RMGL) model is designed for robust power flow prediction. Unlike existing approaches, RMGL predicts bus voltages and branch powers instead of phase angles. This design not only avoids the risk of error amplification in branch power calculation but also guides the model to learn the physical relationships of phase angle differences. In addition, the loss function incorporates extra terms that encourage the model to capture the physical patterns of angle differences and power transmission, further improving consistency between predictions and physical laws. Simulations on the IEEE 39-bus system and a real provincial grid in China demonstrate that the proposed model achieves superior adaptability and generalization under variable system scales, with accuracy improvements of 4.47% and 36.82%, respectively.
Authors: Zewei Yu, Jianqiu Xu, Caimin Li
Abstract: With the increasing volume of streaming data in industrial systems, online anomaly detection has become a critical task. The diverse and rapidly evolving data patterns pose significant challenges for online anomaly detection. Many existing anomaly detection methods are designed for offline settings or have difficulty in handling heterogeneous streaming data effectively. This paper proposes GDME, an unsupervised graph-based framework for online time series anomaly detection using model ensemble. GDME maintains a dynamic model pool that is continuously updated by pruning underperforming models and introducing new ones. It utilizes a dynamic graph structure to represent relationships among models and employs community detection on the graph to select an appropriate subset for ensemble. The graph structure is also used to detect concept drift by monitoring structural changes, allowing the framework to adapt to evolving streaming data. Experiments on seven heterogeneous time series demonstrate that GDME outperforms existing online anomaly detection methods, achieving improvements of up to 24%. In addition, its ensemble strategy provides superior detection performance compared with both individual models and average ensembles, with competitive computational efficiency.
Authors: Itay Safran
Abstract: We consider the problem of exact computation of the maximum function over $d$ real inputs using ReLU neural networks. We prove a depth hierarchy, wherein width $\Omega\big(d^{1+\frac{1}{2^{k-2}-1}}\big)$ is necessary to represent the maximum for any depth $3\le k\le \log_2(\log_2(d))$. This is the first unconditional super-linear lower bound for this fundamental operator at depths $k\ge3$, and it holds even if the depth scales with $d$. Our proof technique is based on a combinatorial argument and associates the non-differentiable ridges of the maximum with cliques in a graph induced by the first hidden layer of the computing network, utilizing Tur\'an's theorem from extremal graph theory to show that a sufficiently narrow network cannot capture the non-linearities of the maximum. This suggests that despite its simple nature, the maximum function possesses an inherent complexity that stems from the geometric structure of its non-differentiable hyperplanes, and provides a novel approach for proving lower bounds for deep neural networks.
Authors: Akshay Sasi, Malavika Pradeep, Nusaibah Farrukh, Rahul Venugopal, Elizabeth Sherly
Abstract: Understanding the interaction of neural and cardiac systems during cognitive activity is critical to advancing physiological computing. Although EEG has been the gold standard for assessing mental workload, its limited portability restricts its real-world use. Widely available ECG through wearable devices proposes a pragmatic alternative. This research investigates whether ECG signals can reliably reflect cognitive load and serve as proxies for EEG-based indicators. In this work, we present multimodal data acquired from two different paradigms involving working-memory and passive-listening tasks. For each modality, we extracted ECG time-domain HRV metrics and Catch22 descriptors against EEG spectral and Catch22 features, respectively. We propose a cross-modal XGBoost framework to project the ECG features onto EEG-representative cognitive spaces, thereby allowing workload inferences using only ECG. Our results show that ECG-derived projections expressively capture variation in cognitive states and provide good support for accurate classification. Our findings underpin ECG as an interpretable, real-time, wearable solution for everyday cognitive monitoring.
Authors: Jian Feng, Zhihong Huang
Abstract: Fine-tuning large language models (LLMs) with zeroth-order (ZO) optimization reduces memory by approximating gradients through function evaluations, but existing methods rely on one-step gradient estimates from random perturbations. We introduce Bayesian Subspace Zeroth-Order optimization (BSZO), a ZO optimizer that applies Kalman filtering to combine finite-difference information across multiple perturbation directions. By treating each finite-difference measurement as a noisy observation, BSZO builds a posterior distribution over the projected gradient and updates it through Bayesian inference, with a residual-based adaptive mechanism to adjust perturbation scales. Theoretical analysis shows that BSZO improves the convergence rate by a factor of $k/\gamma$ compared to standard ZO methods. Experiments on RoBERTa, Mistral, and OPT models show that BSZO outperforms MeZO, MeZO-Adam, and HiZOO across various tasks, achieving up to 6.67\% absolute average improvement on OPT-13B while keeping memory usage close to inference-only baselines (1.00$\times$--1.08$\times$ of MeZO).
Authors: Ze Peng, Jian Zhang, Yisen Wang, Lei Qi, Yinghuan Shi, Yang Gao
Abstract: Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to derive tighter bounds. However, we observe that although the flatness bias is crucial for SGD's generalization, these bounds fail to capture the improved generalization under better flatness and are also numerically loose. This is caused by the inadequate leverage of SGD's flatness bias in existing IT bounds. This paper derives a more flatness-leveraging IT bound for the flatness-favoring SGD. The bound indicates the learned models generalize better if the large-variance directions of the final weight covariance have small local curvatures in the loss landscape. Experiments on deep neural networks show our bound not only correctly reflects the better generalization when flatness is improved, but is also numerically much tighter. This is achieved by a flexible technique called "omniscient trajectory". When applied to Gradient Descent's minimax excess risk on convex-Lipschitz-Bounded problems, it improves representative IT bounds' $\Omega(1)$ rates to $O(1/\sqrt{n})$. It also implies a by-pass of memorization-generalization trade-offs.
Authors: Myung-Hwan Jang, Jeong-Min Park, Yunyong Ko, Sang-Wook Kim
Abstract: Graph neural networks (GNNs) have achieved breakthroughs in various real-world downstream tasks due to their powerful expressiveness. As the scale of real-world graphs has been continuously growing, \textit{a storage-based approach to GNN training} has been studied, which leverages external storage (e.g., NVMe SSDs) to handle such web-scale graphs on a single machine. Although such storage-based GNN training methods have shown promising potential in large-scale GNN training, we observed that they suffer from a severe bottleneck in data preparation since they overlook a critical challenge: \textit{how to handle a large number of small storage I/Os}. To address the challenge, in this paper, we propose a novel storage-based GNN training framework, named \textsf{AGNES}, that employs a method of \textit{block-wise storage I/O processing} to fully utilize the I/O bandwidth of high-performance storage devices. Moreover, to further enhance the efficiency of each storage I/O, \textsf{AGNES} employs a simple yet effective strategy, \textit{hyperbatch-based processing} based on the characteristics of real-world graphs. Comprehensive experiments on five real-world graphs reveal that \textsf{AGNES} consistently outperforms four state-of-the-art methods, by up to 4.1$\times$ faster than the best competitor. Our code is available at https://github.com/Bigdasgit/agnes-kdd26.
Authors: Ruofeng Yang, Yongcan Li, Bo Jiang, Cheng Chen, Shuai Li
Abstract: Recently, diffusion models have achieved a great performance with a small dataset of size $n$ and a fast optimization process. However, the estimation error of diffusion models suffers from the curse of dimensionality $n^{-1/D}$ with the data dimension $D$. Since images are usually a union of low-dimensional manifolds, current works model the data as a union of linear subspaces with Gaussian latent and achieve a $1/\sqrt{n}$ bound. Though this modeling reflects the multi-manifold property, the Gaussian latent can not capture the multi-modal property of the latent manifold. To bridge this gap, we propose the mixture subspace of low-rank mixture of Gaussian (MoLR-MoG) modeling, which models the target data as a union of $K$ linear subspaces, and each subspace admits a mixture of Gaussian latent ($n_k$ modals with dimension $d_k$). With this modeling, the corresponding score function naturally has a mixture of expert (MoE) structure, captures the multi-modal information, and contains nonlinear property. We first conduct real-world experiments to show that the generation results of MoE-latent MoG NN are much better than MoE-latent Gaussian score. Furthermore, MoE-latent MoG NN achieves a comparable performance with MoE-latent Unet with $10 \times$ parameters. These results indicate that the MoLR-MoG modeling is reasonable and suitable for real-world data. After that, based on such MoE-latent MoG score, we provide a $R^4\sqrt{\Sigma_{k=1}^Kn_k}\sqrt{\Sigma_{k=1}^Kn_kd_k}/\sqrt{n}$ estimation error, which escapes the curse of dimensionality by using data structure. Finally, we study the optimization process and prove the convergence guarantee under the MoLR-MoG modeling. Combined with these results, under a setting close to real-world data, this work explains why diffusion models only require a small training sample and enjoy a fast optimization process to achieve a great performance.
Authors: Itai Morad, Nir Shlezinger, Yonina C. Eldar
Abstract: Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: $(i)$ when the teacher provides the exact Bayes Class Probabilities (BCPs); and $(ii)$ supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.
Authors: Yijie Zhou, Shi Pu
Abstract: Decentralized optimization has emerged as a critical paradigm for distributed learning, enabling scalable training while preserving data privacy through peer-to-peer collaboration. However, existing methods often suffer from communication bottlenecks due to frequent synchronization between nodes. We present Overlapping Local Decentralized SGD (OLDSGD), a novel approach to accelerate decentralized training by computation-communication overlapping, significantly reducing network idle time. With a deliberately designed update, OLDSGD preserves the same average update as Local SGD while avoiding communication-induced stalls. Theoretically, we establish non-asymptotic convergence rates for smooth non-convex objectives, showing that OLDSGD retains the same iteration complexity as standard Local Decentralized SGD while improving per-iteration runtime. Empirical results demonstrate OLDSGD's consistent improvements in wall-clock time convergence under different levels of communication delays. With minimal modifications to existing frameworks, OLDSGD offers a practical solution for faster decentralized learning without sacrificing theoretical guarantees.
Authors: Fan Xu, Wei Gong, Hao Wu, Lilan Peng, Nan Wang, Qingsong Wen, Xian Wu, Kun Wang, Xibin Zhao
Abstract: Wildfires, as an integral component of the Earth system, are governed by a complex interplay of atmospheric, oceanic, and terrestrial processes spanning a vast range of spatiotemporal scales. Modeling their global activity on large timescales is therefore a critical yet challenging task. While deep learning has recently achieved significant breakthroughs in global weather forecasting, its potential for global wildfire behavior prediction remains underexplored. In this work, we reframe this problem and introduce the Hierarchical Graph ODE (HiGO), a novel framework designed to learn the multi-scale, continuous-time dynamics of wildfires. Specifically, we represent the Earth system as a multi-level graph hierarchy and propose an adaptive filtering message passing mechanism for both intra- and inter-level information flow, enabling more effective feature extraction and fusion. Furthermore, we incorporate GNN-parameterized Neural ODE modules at multiple levels to explicitly learn the continuous dynamics inherent to each scale. Through extensive experiments on the SeasFire Cube dataset, we demonstrate that HiGO significantly outperforms state-of-the-art baselines on long-range wildfire forecasting. Moreover, its continuous-time predictions exhibit strong observational consistency, highlighting its potential for real-world applications.
Authors: Pengfei Qu, Wenyu Ouyang, Chi Zhang, Yikai Chai, Shuolong Xu, Lei Ye, Yongri Piao, Miao Zhang, Huchuan Lu
Abstract: Predicting river flow in places without streamflow records is challenging because basins respond differently to climate, terrain, vegetation, and soils. Traditional basin attributes describe some of these differences, but they cannot fully represent the complexity of natural environments. This study examines whether AlphaEarth Foundation embeddings, which are learned from large collections of satellite images rather than designed by experts, offer a more informative way to describe basin characteristics. These embeddings summarize patterns in vegetation, land surface properties, and long-term environmental dynamics. We find that models using them achieve higher accuracy when predicting flows in basins not used for training, suggesting that they capture key physical differences more effectively than traditional attributes. We further investigate how selecting appropriate donor basins influences prediction in ungauged regions. Similarity based on the embeddings helps identify basins with comparable environmental and hydrological behavior, improving performance, whereas adding many dissimilar basins can reduce accuracy. The results show that satellite-informed environmental representations can strengthen hydrological forecasting and support the development of models that adapt more easily to different landscapes.
Authors: Zibo Zhao (Arizona State University), Yuanting Zha (ShanghaiTech University), Haipeng Zhang (ShanghaiTech University), Xingcheng Xu (Shanghai Artificial Intelligence Laboratory)
Abstract: Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how a unified optimization objective gives rise to functionally distinct capabilities of generating solutions and evaluating when to revise them remains opaque. To address this question, we introduce the Gradient Attribution Property to characterize how reward gradients distribute across policy components, formalized through the Two-Stage Decision-Sampling (DS) Hypothesis, which decomposes the policy into sampling ($\pi_{sample}$) for generation and decision ($\pi_{d}$) for verification. We prove that surrogate rewards exhibit Balanced Gradient Attribution, while SFT and KL penalties exhibit Unbalanced Gradient Attribution, with length-weighting creating asymmetric regularization that constrains $\pi_{sample}$ while leaving $\pi_{d}$ under-optimized, providing an theoretical explanation of why RL succeeds where SFT fails. We also empirically validate our theoretical predictions on arithmetic reasoning demonstrates that RL's superior generalization stems primarily from improved decision-making ($\pi_{d}$) rather than sampling capabilities, providing a first-principles mechanistic explanation for self-correction in thinking models.
Authors: Xin Di, Xinglin Piao, Fei Wang, Guodong Jing, Yong Zhang
Abstract: Precipitation nowcasting is critically important for meteorological forecasting. Deep learning-based Radar Echo Extrapolation (REE) has become a predominant nowcasting approach, yet it suffers from poor generalization due to its reliance on high-quality local training data and static model parameters, limiting its applicability across diverse regions and extreme events. To overcome this, we propose REE-TTT, a novel model that incorporates an adaptive Test-Time Training (TTT) mechanism. The core of our model lies in the newly designed Spatio-temporal Test-Time Training (ST-TTT) block, which replaces the standard linear projections in TTT layers with task-specific attention mechanisms, enabling robust adaptation to non-stationary meteorological distributions and thereby significantly enhancing the feature representation of precipitation. Experiments under cross-regional extreme precipitation scenarios demonstrate that REE-TTT substantially outperforms state-of-the-art baseline models in prediction accuracy and generalization, exhibiting remarkable adaptability to data distribution shifts.
Authors: Md Istiauk Hossain Rifat, Moin Khan, Mohammad Zunaed
Abstract: The textile industry in Bangladesh is one of the most energy-intensive sectors, yet its monitoring practices remain largely outdated, resulting in inefficient power usage and high operational costs. To address this, we propose a real-time Non-Intrusive Load Monitoring (NILM)-based framework tailored for industrial applications, with a focus on identical motor-driven loads representing textile cutting machines. A hardware setup comprising voltage and current sensors, Arduino Mega and ESP8266 was developed to capture aggregate and individual load data, which was stored and processed on cloud platforms. A new dataset was created from three identical induction motors and auxiliary loads, totaling over 180,000 samples, to evaluate the state-of-the-art MATNILM model under challenging industrial conditions. Results indicate that while aggregate energy estimation was reasonably accurate, per-appliance disaggregation faced difficulties, particularly when multiple identical machines operated simultaneously. Despite these challenges, the integrated system demonstrated practical real-time monitoring with remote accessibility through the Blynk application. This work highlights both the potential and limitations of NILM in industrial contexts, offering insights into future improvements such as higher-frequency data collection, larger-scale datasets and advanced deep learning approaches for handling identical loads.
Authors: Umesh Vangapally, Wenhan Wu, Chen Chen, Zhishuai Guo
Abstract: Federated AUC maximization is a powerful approach for learning from imbalanced data in federated learning (FL). However, existing methods typically assume full client availability, which is rarely practical. In real-world FL systems, clients often participate in a cyclic manner: joining training according to a fixed, repeating schedule. This setting poses unique optimization challenges for the non-decomposable AUC objective. This paper addresses these challenges by developing and analyzing communication-efficient algorithms for federated AUC maximization under cyclic client participation. We investigate two key settings: First, we study AUC maximization with a squared surrogate loss, which reformulates the problem as a nonconvex-strongly-concave minimax optimization. By leveraging the Polyak-{\L}ojasiewicz (PL) condition, we establish a state-of-the-art communication complexity of $\widetilde{O}(1/\epsilon^{1/2})$ and iteration complexity of $\widetilde{O}(1/\epsilon)$. Second, we consider general pairwise AUC losses. We establish a communication complexity of $O(1/\epsilon^3)$ and an iteration complexity of $O(1/\epsilon^4)$. Further, under the PL condition, these bounds improve to communication complexity of $\widetilde{O}(1/\epsilon^{1/2})$ and iteration complexity of $\widetilde{O}(1/\epsilon)$. Extensive experiments on benchmark tasks in image classification, medical imaging, and fraud detection demonstrate the superior efficiency and effectiveness of our proposed methods.
Authors: Hao Xiang Li, Yash Shah, Lorenzo Giusti
Abstract: In the face of adverse motives, it is indispensable to achieve a consensus. Elections have been the canonical way by which modern democracy has operated since the 17th century. Nowadays, they regulate markets, provide an engine for modern recommender systems or peer-to-peer networks, and remain the main approach to represent democracy. However, a desirable universal voting rule that satisfies all hypothetical scenarios is still a challenging topic, and the design of these systems is at the forefront of mechanism design research. Automated mechanism design is a promising approach, and recent works have demonstrated that set-invariant architectures are uniquely suited to modelling electoral systems. However, various concerns prevent the direct application to real-world settings, such as robustness to strategic voting. In this paper, we generalise the expressive capability of learned voting rules, and combine improvements in neural network architecture with adversarial training to improve the resilience of voting rules while maximizing social welfare. We evaluate the effectiveness of our methods on both synthetic and real-world datasets. Our method resolves critical limitations of prior work regarding learning voting rules by representing elections using bipartite graphs, and learning such voting rules using graph neural networks. We believe this opens new frontiers for applying machine learning to real-world elections.
Authors: He Sun, Jiwoong Shin, Ravi Dhar
Abstract: We study generative modeling of \emph{variable-length trajectories} -- sequences of visited locations/items with associated timestamps -- for downstream simulation and counterfactual analysis. A recurring practical issue is that standard mini-batch training can be unstable when trajectory lengths are highly heterogeneous, which in turn degrades \emph{distribution matching} for trajectory-derived statistics. We propose \textbf{length-aware sampling (LAS)}, a simple batching strategy that groups trajectories by length and samples batches from a single length bucket, reducing within-batch length heterogeneity (and making updates more consistent) without changing the model class. We integrate LAS into a conditional trajectory GAN with auxiliary time-alignment losses and provide (i) a distribution-level guarantee for derived variables under mild boundedness assumptions, and (ii) an IPM/Wasserstein mechanism explaining why LAS improves distribution matching by removing length-only shortcut critics and targeting within-bucket discrepancies. Empirically, LAS consistently improves matching of derived-variable distributions on a multi-mall dataset of shopper trajectories and on diverse public sequence datasets (GPS, education, e-commerce, and movies), outperforming random sampling across dataset-specific metrics.
Authors: Amichai Painsky
Abstract: Consider a collection of m competing machine learning algorithms. Given their performance on a benchmark of datasets, we would like to identify the best performing algorithm. Specifically, which algorithm is most likely to ``win'' (rank highest) on a future, unseen dataset. The standard maximum likelihood approach suggests counting the number of wins per each algorithm. In this work, we argue that there is much more information in the complete rankings. That is, the number of times that each algorithm finished second, third and so forth. Yet, it is not entirely clear how to effectively utilize this information for our purpose. In this work we introduce a novel conceptual framework for estimating the win probability for each of the m algorithms, given their complete rankings over a benchmark of datasets. Our proposed framework significantly improves upon currently known methods in synthetic and real-world examples.
Authors: Wei Liu, Yaoxin Wu, Yingqian Zhang, Thomas B\"ack, Yingjie Fan
Abstract: Deep reinforcement learning (DRL) has shown great promise in addressing multi-objective combinatorial optimization problems (MOCOPs). Nevertheless, the robustness of these learning-based solvers has remained insufficiently explored, especially across diverse and complex problem distributions. In this paper, we propose a unified robustness-oriented framework for preference-conditioned DRL solvers for MOCOPs. Within this framework, we develop a preference-based adversarial attack to generate hard instances that expose solver weaknesses, and quantify the attack impact by the resulting degradation on Pareto-front quality. We further introduce a defense strategy that integrates hardness-aware preference selection into adversarial training to reduce overfitting to restricted preference regions and improve out-of-distribution performance. The experimental results on multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multi-objective knapsack problem (MOKP) verify that our attack method successfully learns hard instances for different solvers. Furthermore, our defense method significantly strengthens the robustness and generalizability of neural solvers, delivering superior performance on hard or out-of-distribution instances.
Authors: Siba Smarak Panigrahi, Jovana Videnovi\'c, Maria Brbi\'c
Abstract: LLM-based reasoning models have enabled the development of agentic systems that act as co-scientists, assisting in multi-step scientific analysis. However, evaluating these systems is challenging, as it requires realistic, end-to-end research scenarios that integrate data analysis, interpretation, and the generation of new insights from the experimental data. To address this limitation, we introduce HeurekaBench, a framework to create benchmarks with exploratory, open-ended research questions for experimental datasets. Each such question is grounded in a scientific study and its corresponding code repository, and is created using a semi-automated pipeline that leverages multiple LLMs to extract insights and generate candidate workflows, which are then verified against reported findings. We instantiate the framework in single-cell biology to obtain sc-HeurekaBench benchmark and use it to compare state-of-the-art single-cell agents. We further showcase the benefits of our benchmark for quantitatively analyzing current design choices in agentic systems. We find that the addition of a critic module can improve ill-formed responses for open-source LLM-based agents by up to 22% and close the gap with their closed-source counterparts. Overall, HeurekaBench sets a path toward rigorous, end-to-end evaluation of scientific agents, grounding benchmark construction in real scientific workflows.
Authors: Yash Thesia, Meera Suthar
Abstract: Model stealing attacks pose an existential threat to Machine Learning as a Service (MLaaS), allowing adversaries to replicate proprietary models for a fraction of their training cost. While Data-Free Model Extraction (DFME) has emerged as a stealthy vector, it remains fundamentally constrained by the "Cold Start" problem: GAN-based adversaries waste thousands of queries converging from random noise to meaningful data. We propose DiMEx, a framework that weaponizes the rich semantic priors of pre-trained Latent Diffusion Models to bypass this initialization barrier entirely. By employing Random Embedding Bayesian Optimization (REMBO) within the generator's latent space, DiMEx synthesizes high-fidelity queries immediately, achieving 52.1 percent agreement on SVHN with just 2,000 queries - outperforming state-of-the-art GAN baselines by over 16 percent. To counter this highly semantic threat, we introduce the Hybrid Stateful Ensemble (HSE) defense, which identifies the unique "optimization trajectory" of latent-space attacks. Our results demonstrate that while DiMEx evades static distribution detectors, HSE exploits this temporal signature to suppress attack success rates to 21.6 percent with negligible latency.
Authors: Erfan Hajihashemi, Yanning Shen
Abstract: Conformal prediction is a framework for uncertainty quantification that constructs prediction sets for previously unseen data, guaranteeing coverage of the true label with a specified probability. However, the efficiency of these prediction sets, measured by their size, depends on the choice of the underlying learning model. Relying on a single fixed model may lead to suboptimal performance in online environments, as a single model may not consistently perform well across all time steps. To mitigate this, prior work has explored selecting a model from a set of candidates. However, this approach becomes computationally expensive as the number of candidate models increases. Moreover, poorly performing models in the set may also hinder the effectiveness. To tackle this challenge, this work develops a novel multi-model online conformal prediction algorithm that reduces computational complexity and improves prediction efficiency. At each time step, a bipartite graph is generated to identify a subset of effective models, from which a model is selected to construct the prediction set. Experiments demonstrate that our method outperforms existing multi-model conformal prediction techniques in terms of both prediction set size and computational efficiency.
Authors: Mohammed Ayalew Belay, Adil Rasheed, Pierluigi Salvo Rossi
Abstract: Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, with the advent of digital twins and data-driven decision-making, several statistical and machine-learning methods have been proposed. However, these methods face several challenges, such as dependence on only real sensor datasets, limited labeled data, high false alarm rates, and privacy concerns. To address these problems, we propose a suite of digital twin-integrated federated learning (DTFL) methods that enhance global model performance while preserving data privacy and communication efficiency. Specifically, we present five novel approaches: Digital Twin-Based Meta-Learning (DTML), Federated Parameter Fusion (FPF), Layer-wise Parameter Exchange (LPE), Cyclic Weight Adaptation (CWA), and Digital Twin Knowledge Distillation (DTKD). Each method introduces a unique mechanism to combine synthetic and real-world knowledge, balancing generalization with communication overhead. We conduct an extensive experiment using a publicly available cyber-physical anomaly detection dataset. For a target accuracy of 80%, CWA reaches the target in 33 rounds, FPF in 41 rounds, LPE in 48 rounds, and DTML in 87 rounds, whereas the standard FedAvg baseline and DTKD do not reach the target within 100 rounds. These results highlight substantial communication-efficiency gains (up to 62% fewer rounds than DTML and 31% fewer than LPE) and demonstrate that integrating DT knowledge into FL accelerates convergence to operationally meaningful accuracy thresholds for IIoT anomaly detection.
Authors: Kareem Ahmed, Sameer Singh
Abstract: Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM distribution to a set of high-probability continuations, but rely on greedy heuristics that introduce myopic distortions, yielding sentences that are homogeneous, repetitive and incoherent. In this paper, we introduce EPIC, a hyperparameter-free decoding approach that incorporates the entropy of future trajectories into LM decoding. EPIC explicitly regulates the amount of uncertainty expressed at every step of generation, aligning the sampling distribution's entropy to the aleatoric (data) uncertainty. Through Entropy-Aware Lazy Gumbel-Max sampling, EPIC manages to be exact, while also being efficient, requiring only a sublinear number of entropy evaluations per step. Unlike current baselines, EPIC yields sampling distributions that are empirically well-aligned with the entropy of the underlying data distribution. Across creative writing and summarization tasks, EPIC consistently improves LM-as-judge preference win-rates over widely used decoding strategies. These preference gains are complemented by automatic metrics, showing that EPIC produces more diverse generations and more faithful summaries. We also evaluate EPIC on mathematical reasoning, where it outperforms all baselines.
Authors: Selim Jerad, Anej Svete, Sophie Hao, Ryan Cotterell, William Merrill
Abstract: Transformers excel on tasks that process well-formed inputs according to some grammar, such as natural language and code. However, it remains unclear how they can process grammatical syntax. In fact, under standard complexity conjectures, standard transformers cannot recognize context-free languages (CFLs), a canonical formalism to describe syntax, or even regular languages, a subclass of CFLs (Merrill et al., 2022). Merrill & Sabharwal (2024) show that $\mathcal{O}(\log n)$ looping layers (w.r.t. input length $n$) allows transformers to recognize regular languages, but the question of context-free recognition remained open. In this work, we show that looped transformers with $\mathcal{O}(\log n)$ looping layers and $\mathcal{O}(n^6)$ padding tokens can recognize all CFLs. However, training and inference with $\mathcal{O}(n^6)$ padding tokens is potentially impractical. Fortunately, we show that, for natural subclasses such as unambiguous CFLs, the recognition problem on transformers becomes more tractable, requiring $\mathcal{O}(n^3)$ padding. We empirically validate our results and show that looping helps on a language that provably requires logarithmic depth. Overall, our results shed light on the intricacy of CFL recognition by transformers: While general recognition may require an intractable amount of padding, natural constraints such as unambiguity yield efficient recognition algorithms.
Authors: Intae Jeon, Yujeong Kwon, Hyungjoon Koo
Abstract: The ever-increasing adoption of Large Language Models in critical sectors like finance, healthcare, and government raises privacy concerns regarding the handling of sensitive Personally Identifiable Information (PII) during training. In response, regulations such as European Union's General Data Protection Regulation (GDPR) mandate the deletion of PII upon requests, underscoring the need for reliable and cost-effective data removal solutions. Machine unlearning has emerged as a promising direction for selectively forgetting data points. However, existing unlearning techniques typically apply a uniform forgetting strategy that neither accounts for the varying privacy risks posed by different PII attributes nor reflects associated business risks. In this work, we propose UnPII, the first PII-centric unlearning approach that prioritizes forgetting based on the risk of individual or combined PII attributes. To this end, we introduce the PII risk index (PRI), a composite metric that incorporates multiple dimensions of risk factors: identifiability, sensitivity, usability, linkability, permanency, exposability, and compliancy. The PRI enables a nuanced evaluation of privacy risks associated with PII exposures and can be tailored to align with organizational privacy policies. To support realistic assessment, we systematically construct a synthetic PII dataset (e.g., 1,700 PII instances) that simulates realistic exposure scenarios. UnPII seamlessly integrates with established unlearning algorithms, such as Gradient Ascent, Negative Preference Optimization, and Direct Preference Optimization, without modifying their underlying principles. Our experimental results demonstrate that UnPII achieves the improvements of accuracy up to 11.8%, utility up to 6.3%, and generalizability up to 12.4%, respectively, while incurring a modest fine-tuning overhead of 27.5% on average during unlearning.
Authors: NAVER Cloud HyperCLOVA X Team
Abstract: In this report, we present HyperCLOVA X 8B Omni, the first any-to-any omnimodal model in the HyperCLOVA X family that supports text, audio, and vision as both inputs and outputs. By consolidating multimodal understanding and generation into a single model rather than separate modality-specific pipelines, HyperCLOVA X 8B Omni serves as an 8B-scale omni-pathfinding point toward practical any-to-any omni assistants. At a high level, the model unifies modalities through a shared next-token prediction interface over an interleaved multimodal sequence, while vision and audio encoders inject continuous embeddings for fine-grained understanding and grounding. Empirical evaluations demonstrate competitive performance against comparably sized models across diverse input-output combinations spanning text, audio, and vision, in both Korean and English. We anticipate that the open-weight release of HyperCLOVA X 8B Omni will support a wide range of research and deployment scenarios.
Authors: Shamik Bhattacharyya, Rachel Kalpana Kalaimani
Abstract: Federated learning is a privacy-focused approach towards machine learning where models are trained on client devices with locally available data and aggregated at a central server. However, the dependence on a single central server is challenging in the case of a large number of clients and even poses the risk of a single point of failure. To address these critical limitations of scalability and fault-tolerance, we present a distributed approach to federated learning comprising multiple servers with inter-server communication capabilities. While providing a fully decentralized approach, the designed framework retains the core federated learning structure where each server is associated with a disjoint set of clients with server-client communication capabilities. We propose a novel DFL (Distributed Federated Learning) algorithm which uses alternating periods of local training on the client data followed by global training among servers. We show that the DFL algorithm, under a suitable choice of parameters, ensures that all the servers converge to a common model value within a small tolerance of the ideal model, thus exhibiting effective integration of local and global training models. Finally, we illustrate our theoretical claims through numerical simulations.
Authors: Qi Wei, Junchao Fan, Zhao Yang, Jianhua Wang, Jingkai Mao, Xiaolin Chang
Abstract: Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment. As a primary countermeasure, adversarial training improves policy robustness by training the AD agent in the presence of an adversary that deliberately introduces perturbations. Existing approaches typically model the interaction as a zero-sum game with continuous attacks. However, such designs overlook the inherent asymmetry between the agent and the adversary and then fail to reflect the sparsity of safety-critical risks, rendering the achieved robustness inadequate for practical AD scenarios. To address these limitations, we introduce criticality-aware robust RL (CARRL), a novel adversarial training approach for handling sparse, safety-critical risks in autonomous driving. CARRL consists of two interacting components: a risk exposure adversary (REA) and a risk-targeted robust agent (RTRA). We model the interaction between the REA and RTRA as a general-sum game, allowing the REA to focus on exposing safety-critical failures (e.g., collisions) while the RTRA learns to balance safety with driving efficiency. The REA employs a decoupled optimization mechanism to better identify and exploit sparse safety-critical moments under a constrained budget. However, such focused attacks inevitably result in a scarcity of adversarial data. The RTRA copes with this scarcity by jointly leveraging benign and adversarial experiences via a dual replay buffer and enforces policy consistency under perturbations to stabilize behavior. Experimental results demonstrate that our approach reduces the collision rate by at least 22.66\% across all cases compared to state-of-the-art baseline methods.
Authors: Dennis Jabs, Aditya Mohan, Marius Lindauer
Abstract: Deep Reinforcement Learning (RL) agents often learn policies that achieve the same episodic return yet behave very differently, due to a combination of environmental (random transitions, initial conditions, reward noise) and algorithmic (minibatch selection, exploration noise) factors. In continuous control tasks, even small parameter shifts can produce unstable gaits, complicating both algorithm comparison and real-world transfer. Previous work has shown that such instability arises when policy updates traverse noisy neighborhoods and that the spread of post-update return distribution $R(\theta)$, obtained by repeatedly sampling minibatches, updating $\theta$, and measuring final returns, is a useful indicator of this noise. Although explicitly constraining the policy to maintain a narrow $R(\theta)$ can improve stability, directly estimating $R(\theta)$ is computationally expensive in high-dimensional settings. We propose an alternative that takes advantage of environmental stochasticity to mitigate update-induced variability. Specifically, we model state-action return distribution through a distributional critic and then bias the advantage function of PPO using higher-order moments (skewness and kurtosis) of this distribution. By penalizing extreme tail behaviors, our method discourages policies from entering parameter regimes prone to instability. We hypothesize that in environments where post-update critic values align poorly with post-update returns, standard PPO struggles to produce a narrow $R(\theta)$. In such cases, our moment-based correction narrows $R(\theta)$, improving stability by up to 75% in Walker2D, while preserving comparable evaluation returns.
Authors: Peiyan Hu, Haodong Feng, Hongyuan Liu, Tongtong Yan, Wenhao Deng, Tianrun Gao, Rong Zheng, Haoren Zheng, Chenglei Yu, Chuanrui Wang, Kaiwen Li, Zhi-Ming Ma, Dezhi Zhou, Xingcai Lu, Dixia Fan, Tailin Wu
Abstract: Predicting the evolution of complex physical systems remains a central problem in science and engineering. Despite rapid progress in scientific Machine Learning (ML) models, a critical bottleneck is the lack of expensive real-world data, resulting in most current models being trained and validated on simulated data. Beyond limiting the development and evaluation of scientific ML, this gap also hinders research into essential tasks such as sim-to-real transfer. We introduce RealPDEBench, the first benchmark for scientific ML that integrates real-world measurements with paired numerical simulations. RealPDEBench consists of five datasets, three tasks, eight metrics, and ten baselines. We first present five real-world measured datasets with paired simulated datasets across different complex physical systems. We further define three tasks, which allow comparisons between real-world and simulated data, and facilitate the development of methods to bridge the two. Moreover, we design eight evaluation metrics, spanning data-oriented and physics-oriented metrics, and finally benchmark ten representative baselines, including state-of-the-art models, pretrained PDE foundation models, and a traditional method. Experiments reveal significant discrepancies between simulated and real-world data, while showing that pretraining with simulated data consistently improves both accuracy and convergence. In this work, we hope to provide insights from real-world data, advancing scientific ML toward bridging the sim-to-real gap and real-world deployment. Our benchmark, datasets, and instructions are available at https://realpdebench.github.io/.
Authors: Chenyu Hu, Qiming Hu, Sinan Chen, Nianyu Li, Mingyue Zhang, Jialong Li
Abstract: Federated Learning (FL) enables multiple clients to collaboratively train a shared model without exposing local data. However, backdoor attacks pose a significant threat to FL. These attacks aim to implant a stealthy trigger into the global model, causing it to mislead on inputs that possess a specific trigger while functioning normally on benign data. Although pre-aggregation detection is a main defense direction, existing state-of-the-art defenses often rely on fixed defense parameters. This reliance makes them vulnerable to single-point-of-failure risks, rendering them less effective against sophisticated attackers. To address these limitations, we propose FAROS, an enhanced FL framework that incorporates Adaptive Differential Scaling (ADS) and Robust Core-set Computing (RCC). The ADS mechanism adjusts the defense's sensitivity dynamically, based on the dispersion of uploaded gradients by clients in each round. This allows it to counter attackers who strategically shift between stealthiness and effectiveness. Furthermore, the RCC effectively mitigates the risk of single-point failure by computing the centroid of a core set comprising clients with the highest confidence. We conducted extensive experiments across various datasets, models, and attack scenarios. The results demonstrate that our method outperforms current defenses in both attack success rate and main task accuracy.
Authors: Qiantao Yang, Liquan Chen, Mingfu Xue, Songze Li
Abstract: Federated learning has drawn widespread interest from researchers, yet the data heterogeneity across edge clients remains a key challenge, often degrading model performance. Existing methods enhance model compatibility with data heterogeneity by splitting models and knowledge distillation. However, they neglect the insufficient communication bandwidth and computing power on the client, failing to strike an effective balance between addressing data heterogeneity and accommodating limited client resources. To tackle this limitation, we propose a personalized federated learning method based on cosine sparsification parameter packing and dual-weighted aggregation (FedCSPACK), which effectively leverages the limited client resources and reduces the impact of data heterogeneity on model performance. In FedCSPACK, the client packages model parameters and selects the most contributing parameter packages for sharing based on cosine similarity, effectively reducing bandwidth requirements. The client then generates a mask matrix anchored to the shared parameter package to improve the alignment and aggregation efficiency of sparse updates on the server. Furthermore, directional and distribution distance weights are embedded in the mask to implement a weighted-guided aggregation mechanism, enhancing the robustness and generalization performance of the global model. Extensive experiments across four datasets using ten state-of-the-art methods demonstrate that FedCSPACK effectively improves communication and computational efficiency while maintaining high model accuracy.
Authors: Shuta Kikuchi, Shu Tanaka
Abstract: Detecting high-order epistasis is a fundamental challenge in genetic association studies due to the combinatorial explosion of candidate locus combinations. Although multifactor dimensionality reduction (MDR) is a widely used method for evaluating epistasis, exhaustive MDR-based searches become computationally infeasible as the number of loci or the interaction order increases. In this paper, we define the epistasis detection problem as a black-box optimization problem and solve it with a factorization machine with quadratic optimization annealing (FMQA). We propose an efficient epistasis detection method based on FMQA, in which the classification error rate (CER) computed by MDR is used as a black-box objective function. Experimental evaluations were conducted using simulated case-control datasets with predefined high-order epistasis. The results demonstrate that the proposed method successfully identified ground-truth epistasis across various interaction orders and the numbers of genetic loci within a limited number of iterations. These results indicate that the proposed method is effective and computationally efficient for high-order epistasis detection.
Authors: Jiawen Zhang, Lipeng He, Kejia Chen, Jian Lou, Jian Liu, Xiaohu Yang, Ruoxi Jia
Abstract: Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not only incur significant computational overhead during realignment but also lead to noticeable degradation in model utility. Contrary to this belief, we show that safety alignment can be fully recovered with only a single safety example, without sacrificing utility and at minimal cost. Remarkably, this recovery is effective regardless of the number of harmful examples used in fine-tuning or the size of the underlying model, and convergence is achieved within just a few epochs. Furthermore, we uncover the low-rank structure of the safety gradient, which explains why such efficient correction is possible. We validate our findings across five safety-aligned LLMs and multiple datasets, demonstrating the generality of our approach.
Authors: Yuexuan Xia, Yinghao Zhang, Yalin Liu, Hong-Ning Dai, Yong Xia
Abstract: Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, making OSFL attractive for privacy-sensitive medical applications. However, existing methods aggregate predictions from all clients to form a global teacher. Under non-IID data, conflicting predictions cancel out during averaging, yielding near-uniform soft labels that provide weak supervision for distillation. We propose FedBiCross, a personalized OSFL framework with three stages: (1) clustering clients by model output similarity to form coherent sub-ensembles, (2) bi-level cross-cluster optimization that learns adaptive weights to selectively leverage beneficial cross-cluster knowledge while suppressing negative transfer, and (3) personalized distillation for client-specific adaptation. Experiments on four medical image datasets demonstrate that FedBiCross consistently outperforms state-of-the-art baselines across different non-IID degrees.
Authors: Ungsik Kim, Suwon Lee
Abstract: The Faithful Shapley Interaction (FSI) index uniquely satisfies the faithfulness axiom among Shapley interaction indices, but computing FSI requires $O(d^\ell \cdot 2^d)$ time and existing implementations use $O(4^d)$ memory. We present TT-FSI, which exploits FSI's algebraic structure via Matrix Product Operators (MPO). Our main theoretical contribution is proving that the linear operator $v \mapsto \text{FSI}(v)$ admits an MPO representation with TT-rank $O(\ell d)$, enabling an efficient sweep algorithm with $O(\ell^2 d^3 \cdot 2^d)$ time and $O(\ell d^2)$ core storage an exponential improvement over existing methods. Experiments on six datasets ($d=8$ to $d=20$) demonstrate up to 280$\times$ speedup over baseline, 85$\times$ over SHAP-IQ, and 290$\times$ memory reduction. TT-FSI scales to $d=20$ (1M coalitions) where all competing methods fail.
Authors: Yuxuan Li, Harshith Reddy Kethireddy, Srijita Das
Abstract: Learning from Preferences in Reinforcement Learning (PbRL) has gained attention recently, as it serves as a natural fit for complicated tasks where the reward function is not easily available. However, preferences often come with uncertainty and noise if they are not from perfect teachers. Much prior literature aimed to detect noise, but with limited types of noise and most being uniformly distributed with no connection to observations. In this work, we formalize the notion of targeted feature-dependent noise and propose several variants like trajectory feature noise, trajectory similarity noise, uncertainty-aware noise, and Language Model noise. We evaluate feature-dependent noise, where noise is correlated with certain features in complex continuous control tasks from DMControl and Meta-world. Our experiments show that in some feature-dependent noise settings, the state-of-the-art noise-robust PbRL method's learning performance is significantly deteriorated, while PbRL method with no explicit denoising can surprisingly outperform noise-robust PbRL in majority settings. We also find language model's noise exhibits similar characteristics to feature-dependent noise, thereby simulating realistic humans and call for further study in learning with feature-dependent noise robustly.
Authors: Ryo Iwaki, Takayuki Osogami
Abstract: While Distributional Reinforcement Learning (DRL) methods have demonstrated strong performance in online settings, its success in offline scenarios remains limited. We hypothesize that a key limitation of existing offline DRL methods lies in their approach to uniformly underestimate return quantiles. This uniform pessimism can lead to overly conservative value estimates, ultimately hindering generalization and performance. To address this, we introduce a novel concept called quantile distortion, which enables non-uniform pessimism by adjusting the degree of conservatism based on the availability of supporting data. Our approach is grounded in theoretical analysis and empirically validated, demonstrating improved performance over uniform pessimism.
Authors: Firuz Kamalov, Hana Sulieman, Witold Pedrycz
Abstract: Imbalanced data affects a wide range of machine learning applications, from healthcare to network security. As SMOTE is one of the most popular approaches to addressing this issue, it is imperative to validate it not only empirically but also theoretically. In this paper, we provide a rigorous theoretical analysis of SMOTE's convergence properties. Concretely, we prove that the synthetic random variable Z converges in probability to the underlying random variable X. We further prove a stronger convergence in mean when X is compact. Finally, we show that lower values of the nearest neighbor rank lead to faster convergence offering actionable guidance to practitioners. The theoretical results are supported by numerical experiments using both real-life and synthetic data. Our work provides a foundational understanding that enhances data augmentation techniques beyond imbalanced data scenarios.
Authors: Willem R\"opke, Samuel Coward, Andrei Lupu, Thomas Foster, Tim Rockt\"aschel, Jakob Foerster
Abstract: Recent advances in reasoning models have yielded impressive results in mathematics and coding. However, most approaches rely on static datasets, which have been suggested to encourage memorisation and limit generalisation. We introduce D\'ej\`aQ, a framework that departs from this paradigm by jointly evolving a diverse set of synthetic mathematical problems alongside model training. This evolutionary process adapts to the model's ability throughout training, optimising problems for learnability. We propose two LLM-driven mutation strategies in which the model itself mutates the training data, either by altering contextual details or by directly modifying problem structure. We find that the model can generate novel and meaningful problems, and that these LLM-driven mutations improve RL training. We analyse key aspects of D\'ej\`aQ, including the validity of generated problems and computational overhead. Our results underscore the potential of dynamically evolving training data to enhance mathematical reasoning and indicate broader applicability, which we will support by open-sourcing our code.
Authors: Tieu-Long Phan, Nhu-Ngoc Nguyen Song, Peter F. Stadler
Abstract: We present SynRXN, a unified benchmarking framework and open-data resource for computer-aided synthesis planning (CASP). SynRXN decomposes end-to-end synthesis planning into five task families, covering reaction rebalancing, atom-to-atom mapping, reaction classification, reaction property prediction, and synthesis route design. Curated, provenance-tracked reaction corpora are assembled from heterogeneous public sources into a harmonized representation and packaged as versioned datasets for each task family, with explicit source metadata, licence tags, and machine-readable manifests that record checksums, and row counts. For every task, SynRXN provides transparent splitting functions that generate leakage-aware train, validation, and test partitions, together with standardized evaluation workflows and metric suites tailored to classification, regression, and structured prediction settings. For sensitive benchmarking, we combine public training and validation data with held-out gold-standard test sets, and contamination-prone tasks such as reaction rebalancing and atom-to-atom mapping are distributed only as evaluation sets and are explicitly not intended for model training. Scripted build recipes enable bitwise-reproducible regeneration of all corpora across machines and over time, and the entire resource is released under permissive open licences to support reuse and extension. By removing dataset heterogeneity and packaging transparent, reusable evaluation scaffolding, SynRXN enables fair longitudinal comparison of CASP methods, supports rigorous ablations and stress tests along the full reaction-informatics pipeline, and lowers the barrier for practitioners who seek robust and comparable performance estimates for real-world synthesis planning workloads.
Authors: Bo Yin, Qi Li, Runpeng Yu, Xinchao Wang
Abstract: Instruction tuning increasingly relies on LLM-based prompt refinement, where prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction alignment. This motivates an instance-level audit problem: for a fine-tuned model and a training prompt-response pair, can we infer whether the model was trained on the original prompt or its LLM-refined version within a mixed corpus? This matters for dataset governance and dispute resolution when training data are contested. However, it is non-trivial in practice: refined and raw instances are interleaved in the training corpus with unknown, source-dependent mixture ratios, making it harder to develop provenance methods that generalize across models and training setups. In this paper, we formalize this audit task as Refinement Provenance Inference (RPI) and show that prompt refinement yields stable, detectable shifts in teacher-forced token distributions, even when semantic differences are not obvious. Building on this phenomenon, we propose RePro, a logit-based provenance framework that fuses teacher-forced likelihood features with logit-ranking signals. During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access. Empirically, RePro consistently attains strong performance and transfers well across refiners, suggesting that it exploits refiner-agnostic distribution shifts rather than rewrite-style artifacts.
Authors: Julie Keisler (ARCHES), Anastase Alexandre Charantonis (ARCHES), Yannig Goude (EDF R\&D OSIRIS, LMO), Boutheina Oueslati (EDF R\&D OSIRIS), Claire Monteleoni (ARCHES)
Abstract: Domain alignment refers broadly to learning correspondences between data distributions from distinct domains. In this work, we focus on a setting where domains share underlying structural patterns despite differences in their specific realizations. The task is particularly challenging in the absence of paired observations, which removes direct supervision across domains. We introduce a generative framework, called SerpentFlow (SharEd-structuRe decomPosition for gEnerative domaiN adapTation), for unpaired domain alignment. SerpentFlow decomposes data within a latent space into a shared component common to both domains and a domain-specific one. By isolating the shared structure and replacing the domain-specific component with stochastic noise, we construct synthetic training pairs between shared representations and target-domain samples, thereby enabling the use of conditional generative models that are traditionally restricted to paired settings. We apply this approach to super-resolution tasks, where the shared component naturally corresponds to low-frequency content while high-frequency details capture domain-specific variability. The cutoff frequency separating low- and high-frequency components is determined automatically using a classifier-based criterion, ensuring a data-driven and domain-adaptive decomposition. By generating pseudo-pairs that preserve low-frequency structures while injecting stochastic high-frequency realizations, we learn the conditional distribution of the target domain given the shared representation. We implement SerpentFlow using Flow Matching as the generative pipeline, although the framework is compatible with other conditional generative approaches. Experiments on synthetic images, physical process simulations, and a climate downscaling task demonstrate that the method effectively reconstructs high-frequency structures consistent with underlying low-frequency patterns, supporting shared-structure decomposition as an effective strategy for unpaired domain alignment.
Authors: Yifan Zhu, John C. Duchi, Benjamin Van Roy
Abstract: We prove that Thompson sampling exhibits $\tilde{O}(\sigma d \sqrt{T} + d r \sqrt{\mathrm{Tr}(\Sigma_0)})$ Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(\mu_0, \Sigma_0)$ prior distribution on the coefficients, where $d$ is the dimension, $T$ is the time horizon, $r$ is the maximum $\ell_2$ norm of the actions, and $\sigma^2$ is the noise variance. In contrast to existing regret bounds, this shows that to within logarithmic factors, the prior-dependent ``burn-in'' term $d r \sqrt{\mathrm{Tr}(\Sigma_0)}$ decouples additively from the minimax (long run) regret $\sigma d \sqrt{T}$. Previous regret bounds exhibit a multiplicative dependence on these terms. We establish these results via a new ``elliptical potential'' lemma, and also provide a lower bound indicating that the burn-in term is unavoidable.
Authors: Felix Stollenwerk, Anna Lokrantz, Niclas Hertzberg
Abstract: Pretraining of large language models is not only expensive but also prone to certain training instabilities. A specific instability that often occurs for large learning rates at the end of training is output logit divergence. The most widely used mitigation strategy, z-loss, merely addresses the symptoms rather than the underlying cause of the problem. In this paper, we analyze the instability from the perspective of the output embeddings' geometry and identify its cause. Based on this, we propose output embedding centering (OEC) as a new mitigation strategy, and prove that it suppresses output logit divergence. OEC can be implemented in two different ways, as a deterministic operation called {\mu}-centering, or a regularization method called {\mu}-loss. Our experiments show that both variants outperform z-loss in terms of training stability and learning rate sensitivity. In particular, they ensure that training converges even for large learning rates when z-loss fails. Furthermore, we find that {\mu}-loss is significantly less sensitive to regularization hyperparameter tuning than z-loss.
Authors: Yiyang Wang, Xi Chen, Xiaogang Xu, Yu Liu, Hengshuang Zhao
Abstract: Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it faces challenges including low efficiency, dependency on stochastic samplers, and reward hacking. The problem is that rectified flow models are fundamentally different from LLMs: 1) For efficiency, online image sampling takes much more time and dominates the time of training. 2) For stochasticity, rectified flow is deterministic once the initial noise is fixed. Aiming at these problems and inspired by the effects of group-level rewards from LLMs, we design Group-level Direct Reward Optimization (GDRO). GDRO is a new post-training paradigm for group-level reward alignment that combines the characteristics of rectified flow models. Through rigorous theoretical analysis, we point out that GDRO supports full offline training that saves the large time cost for image rollout sampling. Also, it is diffusion-sampler-independent, which eliminates the need for the ODE-to-SDE approximation to obtain stochasticity. We also empirically study the reward hacking trap that may mislead the evaluation, and involve this factor in the evaluation using a corrected score that not only considers the original evaluation reward but also the trend of reward hacking. Extensive experiments demonstrate that GDRO effectively and efficiently improves the reward score of the diffusion model through group-wise offline optimization across the OCR and GenEval tasks, while demonstrating strong stability and robustness in mitigating reward hacking.
Authors: Wei Hu, Zewei Yu, Jianqiu Xu
Abstract: Multivariate time-series (MTS) anomaly detection is critical in domains such as service monitor, IoT, and network security. While multi-model methods based on selection or ensembling outperform single-model ones, they still face limitations: (i) selection methods rely on a single chosen model and are sensitive to the strategy; (ii) ensembling methods often combine all models or are restricted to univariate data; and (iii) most methods depend on fixed data dimensionality, limiting scalability. To address these, we propose DMPEAD, a Dynamic Model Pool and Ensembling framework for MTS Anomaly Detection. The framework first (i) constructs a diverse model pool via parameter transfer and diversity metric, then (ii) updates it with a meta-model and similarity-based strategy for adaptive pool expansion, subset selection, and pool merging, finally (iii) ensembles top-ranked models through proxy metric ranking and top-k aggregation in the selected subset, outputting the final anomaly detection result. Extensive experiments on 8 real-world datasets show that our model outperforms all baselines, demonstrating superior adaptability and scalability.
Authors: Yanhai Gan, Yipeng Chen, Ning Li, Xingguo Liu, Junyu Dong, Xianyao Chen
Abstract: The El Ni{~n}o-Southern Oscillation (ENSO) exerts profound influence on global climate variability, yet its prediction remains a grand challenge. Recent advances in deep learning have significantly improved forecasting skill, but the opacity of these models hampers scientific trust and operational deployment. Here, we introduce a mathematically grounded interpretability framework based on bounded variation function. By rescuing the "dead" neurons from the saturation zone of the activation function, we enhance the model's expressive capacity. Our analysis reveals that ENSO predictability emerges dominantly from the tropical Pacific, with contributions from the Indian and Atlantic Oceans, consistent with physical understanding. Controlled experiments affirm the robustness of our method and its alignment with established predictors. Notably, we probe the persistent Spring Predictability Barrier (SPB), finding that despite expanded sensitivity during spring, predictive performance declines-likely due to suboptimal variable selection. These results suggest that incorporating additional ocean-atmosphere variables may help transcend SPB limitations and advance long-range ENSO prediction.
Authors: Yizhi Liu
Abstract: Doubly-stochastic matrices (DSM) are increasingly utilized in structure-preserving deep architectures -- such as Optimal Transport layers and Sinkhorn-based attention -- to enforce numerical stability and probabilistic interpretability. In this work, we identify a critical spectral degradation phenomenon inherent to these constraints, termed the Homogeneity Trap. We demonstrate that the maximum-entropy bias, typical of Sinkhorn-based projections, drives the mixing operator towards the uniform barycenter, thereby suppressing the subdominant singular value \sigma_2 and filtering out high-frequency feature components. We derive a spectral bound linking \sigma_2 to the network's effective depth, showing that high-entropy constraints restrict feature transformation to a shallow effective receptive field. Furthermore, we formally demonstrate that Layer Normalization fails to mitigate this collapse in noise-dominated regimes; specifically, when spectral filtering degrades the Signal-to-Noise Ratio (SNR) below a critical threshold, geometric structure is irreversibly lost to noise-induced orthogonal collapse. Our findings highlight a fundamental trade-off between entropic stability and spectral expressivity in DSM-constrained networks.
Authors: Jiacheng Lyu, Bihua Bao
Abstract: The proliferation of large-scale datasets poses a major computational challenge to model training. The traditional data subsampling method works as a static, task independent preprocessing step which usually discards information that is critical to downstream prediction. In this paper, we introduces the antagonistic soft selection subsampling (ASSS) framework as is a novel paradigm that reconstructs data reduction into a differentiable end-to-end learning problem. ASSS uses the adversarial game between selector network and task network, and selector network learning assigns continuous importance weights to samples. This direct optimization implemented by Gumbel-Softmax relaxation allows the selector to identify and retain samples with the maximum amount of information for a specific task target under the guidance of the loss function that balances the fidelity and sparsity of the prediction. Theoretical analysis links this framework with the information bottleneck principle. Comprehensive experiments on four large-scale real world datasets show that ASSS has always been better than heuristic subsampling baselines such as clustering and nearest neighbor thinning in maintaining model performance. It is worth noting that ASSS can not only match, but also sometimes exceed the training performance of the entire dataset, showcasing the effect of intelligent denoising. This work establishes task aware data subsampling as a learnable component, providing a principled solution for effective large-scale data learning.
Authors: Hans Krupakar, V A Kandappan
Abstract: Neural networks for time series forecasting have relied on error metrics and architecture-specific interpretability approaches for model selection that don't apply across models of different families. To interpret forecasting models agnostic to the types of layers across state-of-the-art model families, we introduce Horizon Activation Mapping (HAM), a visual interpretability technique inspired by grad-CAM that uses gradient norm averages to study the horizon's subseries where grad-CAM studies attention maps over image data. We introduce causal and anti-causal modes to calculate gradient update norm averages across subseries at every timestep and lines of proportionality signifying uniform distributions of the norm averages. Optimization landscape studies with respect to changes in batch sizes, early stopping, train-val-test splits, univariate forecasting and dropouts are studied with respect to performances and subseries in HAM. Interestingly, batch size based differences in activities seem to indicate potential for existence of an exponential approximation across them per epoch relative to each other. Multivariate forecasting models including MLP-based CycleNet, N-Linear, N-HITS, self attention-based FEDformer, Pyraformer, SSM-based SpaceTime and diffusion-based Multi-Resolution DDPM over different horizon sizes trained over the ETTm2 dataset are used for HAM plots in this study. NHITS' neural approximation theorem and SpaceTime's exponential autoregressive activities have been attributed to trends in HAM plots over their training, validation and test sets. In general, HAM can be used for granular model selection, validation set choices and comparisons across different neural network model families.
Authors: Hyunjun Kim
Abstract: Weight initialization remains decisive for neural network optimization, yet existing methods are largely layer-agnostic. We study initialization for deeply-supervised architectures with auxiliary classifiers, where untrained auxiliary heads can destabilize early training through gradient interference. We propose LION-DG, a layer-informed initialization that zero-initializes auxiliary classifier heads while applying standard He-initialization to the backbone. We prove that this implements Gradient Awakening: auxiliary gradients are exactly zero at initialization, then phase in naturally as weights grow -- providing an implicit warmup without hyperparameters. Experiments on CIFAR-10 and CIFAR-100 with DenseNet-DS and ResNet-DS architectures demonstrate: (1) DenseNet-DS: +8.3% faster convergence on CIFAR-10 with comparable accuracy, (2) Hybrid approach: Combining LSUV with LION-DG achieves best accuracy (81.92% on CIFAR-10), (3) ResNet-DS: Positive speedup on CIFAR-100 (+11.3%) with side-tap auxiliary design. We identify architecture-specific trade-offs and provide clear guidelines for practitioners. LION-DG is simple, requires zero hyperparameters, and adds no computational overhead.
Authors: Ashish Rana, Ammar Shaker, Sascha Saralajew, Takashi Suzuki, Kosuke Yasuda, Shintaro Kato, Toshikazu Wada, Toshiyuki Fujikawa, Toru Kikutsuji
Abstract: Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the healthcare sector. We present a demonstration of how prototype-based learning can address these needs. Our proposed framework, ProtoPal, features both front- and back-end modes; it achieves superior quantitative performance while also providing an intuitive presentation of interventions and their simulated outcomes.
Authors: Weisen Yang, Hanqing Zhang, Wangren Qiu, Xuan Xiao, Weizhong Lin
Abstract: Accurate identification of protein binding sites is crucial for understanding biomolecular interaction mechanisms and for the rational design of drug targets. Traditional predictive methods often struggle to balance prediction accuracy with computational efficiency when capturing complex spatial conformations. To address this challenge, we propose an Edge-aware Graph Attention Network (Edge-aware GAT) model for the fine-grained prediction of binding sites across various biomolecules, including proteins, DNA/RNA, ions, ligands, and lipids. Our method constructs atom-level graphs and integrates multidimensional structural features, including geometric descriptors, DSSP-derived secondary structure, and relative solvent accessibility (RSA), to generate spatially aware embedding vectors. By incorporating interatomic distances and directional vectors as edge features within the attention mechanism, the model significantly enhances its representation capacity. On benchmark datasets, our model achieves an ROC-AUC of 0.93 for protein-protein binding site prediction, outperforming several state-of-the-art methods. The use of directional tensor propagation and residue-level attention pooling further improves both binding site localization and the capture of local structural details. Visualizations using PyMOL confirm the model's practical utility and interpretability. To facilitate community access and application, we have deployed a publicly accessible web server at http://119.45.201.89:5000/. In summary, our approach offers a novel and efficient solution that balances prediction accuracy, generalization, and interpretability for identifying functional sites in proteins.
Authors: Muxi Diao, Lele Yang, Wuxuan Gong, Yutong Zhang, Zhonghao Yan, Yufei Han, Kongming Liang, Weiran Xu, Zhanyu Ma
Abstract: Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities. We investigate this discrepancy and identify a fundamental distributional gap: while RL aligns with the model's internal belief, SFT forces the model to fit external supervision. This mismatch often manifests as "Confident Conflicts" tokens characterized by low probability but low entropy. In these instances, the model is highly confident in its own prediction but is forced to learn a divergent ground truth, triggering destructive gradient updates. To address this, we propose Entropy-Adaptive Fine-Tuning (EAFT). Unlike methods relying solely on prediction probability, EAFT utilizes token-level entropy as a gating mechanism to distinguish between epistemic uncertainty and knowledge conflict. This allows the model to learn from uncertain samples while suppressing gradients on conflicting data. Extensive experiments on Qwen and GLM series (ranging from 4B to 32B parameters) across mathematical, medical, and agentic domains confirm our hypothesis. EAFT consistently matches the downstream performance of standard SFT while significantly mitigating the degradation of general capabilities.
Authors: Kasper Green Larsen, Chirag Pabbaraju, Abhishek Shetty
Abstract: We study the extent to which standard machine learning algorithms rely on exchangeability and independence of data by introducing a monotone adversarial corruption model. In this model, an adversary, upon looking at a "clean" i.i.d. dataset, inserts additional "corrupted" points of their choice into the dataset. These added points are constrained to be monotone corruptions, in that they get labeled according to the ground-truth target function. Perhaps surprisingly, we demonstrate that in this setting, all known optimal learning algorithms for binary classification can be made to achieve suboptimal expected error on a new independent test point drawn from the same distribution as the clean dataset. On the other hand, we show that uniform convergence-based algorithms do not degrade in their guarantees. Our results showcase how optimal learning algorithms break down in the face of seemingly helpful monotone corruptions, exposing their overreliance on exchangeability.
Authors: Yu Li, Sizhe Tang, Rongqian Chen, Fei Xu Yu, Guangyu Jiang, Mahdi Imani, Nathaniel D. Bastian, Tian Lan
Abstract: Automated cyber defense (ACD) seeks to protect computer networks with minimal or no human intervention, reacting to intrusions by taking corrective actions such as isolating hosts, resetting services, deploying decoys, or updating access controls. However, existing approaches for ACD, such as deep reinforcement learning (RL), often face difficult exploration in complex networks with large decision/state spaces and thus require an expensive amount of samples. Inspired by the need to learn sample-efficient defense policies, we frame ACD in CAGE Challenge 4 (CAGE-4 / CC4) as a context-based partially observable Markov decision problem and propose a planning-centric defense policy based on Monte Carlo Tree Search (MCTS). It explicitly models the exploration-exploitation tradeoff in ACD and uses statistical sampling to guide exploration and decision making. We make novel use of graph neural networks (GNNs) to embed observations from the network as attributed graphs, to enable permutation-invariant reasoning over hosts and their relationships. To make our solution practical in complex search spaces, we guide MCTS with learned graph embeddings and priors over graph-edit actions, combining model-free generalization and policy distillation with look-ahead planning. We evaluate the resulting agent on CC4 scenarios involving diverse network structures and adversary behaviors, and show that our search-guided, graph-embedding-based planning improves defense reward and robustness relative to state-of-the-art RL baselines.
Authors: Keyu Wang, Bingchen Miao, Wendong Bu, Yu Wu, Juncheng Li, Shengyu Zhang, Wenqiao Zhang, Siliang Tang, Jun Xiao, Yueting Zhuang
Abstract: The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective through imitation but suffers from low behavioral diversity, while Reinforcement Learning is capable of discovering novel strategies through exploration but heavily relies on manually designed reward functions. To address the conflict between these two methods, we present CORE, a Code-based Inverse Self-Training Framework with Graph Expansion that bridges imitation and exploration, offering a novel training framework that promotes behavioral diversity while eliminating the reliance on manually reward design. Specifically, we introduce Semantic Code Abstraction to automatically infers reward functions from expert demonstrations without manual design. The inferred reward function, referred to as the Label Function, is executable code that verifies one key step within a task. Building on this, we propose Strategy Graph Expansion to enhance in-domain behavioral diversity, which constructs a multi-path graph called Strategy Graph that captures diverse valid solutions beyond expert demonstrations. Furthermore, we introduce Trajectory-Guided Extrapolation, which enriches out-of-domain behavioral diversity by utilizing both successful and failed trajectories to expand the task space. Experiments on Web and Android platforms demonstrate that CORE significantly improves both overall performance and generalization, highlighting its potential as a robust and generalizable training paradigm for building powerful virtual agents.
Authors: Haoyu Zhou, Ping Xue, Tianfan Fu, Hao Zhang
Abstract: Deploying 3D graph neural networks (GNNs) that are equivariant to 3D rotations (the group SO(3)) on edge devices is challenging due to their high computational cost. This paper addresses the problem by compressing and accelerating an SO(3)-equivariant GNN using low-bit quantization techniques. Specifically, we introduce three innovations for quantized equivariant transformers: (1) a magnitude-direction decoupled quantization scheme that separately quantizes the norm and orientation of equivariant (vector) features, (2) a branch-separated quantization-aware training strategy that treats invariant and equivariant feature channels differently in an attention-based $SO(3)$-GNN, and (3) a robustness-enhancing attention normalization mechanism that stabilizes low-precision attention computations. Experiments on the QM9 and rMD17 molecular benchmarks demonstrate that our 8-bit models achieve accuracy on energy and force predictions comparable to full-precision baselines with markedly improved efficiency. We also conduct ablation studies to quantify the contribution of each component to maintain accuracy and equivariance under quantization, using the Local error of equivariance (LEE) metric. The proposed techniques enable the deployment of symmetry-aware GNNs in practical chemistry applications with 2.37--2.73x faster inference and 4x smaller model size, without sacrificing accuracy or physical symmetry.
Authors: Shristi Das Biswas, Yue Zhang, Anwesan Pal, Radhika Bhargava, Kaushik Roy
Abstract: Large Language Models (LLMs) suffer severe catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing approaches are fundamentally limited: replay-based methods are impractical and privacy-violating, while strict orthogonality-based methods collapse under scale: each new task is projected onto an orthogonal complement, progressively reducing the residual degrees of freedom and eliminating forward transfer by forbidding overlap in shared representations. In this work, we introduce ELLA, a training framework built on the principle of selective subspace de-correlation. Rather than forbidding all overlap, ELLA explicitly characterizes the structure of past updates and penalizes alignments along their high-energy, task-specific directions, while preserving freedom in the low-energy residual subspaces to enable transfer. Formally, this is realized via a lightweight regularizer on a single aggregated update matrix. We prove this mechanism corresponds to an anisotropic shrinkage operator that bounds interference, yielding a penalty that is both memory- and compute-constant regardless of task sequence length. ELLA requires no data replay, no architectural expansion, and negligible storage. Empirically, it achieves state-of-the-art CL performance on three popular benchmarks, with relative accuracy gains of up to $9.6\%$ and a $35\times$ smaller memory footprint. Further, ELLA scales robustly across architectures and actively enhances the model's zero-shot generalization performance on unseen tasks, establishing a principled and scalable solution for constructive lifelong LLM adaptation.
Authors: Emrah Mete, Emin Erkan Korkmaz
Abstract: The rapid proliferation of Deep Learning is increasingly constrained by its heavy reliance on high-performance hardware, particularly Graphics Processing Units (GPUs). These specialized accelerators are not only prohibitively expensive and energy-intensive but also suffer from significant supply scarcity, limiting the ubiquity of Artificial Intelligence (AI) deployment on edge devices. The core of this inefficiency stems from the standard artificial perceptron's dependence on intensive matrix multiplications. However, biological nervous systems achieve unparalleled efficiency without such arithmetic intensity; synaptic signal transmission is regulated by physical ion channel limits and chemical neurotransmitter levels rather than a process that can be analogous to arithmetic multiplication. Inspired by this biological mechanism, we propose Neuro-Channel Networks (NCN), a novel multiplication-free architecture designed to decouple AI from expensive hardware dependencies. In our model, weights are replaced with Channel Widths that physically limit the signal magnitude, while a secondary parameter acts as a Neurotransmitter to regulate Signal Transmission based on sign logic. The forward pass relies exclusively on addition, subtraction, and bitwise operations (minimum, sign), eliminating floating-point multiplication entirely. In this proof-of-concept study, we demonstrate that NCNs can solve non-linearly separable problems like XOR and the Majority function with 100% accuracy using standard backpropagation, proving their capability to form complex decision boundaries without multiplicative weights. This architecture offers a highly efficient alternative for next-generation neuromorphic hardware, paving the way for running complex models on commodity CPUs or ultra-low-power chips without relying on costly GPU clusters.
Authors: Boris Kriuk, Fedor Kriuk
Abstract: Earthquake prediction and seismic hazard assessment remain fundamental challenges in geophysics, with existing machine learning approaches often operating as black boxes that ignore established physical laws. We introduce POSEIDON (Physics-Optimized Seismic Energy Inference and Detection Operating Network), a physics-informed energy-based model for unified multi-task seismic event prediction, alongside the Poseidon dataset -- the largest open-source global earthquake catalog comprising 2.8 million events spanning 30 years. POSEIDON embeds fundamental seismological principles, including the Gutenberg-Richter magnitude-frequency relationship and Omori-Utsu aftershock decay law, as learnable constraints within an energy-based modeling framework. The architecture simultaneously addresses three interconnected prediction tasks: aftershock sequence identification, tsunami generation potential, and foreshock detection. Extensive experiments demonstrate that POSEIDON achieves state-of-the-art performance across all tasks, outperforming gradient boosting, random forest, and CNN baselines with the highest average F1 score among all compared methods. Crucially, the learned physics parameters converge to scientifically interpretable values -- Gutenberg-Richter b-value of 0.752 and Omori-Utsu parameters p=0.835, c=0.1948 days -- falling within established seismological ranges while enhancing rather than compromising predictive accuracy. The Poseidon dataset is publicly available at https://huggingface.co/datasets/BorisKriuk/Poseidon, providing pre-computed energy features, spatial grid indices, and standardized quality metrics to advance physics-informed seismic research.
Authors: Dina El Zein, James Henderson
Abstract: We propose a privacy-preserving method for sharing text data by sharing noisy versions of their transformer embeddings. It has been shown that hidden representations learned by deep models can encode sensitive information from the input, making it possible for adversaries to recover the input data with considerable accuracy. This problem is exacerbated in transformer embeddings because they consist of multiple vectors, one per token. To mitigate this risk, we propose Nonparametric Variational Differential Privacy (NVDP), which ensures both useful data sharing and strong privacy protection. We take a differential privacy approach, integrating a Nonparametric Variational Information Bottleneck (NVIB) layer into the transformer architecture to inject noise into its multi-vector embeddings and thereby hide information, and measuring privacy protection with R\'enyi divergence and its corresponding Bayesian Differential Privacy (BDP) guarantee. Training the NVIB layer calibrates the noise level according to utility. We test NVDP on the GLUE benchmark and show that varying the noise level gives us a useful tradeoff between privacy and accuracy. With lower noise levels, our model maintains high accuracy while offering strong privacy guarantees, effectively balancing privacy and utility.
Authors: Ahmad Makinde
Abstract: High-Frequency trading (HFT) environments are characterised by large volumes of limit order book (LOB) data, which is notoriously noisy and non-linear. Alpha decay represents a significant challenge, with traditional models such as DeepLOB losing predictive power as the time horizon (k) increases. In this paper, using data from the FI-2010 dataset, we introduce Temporal Kolmogorov-Arnold Networks (T-KAN) to replace the fixed, linear weights of standard LSTMs with learnable B-spline activation functions. This allows the model to learn the 'shape' of market signals as opposed to just their magnitude. This resulted in a 19.1% relative improvement in the F1-score at the k = 100 horizon. The efficacy of T-KAN networks cannot be understated, producing a 132.48% return compared to the -82.76% DeepLOB drawdown under 1.0 bps transaction costs. In addition to this, the T-KAN model proves quite interpretable, with the 'dead-zones' being clearly visible in the splines. The T-KAN architecture is also uniquely optimized for low-latency FPGA implementation via High level Synthesis (HLS). The code for the experiments in this project can be found at https://github.com/AhmadMak/Temporal-Kolmogorov-Arnold-Networks-T-KAN-for-High-Frequency-Limit-Order-Book-Forecasting.
Authors: Hanzaleh Akbari Nodehi, Viveck R. Cadambe, Mohammad Ali Maddah-Ali
Abstract: Coding theory plays a crucial role in enabling reliable communication, storage, and computation. Classical approaches assume a worst-case adversarial model and ensure error correction and data recovery only when the number of honest nodes exceeds the number of adversarial ones by some margin. However, in some emerging decentralized applications, particularly in decentralized machine learning (DeML), participating nodes are rewarded for accepted contributions. This incentive structure naturally gives rise to rational adversaries who act strategically rather than behaving in purely malicious ways. In this paper, we first motivate the need for coding in the presence of rational adversaries, particularly in the context of outsourced computation in decentralized systems. We contrast this need with existing approaches and highlight their limitations. We then introduce the game of coding, a novel game-theoretic framework that extends coding theory to trust-minimized settings where honest nodes are not in the majority. Focusing on repetition coding, we highlight two key features of this framework: (1) the ability to achieve a non-zero probability of data recovery even when adversarial nodes are in the majority, and (2) Sybil resistance, i.e., the equilibrium remains unchanged even as the number of adversarial nodes increases. Finally, we explore scenarios in which the adversary's strategy is unknown and outline several open problems for future research.
Authors: Siddharth Joshi, Haoli Yin, Rishabh Adiga, Ricardo Monti, Aldo Carranza, Alex Fang, Alvin Deng, Amro Abbas, Brett Larsen, Cody Blakeney, Darren Teh, David Schwab, Fan Pan, Haakon Mongstad, Jack Urbanek, Jason Lee, Jason Telanoff, Josh Wills, Kaleigh Mentzer, Luke Merrick, Parth Doshi, Paul Burstein, Pratyush Maini, Scott Loftin, Spandan Das, Tony Jiang, Vineeth Dorna, Zhengping Wang, Bogdan Gaza, Ari Morcos, Matthew Leavitt
Abstract: Empirical evaluation serves as the primary compass guiding research progress in foundation models. Despite a large body of work focused on training frontier vision-language models (VLMs), approaches to their evaluation remain nascent. To guide their maturation, we propose three desiderata that evaluations should satisfy: (1) faithfulness to the modality and application, (2) discriminability between models of varying quality, and (3) efficiency in compute. Through this lens, we identify critical failure modes that violate faithfulness and discriminability, misrepresenting model capabilities: (i) multiple-choice formats reward guessing, poorly reflect downstream use cases, and saturate early as models improve; (ii) blindly solvable questions, which can be answered without images, constitute up to 70% of some evaluations; and (iii) mislabeled or ambiguous samples compromise up to 42% of examples in certain datasets. Regarding efficiency, the computational burden of evaluating frontier models has become prohibitive: by some accounts, nearly 20% of development compute is devoted to evaluation alone. Rather than discarding existing benchmarks, we curate them via transformation and filtering to maximize fidelity and discriminability. We find that converting multiple-choice questions to generative tasks reveals sharp capability drops of up to 35%. In addition, filtering blindly solvable and mislabeled samples improves discriminative power while simultaneously reducing computational cost. We release DatBench-Full, a cleaned evaluation suite of 33 datasets spanning nine VLM capabilities, and DatBench, a discriminative subset that achieves 13x average speedup (up to 50x) while closely matching the discriminative power of the original datasets. Our work outlines a path toward evaluation practices that are both rigorous and sustainable as VLMs continue to scale.
Authors: Yazan Obeidi, Amir Sarfi, Joel Lidin, Paul Janson, Eugene Belilovsky
Abstract: Pre-training large language models (LLMs) increasingly requires distributed compute, yet bandwidth constraints make it difficult to scale beyond well-provisioned datacenters-especially when model parallelism forces frequent, large inter-device communications. We study whether SparseLoCo, a low-communication data parallel method based on infrequent synchronization and sparse pseudo-gradient exchange, can be combined with low-bandwidth pipeline model parallelism via activation and activation-gradient compression. We introduce a heterogeneous distributed training framework where some participants host full replicas on high-bandwidth interconnects, while resource-limited participants are grouped to jointly instantiate a replica using pipeline parallelism with subspace-projected inter-stage communication. To make the recently introduced subspace pipeline compression compatible with SparseLoCo, we study a number of adaptations. Across large-scale language modeling experiments (178M-1B parameters) on standard pretraining corpora, we find that activation compression composes with SparseLoCo at modest cost, while selective (heterogeneous) compression consistently improves the loss-communication tradeoff relative to compressing all replicas-especially at aggressive compression ratios. These results suggest a practical path to incorporating low-bandwidth model parallelism and heterogeneous participants into LLM pre-training.
Authors: Haoyi Zhou, Shuo Li, Tianyu Chen, Qi Song, Chonghan Gao, Jianxin Li
Abstract: While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge distillation improves students' capability as a complement to Rotary Position Embeddings (RoPE) on window sizes (anchored from large models). Building on this insight, we propose LAid, which directly aims at the transfer of long-range attention mechanisms through two complementary components: (1) a progressive distance-weighted attention matching that dynamically emphasizes longer position differences during training, and (2) a learnable RoPE response gain modulation that selectively amplifies position sensitivity where needed. Extensive experiments across multiple model families demonstrate that LAid-distilled models achieve up to 3.2 times longer effective context windows compared to baseline small models, while maintaining or improving performance on standard VL benchmarks. Spectral analysis also suggests that LAid successfully preserves crucial low-frequency attention components that conventional methods fail to transfer. Our work not only provides practical techniques for building more efficient long-context VLMs but also offers theoretical insights into how positional understanding emerges and transfers during distillation.
Authors: Sarim Chaudhry
Abstract: Spiking neural networks (SNNs) offer a biologically grounded and energy-efficient alternative to conventional neural architectures; however, they struggle with long-range temporal dependencies due to fixed synaptic and membrane time constants. This paper introduces ChronoPlastic Spiking Neural Networks (CPSNNs), a novel architectural principle that enables adaptive temporal credit assignment by dynamically modulating synaptic decay rates conditioned on the state of the network. CPSNNs maintain multiple internal temporal traces and learn a continuous time-warping function that selectively preserves task-relevant information while rapidly forgetting noise. Unlike prior approaches based on adaptive membrane constants, attention mechanisms, or external memory, CPSNNs embed temporal control directly within local synaptic dynamics, preserving linear-time complexity and neuromorphic compatibility. We provide a formal description of the model, analyze its computational properties, and demonstrate empirically that CPSNNs learn long-gap temporal dependencies significantly faster and more reliably than standard SNN baselines. Our results suggest that adaptive temporal modulation is a key missing ingredient for scalable temporal learning in spiking systems.
Authors: \'Angel Miguel Garc\'ia-Vico, Huseyin Seker, Muhammad Afzal
Abstract: Coccidiosis, a disease caused by the Eimeria parasite, represents a major threat to the poultry and rabbit industries, demanding rapid and accurate diagnostic tools. While deep learning models offer high precision, their significant energy consumption limits their deployment in resource-constrained environments. This paper introduces a novel two-stage Spiking Neural Network (SNN) architecture, where a pre-trained Convolutional Neural Network is first converted into a spiking feature extractor and then coupled with a lightweight, unsupervised SNN classifier trained with Spike-Timing-Dependent Plasticity (STDP). The proposed model sets a new state-of-the-art, achieving 98.32\% accuracy in Eimeria classification. Remarkably, this performance is accomplished with a significant reduction in energy consumption, showing an improvement of more than 223 times compared to its traditional ANN counterpart. This work demonstrates a powerful synergy between high accuracy and extreme energy efficiency, paving the way for autonomous, low-power diagnostic systems on neuromorphic hardware.
Authors: Mohammadhossien Rashidi
Abstract: Exit timing after an IPO is one of the most consequential decisions for venture capital (VC) investors, yet existing research focuses mainly on describing when VCs exit rather than evaluating whether those choices are economically optimal. Meanwhile, large language models (LLMs) have shown promise in synthesizing complex financial data and textual information but have not been applied to post-IPO exit decisions. This study introduces a framework that uses LLMs to estimate the optimal time for VC exit by analyzing monthly post IPO information financial performance, filings, news, and market signals and recommending whether to sell or continue holding. We compare these LLM generated recommendations with the actual exit dates observed for VCs and compute the return differences between the two strategies. By quantifying gains or losses associated with following the LLM, this study provides evidence on whether AI-driven guidance can improve exit timing and complements traditional hazard and real-options models in venture capital research.
Authors: Ismail Ahmad Abdullah
Abstract: Contemporary AI systems achieve extraordinary performance yet remain opaque and non-verifiable, creating a crisis of trust for safety-critical deployment. We introduce MathLedger, a substrate for verifiable machine cognition that integrates formal verification, cryptographic attestation, and learning dynamics into a single epistemic loop. The system implements Reflexive Formal Learning (RFL), a symbolic analogue of gradient descent where updates are driven by verifier outcomes rather than statistical loss. Phase I experiments validate the measurement and governance substrate under controlled conditions. CAL-EXP-3 validates measurement infrastructure (Delta p computation, variance tracking); separate stress tests confirm fail-closed governance triggers correctly under out-of-bounds conditions. No convergence or capability claims are made. The contribution is infrastructural: a working prototype of ledger-attested learning that enables auditability at scale. Keywords: verifiable learning, formal verification, cryptographic attestation, reflexive feedback, fail-closed governance
Authors: Tangtang Wang, Kaijie Zhang, Kuangcong Liu
Abstract: In modern digital marketing, the growing complexity of advertisement data demands intelligent systems capable of understanding semantic relationships among products, audiences, and advertising content. To address this challenge, this paper proposes a Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System (KGSR-ADS) for advertisement retrieval and personalization. The proposed framework integrates a heterogeneous Ad-Knowledge Graph (Ad-KG) that captures multi-relational semantics, a Semantic Embedding Layer that leverages large language models (LLMs) such as GPT and LLaMA to generate context-aware vector representations, a GNN + Attention Model that infers cross-entity dependencies, and a Database Optimization & Retrieval Layer based on vector indexing (FAISS/Milvus) for efficient semantic search. This layered architecture enables both accurate semantic matching and scalable retrieval, allowing personalized ad recommendations under large-scale heterogeneous workloads.
Authors: Emily Lu, Gabriel Perez, Peter Baker, Daniel Irving, Santosh Kumar, Veronica Celorrio, Sylvia Britto, Thomas F. Headen, Miguel Gomez-Gonzalez, Connor Wright, Calum Green, Robert Scott Young, Oleg Kirichek, Ali Mortazavi, Sarah Day, Isabel Antony, Zoe Wright, Thomas Wood, Tim Snow, Jeyan Thiyagalingam, Paul Quinn, Martin Owen Jones, William David, James Le Houx
Abstract: Unravelling the complex processes governing battery degradation is critical to the energy transition, yet the efficacy of operando characterisation is severely constrained by a lack of Reliability, Representativeness, and Reproducibility (the 3Rs). Current methods rely on bespoke hardware and passive, pre-programmed methodologies that are ill-equipped to capture stochastic failure events. Here, using the Rutherford Appleton Laboratory's multi-modal toolkit as a case study, we expose the systemic inability of conventional experiments to capture transient phenomena like dendrite initiation. To address this, we propose Heuristic Operando experiments: a framework where an AI pilot leverages physics-based digital twins to actively steer the beamline to predict and deterministically capture these rare events. Distinct from uncertainty-driven active learning, this proactive search anticipates failure precursors, redefining experimental efficiency via an entropy-based metric that prioritises scientific insight per photon, neutron, or muon. By focusing measurements only on mechanistically decisive moments, this framework simultaneously mitigates beam damage and drastically reduces data redundancy. When integrated with FAIR data principles, this approach serves as a blueprint for the trusted autonomous battery laboratories of the future.
Authors: Joseph Oche Agada, Andrew McAninch, Haley Day, Yasemin Tanyu, Ewan McCombs, Seyed M. Koohpayeh, Brian H. Toby, Yishu Wang, Arpan Biswas
Abstract: Physical properties and functionalities of materials are dictated by global crystal structures as well as local defects. To establish a structure-property relationship, not only the crystallographic symmetry but also quantitative knowledge about defects are required. Here we present a hybrid Machine Learning framework that integrates a physically-constrained variational-autoencoder (pcVAE) with different Bayesian Optimization (BO) methods to systematically accelerate and improve crystal structure refinement with resolution of defects. We chose the pyrochlore structured Ho2Ti2O7 as a model system and employed the GSAS2 package for benchmarking crystallographic parameters from Rietveld refinement. However, the function space of these material systems is highly nonlinear, which limits optimizers like traditional Rietveld refinement, into trapping at local minima. Also, these naive methods don't provide an extensive learning about the overall function space, which is essential for large space, large time consuming explorations to identify various potential regions of interest. Thus, we present the approach of exploring the high Dimensional structure parameters of defect sensitive systems via pretrained pcVAE assisted BO and Sparse Axis Aligned BO. The pcVAE projects high-Dimensional diffraction data consisting of thousands of independently measured diffraction orders into a lowD latent space while enforcing scaling invariance and physical relevance. Then via BO methods, we aim to minimize the L2 norm based chisq errors in the real and latent spaces separately between experimental and simulated diffraction patterns, thereby steering the refinement towards potential optimum crystal structure parameters. We investigated and compared the results among different pcVAE assisted BO, non pcVAE assisted BO, and Rietveld refinement.
Authors: Likun Cao, James Evans
Abstract: This study offers a new perspective on the depth-versus-breadth debate in innovation strategy, by modeling inventive search within dynamic collective knowledge systems, and underscoring the importance of timing for technological impact. Using frontier machine learning to project patent citation networks in hyperbolic space, we analyze 4.9 million U.S. patents to examine how search strategies give rise to distinct temporal patterns in impact accumulation. We find that inventions based on deep search, which relies on a specialized understanding of complex recombination structures, drive higher short-term impact through early adoption within specialized communities, but face diminishing returns as innovations become "locked-in" with limited diffusion potential. Conversely, when inventions are grounded in broad search that spans disparate domains, they encounter initial resistance but achieve wider diffusion and greater long-term impact by reaching cognitively diverse audiences. Individual inventions require both depth and breadth for stable impact. Organizations can strategically balance approaches across multiple inventions: using depth to build reliable technological infrastructure while pursuing breadth to expand applications. We advance innovation theory by demonstrating how deep and broad search strategies distinctly shape the timing and trajectory of technological impact, and how individual inventors and organizations can leverage these mechanisms to balance exploitation and exploration.
Authors: Anthony Mikinka
Abstract: We present Universal Conditional Logic (UCL), a mathematical framework for prompt optimization that transforms prompt engineering from heuristic practice into systematic optimization. Through systematic evaluation (N=305, 11 models, 4 iterations), we demonstrate significant token reduction (29.8%, t(10)=6.36, p < 0.001, Cohen's d = 2.01) with corresponding cost savings. UCL's structural overhead function O_s(A) explains version-specific performance differences through the Over-Specification Paradox: beyond threshold S* = 0.509, additional specification degrades performance quadratically. Core mechanisms -- indicator functions (I_i in {0,1}), structural overhead (O_s = gamma * sum(ln C_k)), early binding -- are validated. Notably, optimal UCL configuration varies by model architecture -- certain models (e.g., Llama 4 Scout) require version-specific adaptations (V4.1). This work establishes UCL as a calibratable framework for efficient LLM interaction, with model-family-specific optimization as a key research direction.
Authors: KC Aashish, Md Zakir Hossain Zamil, Md Shafiqul Islam Mridul, Lamia Akter, Farmina Sharmin, Eftekhar Hossain Ayon, Md Maruf Bin Reza, Ali Hassan, Abdur Rahim, Sirapa Malla
Abstract: The rising energy footprint of artificial intelligence has become a measurable component of US data center emissions, yet cybersecurity research seldom considers its environmental cost. This study introduces an eco aware anomaly detection framework that unifies machine learning based network monitoring with real time carbon and energy tracking. Using the publicly available Carbon Aware Cybersecurity Traffic Dataset comprising 2300 flow level observations, we benchmark Logistic Regression, Random Forest, Support Vector Machine, Isolation Forest, and XGBoost models across energy, carbon, and performance dimensions. Each experiment is executed in a controlled Colab environment instrumented with the CodeCarbon toolkit to quantify power draw and equivalent CO2 output during both training and inference. We construct an Eco Efficiency Index that expresses F1 score per kilowatt hour to capture the trade off between detection quality and environmental impact. Results reveal that optimized Random Forest and lightweight Logistic Regression models achieve the highest eco efficiency, reducing energy consumption by more than forty percent compared to XGBoost while sustaining competitive detection accuracy. Principal Component Analysis further decreases computational load with negligible loss in recall. Collectively, these findings establish that integrating carbon and energy metrics into cybersecurity workflows enables environmentally responsible machine learning without compromising operational protection. The proposed framework offers a reproducible path toward sustainable carbon accountable cybersecurity aligned with emerging US green computing and federal energy efficiency initiatives.
Authors: Annabelle Yao
Abstract: RNA's diverse biological functions stem from its structural versatility, yet accurately predicting and designing RNA sequences given a 3D conformation (inverse folding) remains a challenge. Here, I introduce a deep learning framework that integrates Geometric Vector Perceptron (GVP) layers with a Transformer architecture to enable end-to-end RNA design. I construct a dataset consisting of experimentally solved RNA 3D structures, filtered and deduplicated from the BGSU RNA list, and evaluate performance using both sequence recovery rate and TM-score to assess sequence and structural fidelity, respectively. On standard benchmarks and RNA-Puzzles, my model achieves state-of-the-art performance, with recovery and TM-scores of 0.481 and 0.332, surpassing existing methods across diverse RNA families and length scales. Masked family-level validation using Rfam annotations confirms strong generalization beyond seen families. Furthermore, inverse-folded sequences, when refolded using AlphaFold3, closely resemble native structures, highlighting the critical role of geometric features captured by GVP layers in enhancing Transformer-based RNA design.
Authors: Annabelle Yao
Abstract: Socioeconomic integration is a critical dimension of social equity, yet persistent disparities remain in access to health insurance, education, and employment across different demographic groups. While previous studies have examined isolated aspects of inequality, there is limited research that integrates both statistical analysis and advanced machine learning to uncover hidden structures within population data. This study leverages statistical analysis ($\chi^2$ test of independence and Two Proportion Z-Test) and machine learning clustering techniques -- K-Modes and K-Prototypes -- along with t-SNE visualization and CatBoost classification to analyze socioeconomic integration and inequality. Using statistical tests, we identified the proportion of the population with healthcare insurance, quality education, and employment. With this data, we concluded that there was an association between employment and citizenship status. Moreover, we were able to determine 5 distinct population groups using Machine Learning classification. The five clusters our analysis identifies reveal that while citizenship status shows no association with workforce participation, significant disparities exist in access to employer-sponsored health insurance. Each cluster represents a distinct demographic of the population, showing that there is a primary split along the lines of educational attainment which separates Clusters 0 and 4 from Clusters 1, 2, and 3. Furthermore, labor force status and nativity serve as secondary differentiators. Non-citizens are also disproportionately concentrated in precarious employment without benefits, highlighting systemic inequalities in healthcare access. By uncovering demographic clusters that face compounded disadvantages, this research contributes to a more nuanced understanding of socioeconomic stratification.
Authors: Yuchao Hou (Shanxi Normal University, Taiyuan, China), Zixuan Zhang (Shanxi Normal University, Taiyuan, China), Jie Wang (Shanxi Normal University, Taiyuan, China), Wenke Huang (Nanyang Technological University, Singapore, Singapore), Lianhui Liang (Guangxi University, Nanning, China), Di Wu (La Trobe University, Melbourne, Australia), Zhiquan Liu (Jinan University, Guangzhou, China), Youliang Tian (Guizhou University, Guiyang, China), Jianming Zhu (Central University of Finance and Economics, Beijing, China), Jisheng Dang (Lanzhou University, Lanzhou, China), Junhao Dong (Nanyang Technological University, Singapore, Singapore), Zhongliang Guo (University of St Andrews, St Andrews, United Kingdom)
Abstract: As a critical application of computational intelligence in remote sensing, deep learning-based synthetic aperture radar (SAR) image target recognition facilitates intelligent perception but typically relies on centralized training, where multi-source SAR data are uploaded to a single server, raising privacy and security concerns. Federated learning (FL) provides an emerging computational intelligence paradigm for SAR image target recognition, enabling cross-site collaboration while preserving local data privacy. However, FL confronts critical security risks, where malicious clients can exploit SAR's multiplicative speckle noise to conceal backdoor triggers, severely challenging the robustness of the computational intelligence model. To address this challenge, we propose NADAFD, a noise-aware and dynamically adaptive federated defense framework that integrates frequency-domain, spatial-domain, and client-behavior analyses to counter SAR-specific backdoor threats. Specifically, we introduce a frequency-domain collaborative inversion mechanism to expose cross-client spectral inconsistencies indicative of hidden backdoor triggers. We further design a noise-aware adversarial training strategy that embeds $\Gamma$-distributed speckle characteristics into mask-guided adversarial sample generation to enhance robustness against both backdoor attacks and SAR speckle noise. In addition, we present a dynamic health assessment module that tracks client update behaviors across training rounds and adaptively adjusts aggregation weights to mitigate evolving malicious contributions. Experiments on MSTAR and OpenSARShip datasets demonstrate that NADAFD achieves higher accuracy on clean test samples and a lower backdoor attack success rate on triggered inputs than existing federated backdoor defenses for SAR target recognition.
Authors: Qiang Li, Shujian Yu, Liang Ma, Chen Ma, Jingyu Liu, Tulay Adali, Vince D. Calhoun
Abstract: Blind source separation, particularly through independent component analysis (ICA), is widely utilized across various signal processing domains for disentangling underlying components from observed mixed signals, owing to its fully data-driven nature that minimizes reliance on prior assumptions. However, conventional ICA methods rely on an assumption of linear mixing, limiting their ability to capture complex nonlinear relationships and to maintain robustness in noisy environments. In this work, we present deep deterministic nonlinear independent component analysis (DDICA), a novel deep neural network-based framework designed to address these limitations. DDICA leverages a matrix-based entropy function to directly optimize the independence criterion via stochastic gradient descent, bypassing the need for variational approximations or adversarial schemes. This results in a streamlined training process and improved resilience to noise. We validated the effectiveness and generalizability of DDICA across a range of applications, including simulated signal mixtures, hyperspectral image unmixing, modeling of primary visual receptive fields, and resting-state functional magnetic resonance imaging (fMRI) data analysis. Experimental results demonstrate that DDICA effectively separates independent components with high accuracy across a range of applications. These findings suggest that DDICA offers a robust and versatile solution for blind source separation in diverse signal processing tasks.
Authors: Sumaiya Ali, Areej Alhothali, Sameera Albasri, Ohoud Alzamzami, Ahmed Abduljabbar, Muhammad Alwazzan
Abstract: Placenta Accreta Spectrum (PAS) is a life-threatening obstetric complication involving abnormal placental invasion into the uterine wall. Early and accurate prenatal diagnosis is essential to reduce maternal and neonatal risks. This study aimed to develop and validate a deep learning framework that enhances PAS detection by integrating multiple imaging modalities. A multimodal deep learning model was designed using an intermediate feature-level fusion architecture combining 3D Magnetic Resonance Imaging (MRI) and 2D Ultrasound (US) scans. Unimodal feature extractors, a 3D DenseNet121-Vision Transformer for MRI and a 2D ResNet50 for US, were selected after systematic comparative analysis. Curated datasets comprising 1,293 MRI and 1,143 US scans were used to train the unimodal models and paired samples of patient-matched MRI-US scans was isolated for multimodal model development and evaluation. On an independent test set, the multimodal fusion model achieved superior performance, with an accuracy of 92.5% and an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.927, outperforming the MRI-only (82.5%, AUC 0.825) and US-only (87.5%, AUC 0.879) models. Integrating MRI and US features provides complementary diagnostic information, demonstrating strong potential to enhance prenatal risk assessment and improve patient outcomes.
Authors: Sheldon Paul, Izzat Alsmadi
Abstract: This paper presents a unified framework for evaluating Linux security hardening on the FABRIC testbed through aggregation of heterogeneous security auditing tools. We deploy three Ubuntu 22.04 nodes configured at baseline, partial, and full hardening levels, and evaluate them using Lynis, OpenSCAP, and AIDE across 108 audit runs. To address the lack of a consistent interpretation across tools, we implement a Unified Compliance Aggregator (UCA) that parses tool outputs, normalizes scores to a common 0--100 scale, and combines them into a weighted metric augmented by a customizable rule engine for organization-specific security policies. Experimental results show that full hardening increases OpenSCAP compliance from 39.7 to 71.8, while custom rule compliance improves from 39.3\% to 83.6\%. The results demonstrate that UCA provides a clearer and more reproducible assessment of security posture than individual tools alone, enabling systematic evaluation of hardening effectiveness in programmable testbed environments.
Authors: Joyjit Roy
Abstract: Automated negotiations in insurance and business-to-business (B2B) commerce encounter substantial challenges. Current systems force a trade-off between convenience and privacy by routing sensitive financial data through centralized servers, increasing security risks, and diminishing user trust. This study introduces a device-native autonomous Artificial Intelligence (AI) agent system for privacy-preserving negotiations. The proposed system operates exclusively on user hardware, enabling real-time bargaining while maintaining sensitive constraints locally. It integrates zero-knowledge proofs to ensure privacy and employs distilled world models to support advanced on-device reasoning. The architecture incorporates six technical components within an agentic AI workflow. Agents autonomously plan negotiation strategies, conduct secure multi-party bargaining, and generate cryptographic audit trails without exposing user data to external servers. The system is evaluated in insurance and B2B procurement scenarios across diverse device configurations. Results show an average success rate of 87%, a 2.4x latency improvement over cloud baselines, and strong privacy preservation through zero-knowledge proofs. User studies show 27% higher trust scores when decision trails are available. These findings establish a foundation for trustworthy autonomous agents in privacy-sensitive financial domains.
Authors: Subhankar Mishra
Abstract: 3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and inflate model sizes, hindering deployment in bandwidth-constrained applications. We present Clean-GS, a method for removing background clutter and floaters from 3DGS reconstructions using sparse semantic masks. Our approach combines whitelist-based spatial filtering with color-guided validation and outlier removal to achieve 60-80\% model compression while preserving object quality. Unlike existing 3DGS pruning methods that rely on global importance metrics, Clean-GS uses semantic information from as few as 3 segmentation masks (1\% of views) to identify and remove Gaussians not belonging to the target object. Our multi-stage approach consisting of (1) whitelist filtering via projection to masked regions, (2) depth-buffered color validation, and (3) neighbor-based outlier removal isolates monuments and objects from complex outdoor scenes. Experiments on Tanks and Temples show that Clean-GS reduces file sizes from 125MB to 47MB while maintaining rendering quality, making 3DGS models practical for web deployment and AR/VR applications. Our code is available at https://github.com/smlab-niser/clean-gs
Authors: Bishwajit Saha, Dmitry Krotov, Mohammed J. Zaki, Parikshit Ram
Abstract: Deep clustering - joint representation learning and latent space clustering - is a well studied problem especially in computer vision and text processing under the deep learning framework. While the representation learning is generally differentiable, clustering is an inherently discrete optimization task, requiring various approximations and regularizations to fit in a standard differentiable pipeline. This leads to a somewhat disjointed representation learning and clustering. In this work, we propose a novel loss function utilizing energy-based dynamics via Associative Memories to formulate a new deep clustering method, DCAM, which ties together the representation learning and clustering aspects more intricately in a single objective. Our experiments showcase the advantage of DCAM, producing improved clustering quality for various architecture choices (convolutional, residual or fully-connected) and data modalities (images or text).
Authors: Marcin Kolakowski, Vitomir Djaja-Josko
Abstract: The paper presents a concept of a dynamic accuracy estimation method, in which the localization errors are derived based on the measurement results used by the positioning algorithm. The concept was verified experimentally in a Wi\nobreakdash-Fi based indoor positioning system, where several regression methods were tested (linear regression, random forest, k-nearest neighbors, and neural networks). The highest positioning error estimation accuracy was achieved for random forest regression, with a mean absolute error of 0.72 m.
Authors: Shiao Wang, Xiao Wang, Haonan Zhao, Jiarui Xu, Bo Jiang, Lin Zhu, Xin Zhao, Yonghong Tian, Jin Tang
Abstract: Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking
Authors: Douglas Costa Braga, Daniel Oliveira Dantas
Abstract: We present a reproducible deep learning pipeline for leukemic cell classification, focusing on system architecture, experimental robustness, and software design choices for medical image analysis. Acute lymphoblastic leukemia (ALL) is the most common childhood cancer, requiring expert microscopic diagnosis that suffers from inter-observer variability and time constraints. The proposed system integrates an attention-based convolutional neural network combining EfficientNetV2-B3 with Squeeze-and-Excitation mechanisms for automated ALL cell classification. Our approach employs comprehensive data augmentation, focal loss for class imbalance, and patient-wise data splitting to ensure robust and reproducible evaluation. On the C-NMC 2019 dataset (12,528 original images from 62 patients), the system achieves a 97.89% F1-score and 97.89% accuracy on the test set, with statistical validation through 100-iteration Monte Carlo experiments confirming significant improvements (p < 0.001) over baseline methods. The proposed pipeline outperforms existing approaches by up to 4.67% while using 89% fewer parameters than VGG16 (15.2M vs. 138M). The attention mechanism provides interpretable visualizations of diagnostically relevant cellular features, demonstrating that modern attention-based architectures can improve leukemic cell classification while maintaining computational efficiency suitable for clinical deployment.
Authors: Zeyu Bian, Max Biggs, Ruijiang Gao, Zhengling Qi
Abstract: This paper develops a practical framework for using observational data to audit the consumer surplus effects of AI-driven decisions, specifically in targeted pricing and algorithmic lending. Traditional approaches first estimate demand functions and then integrate to compute consumer surplus, but these methods can be challenging to implement in practice due to model misspecification in parametric demand forms and the large data requirements and slow convergence of flexible nonparametric or machine learning approaches. Instead, we exploit the randomness inherent in modern algorithmic pricing, arising from the need to balance exploration and exploitation, and introduce an estimator that avoids explicit estimation and numerical integration of the demand function. Each observed purchase outcome at a randomized price is an unbiased estimate of demand and by carefully reweighting purchase outcomes using novel cumulative propensity weights (CPW), we are able to reconstruct the integral. Building on this idea, we introduce a doubly robust variant named the augmented cumulative propensity weighting (ACPW) estimator that only requires one of either the demand model or the historical pricing policy distribution to be correctly specified. Furthermore, this approach facilitates the use of flexible machine learning methods for estimating consumer surplus, since it achieves fast convergence rates by incorporating an estimate of demand, even when the machine learning estimate has slower convergence rates. Neither of these estimators is a standard application of off-policy evaluation techniques as the target estimand, consumer surplus, is unobserved. To address fairness, we extend this framework to an inequality-aware surplus measure, allowing regulators and firms to quantify the profit-equity trade-off. Finally, we validate our methods through comprehensive numerical studies.
Authors: Jin Wang, Angelo De Castro, Yuxi Zhang, Lucas Basolli Borsatto, Yuechen Guo, Victoria Bastos Primo, Ana Beatriz Montevecchio Bernardino, Gota Morota, Ricardo C Chebel, Haipeng Yu
Abstract: Computer vision provides automated, non-invasive, and scalable tools for monitoring dairy cattle, thereby supporting management, health assessment, and phenotypic data collection. Although transfer learning is commonly used for predicting body weight from images, its effectiveness and optimal fine-tuning strategies remain poorly understood in livestock applications, particularly beyond the use of pretrained ImageNet or COCO weights. In addition, while both depth images and three-dimensional point-cloud data have been explored for body weight prediction, direct comparisons of these two modalities in dairy cattle are limited. Therefore, the objectives of this study were to 1) evaluate whether transfer learning from a large farm enhances body weight prediction on a small farm with limited data, and 2) compare the predictive performance of depth-image- and point-cloud-based approaches under three experimental designs. Top-view depth images and point-cloud data were collected from 1,201, 215, and 58 cows at large, medium, and small dairy farms, respectively. Four deep learning models were evaluated: ConvNeXt and MobileViT for depth images, and PointNet and DGCNN for point clouds. Transfer learning markedly improved body weight prediction on the small farm across all four models, outperforming single-source learning and achieving gains comparable to or greater than joint learning. These results indicate that pretrained representations generalize well across farms with differing imaging conditions and dairy cattle populations. No consistent performance difference was observed between depth-image- and point-cloud-based models. Overall, these findings suggest that transfer learning is well suited for small farm prediction scenarios where cross-farm data sharing is limited by privacy, logistical, or policy constraints, as it requires access only to pretrained model weights rather than raw data.
Authors: Milad Rahmati, Nima Rahmati
Abstract: The proliferation of Internet of Things devices in critical infrastructure has created unprecedented cybersecurity challenges, necessitating collaborative threat detection mechanisms that preserve data privacy while maintaining robustness against sophisticated attacks. Traditional federated learning approaches for IoT security suffer from two critical vulnerabilities: susceptibility to Byzantine attacks where malicious participants poison model updates, and inadequacy against future quantum computing threats that can compromise cryptographic aggregation protocols. This paper presents a novel Byzantine-robust federated learning framework integrated with post-quantum secure aggregation specifically designed for real-time threat intelligence sharing across critical IoT infrastructure. The proposed framework combines a adaptive weighted aggregation mechanism with lattice-based cryptographic protocols to simultaneously defend against model poisoning attacks and quantum adversaries. We introduce a reputation-based client selection algorithm that dynamically identifies and excludes Byzantine participants while maintaining differential privacy guarantees. The secure aggregation protocol employs CRYSTALS-Kyber for key encapsulation and homomorphic encryption to ensure confidentiality during parameter updates. Experimental evaluation on industrial IoT intrusion detection datasets demonstrates that our framework achieves 96.8% threat detection accuracy while successfully mitigating up to 40% Byzantine attackers, with only 18% computational overhead compared to non-secure federated approaches. The framework maintains sub-second aggregation latency suitable for real-time applications and provides 256-bit post-quantum security level.
Authors: Ernest Fokou\'e
Abstract: This paper develops the algorithmic and dynamical foundations of recursive ensemble learning driven by Fibonacci-type update flows. In contrast with classical boosting Freund and Schapire (1997); Friedman (2001), where the ensemble evolves through first-order additive updates, we study second-order recursive architectures in which each predictor depends on its two immediate predecessors. These Fibonacci flows induce a learning dynamic with memory, allowing ensembles to integrate past structure while adapting to new residual information. We introduce a general family of recursive weight-update algorithms encompassing Fibonacci, tribonacci, and higher-order recursions, together with continuous-time limits that yield systems of differential equations governing ensemble evolution. We establish global convergence conditions, spectral stability criteria, and non-asymptotic generalization bounds under Rademacher Bartlett and Mendelson (2002) and algorithmic stability analyses. The resulting theory unifies recursive ensembles, structured weighting, and dynamical systems viewpoints in statistical learning. Experiments with kernel ridge regression Rasmussen and Williams (2006), spline smoothers Wahba (1990), and random Fourier feature models Rahimi and Recht (2007) demonstrate that recursive flows consistently improve approximation and generalization beyond static weighting. These results complete the trilogy begun in Papers I and II: from Fibonacci weighting, through geometric weighting theory, to fully dynamical recursive ensemble learning systems.
Authors: Devesh Nath, Haoran Yin, Glen Chou
Abstract: We propose a scalable reachability-based framework for probabilistic, data-driven safety verification of unknown nonlinear dynamics. We use Koopman theory with a neural network (NN) lifting function to learn an approximate linear representation of the dynamics and design linear controllers in this space to enable closed-loop tracking of a reference trajectory distribution. Closed-loop reachable sets are efficiently computed in the lifted space and mapped back to the original state space via NN verification tools. To capture model mismatch between the Koopman dynamics and the true system, we apply conformal prediction to produce statistically-valid error bounds that inflate the reachable sets to ensure the true trajectories are contained with a user-specified probability. These bounds generalize across references, enabling reuse without recomputation. Results on high-dimensional MuJoCo tasks (11D Hopper, 28D Swimmer) and 12D quadcopters show improved reachable set coverage rate, computational efficiency, and conservativeness over existing methods.
Authors: Hyeonjeong Ha, Jinjin Ge, Bo Feng, Kaixin Ma, Gargi Chakraborty
Abstract: Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative understanding requires grounding who is doing what, when, and where, maintaining coherent entity representations across dynamic visual and temporal contexts. We introduce NarrativeTrack, the first benchmark to evaluate narrative understanding in MLLMs through fine-grained entity-centric reasoning. Unlike existing benchmarks limited to short clips or coarse scene-level semantics, we decompose videos into constituent entities and examine their continuity via a Compositional Reasoning Progression (CRP), a structured evaluation framework that progressively increases narrative complexity across three dimensions: entity existence, entity changes, and entity ambiguity. CRP challenges models to advance from temporal persistence to contextual evolution and fine-grained perceptual reasoning. A fully automated entity-centric pipeline enables scalable extraction of temporally grounded entity representations, providing the foundation for CRP. Evaluations of state-of-the-art MLLMs reveal that models fail to robustly track entities across visual transitions and temporal dynamics, often hallucinating identity under context shifts. Open-source general-purpose MLLMs exhibit strong perceptual grounding but weak temporal coherence, while video-specific MLLMs capture temporal context yet hallucinate entity's contexts. These findings uncover a fundamental trade-off between perceptual grounding and temporal reasoning, indicating that narrative understanding emerges only from their integration. NarrativeTrack provides the first systematic framework to diagnose and advance temporally grounded narrative comprehension in MLLMs.
Authors: Xuan Son Nguyen, Shuo Yang, Aymeric Histace
Abstract: Recent works have demonstrated promising performances of neural networks on hyperbolic spaces and symmetric positive definite (SPD) manifolds. These spaces belong to a family of Riemannian manifolds referred to as symmetric spaces of noncompact type. In this paper, we propose a novel approach for developing neural networks on such spaces. Our approach relies on a unified formulation of the distance from a point to a hyperplane on the considered spaces. We show that some existing formulations of the point-to-hyperplane distance can be recovered by our approach under specific settings. Furthermore, we derive a closed-form expression for the point-to-hyperplane distance in higher-rank symmetric spaces of noncompact type equipped with G-invariant Riemannian metrics. The derived distance then serves as a tool to design fully-connected (FC) layers and an attention mechanism for neural networks on the considered spaces. Our approach is validated on challenging benchmarks for image classification, electroencephalogram (EEG) signal classification, image generation, and natural language inference.
Authors: Kla Tantithamthavorn, Yaotian Zou, Andy Wong, Michael Gupta, Zhe Wang, Mike Buller, Ryan Jiang, Matthew Watson, Minwoo Jeong, Kun Chen, Ming Wu
Abstract: Large Language Models (LLMs)-powered code review automation has the potential to transform code review workflows. Despite the advances of LLM-powered code review comment generation approaches, several practical challenges remain for designing enterprise-grade code review automation tools. In particular, this paper aims at answering the practical question: how can we design a review-guided, context-aware, quality-checked code review comment generation without fine-tuning? In this paper, we present RovoDev Code Reviewer, an enterprise-grade LLM-based code review automation tool designed and deployed at scale within Atlassian's development ecosystem with seamless integration into Atlassian's Bitbucket. Through the offline, online, user feedback evaluations over a one-year period, we conclude that RovoDev Code Reviewer is (1) effective in generating code review comments that could lead to code resolution for 38.70% (i.e., comments that triggered code changes in the subsequent commits); and (2) offers the promise of accelerating feedback cycles (i.e., decreasing the PR cycle time by 30.8%), alleviating reviewer workload (i.e., reducing the number of human-written comments by 35.6%), and improving overall software quality (i.e., finding errors with actionable suggestions).
Authors: Hao-Hsung Yang, Ssu-Yuan Lo, Kuan-Lun Chen, Ching-Kai Wang
Abstract: We address the Diverse Traveling Salesman Problem (D-TSP), a bi-criteria optimization challenge that seeks a set of $k$ distinct TSP tours. The objective requires every selected tour to have a length at most $c|T^*|$ (where $|T^*|$ is the optimal tour length) while minimizing the average Jaccard similarity across all tour pairs. This formulation is crucial for applications requiring both high solution quality and fault tolerance, such as logistics planning, robotics pathfinding or strategic patrolling. Current methods are limited: traditional heuristics, such as the Niching Memetic Algorithm (NMA) or bi-criteria optimization, incur high computational complexity $O(n^3)$, while modern neural approaches (e.g., RF-MA3S) achieve limited diversity quality and rely on complex, external mechanisms. To overcome these limitations, we propose a novel hybrid framework that decomposes D-TSP into two efficient steps. First, we utilize a simple Graph Pointer Network (GPN), augmented with an approximated sequence entropy loss, to efficiently sample a large, diverse pool of high-quality tours. This simple modification effectively controls the quality-diversity trade-off without complex external mechanisms. Second, we apply a greedy algorithm that yields a 2-approximation for the dispersion problem to select the final $k$ maximally diverse tours from the generated pool. Our results demonstrate state-of-the-art performance. On the Berlin instance, our model achieves an average Jaccard index of $0.015$, significantly outperforming NMA ($0.081$) and RF-MA3S. By leveraging GPU acceleration, our GPN structure achieves a near-linear empirical runtime growth of $O(n)$. While maintaining solution diversity comparable to complex bi-criteria algorithms, our approach is over 360 times faster on large-scale instances (783 cities), delivering high-quality TSP solutions with unprecedented efficiency and simplicity.
Authors: Johan Hallberg Szabadv\'ary
Abstract: Conformal Test Martingales (CTMs) are a standard method within the Conformal Prediction framework for testing the crucial assumption of data exchangeability by monitoring deviations from uniformity in the p-value sequence. Although exchangeability implies uniform p-values, the converse does not hold. This raises the question of whether a significant break in exchangeability can occur, such that the p-values remain uniform, rendering CTMs blind. We answer this affirmatively, demonstrating the phenomenon of \emph{conformal blindness}. Through explicit construction, for the theoretically ideal ``oracle'' conformity measure (given by the true conditional density), we demonstrate the possibility of an \emph{$A$-cryptic change-point} (where $A$ refers to the conformity measure). Using bivariate Gaussian distributions, we identify a line along which a change in the marginal means does not alter the distribution of the conformity scores, thereby producing perfectly uniform p-values. Simulations confirm that even a massive distribution shift can be perfectly cryptic to the CTM, highlighting a fundamental limitation and emphasising the critical role of the alignment of the conformity measure with potential shifts.
Authors: Boris Prokhorov, Semyon Chebykin, Alexander Gasnikov, Aleksandr Beznosikov
Abstract: This paper deals with stochastic optimization problems involving Markovian noise with a zero-order oracle. We present and analyze a novel derivative-free method for solving such problems in strongly convex smooth and non-smooth settings with both one-point and two-point feedback oracles. Using a randomized batching scheme, we show that when mixing time $\tau$ of the underlying noise sequence is less than the dimension of the problem $d$, the convergence estimates of our method do not depend on $\tau$. This observation provides an efficient way to interact with Markovian stochasticity: instead of invoking the expensive first-order oracle, one should use the zero-order oracle. Finally, we complement our upper bounds with the corresponding lower bounds. This confirms the optimality of our results.
Authors: Riccardo Gelato, Carlo Sgaravatti, Jakob Grahn, Giacomo Boracchi, Filippo Maria Bianchi
Abstract: Remote sensing solutions for avalanche segmentation and mapping are key to supporting risk forecasting and mitigation in mountain regions. Synthetic Aperture Radar (SAR) imagery from Sentinel-1 can be effectively used for this task, but training an effective detection model requires gathering a large dataset with high-quality annotations from domain experts, which is prohibitively time-consuming. In this work, we aim to facilitate and accelerate the annotation of SAR images for avalanche mapping. We build on the Segment Anything Model (SAM), a segmentation foundation model trained on natural images, and tailor it to Sentinel-1 SAR data. Adapting SAM to our use-case requires addressing several domain-specific challenges: (i) domain mismatch, since SAM was not trained on satellite/SAR imagery; (ii) input adaptation, because SAR products typically provide more than three channels, while SAM is constrained to RGB images; (iii) robustness to imprecise prompts that can affect target identification and degrade the segmentation quality, an issue exacerbated in small, low-contrast avalanches; and (iv) training efficiency, since standard fine-tuning is computationally demanding for SAM. We tackle these challenges through a combination of adapters to mitigate the domain gap, multiple encoders to handle multi-channel SAR inputs, prompt-engineering strategies to improve avalanche localization accuracy, and a training algorithm that limits the training time of the encoder, which is recognized as the major bottleneck. We integrate the resulting model into an annotation tool and show experimentally that it speeds up the annotation of SAR images.
Authors: Furkan Gen\c{c}, Boran \.Ismet Macun, Sait Sarper \"Ozaslan, Emine U. Saritas, Tolga \c{C}ukur
Abstract: Accurate fMRI analysis requires sensitivity to temporal structure across multiple scales, as BOLD signals encode cognitive processes that emerge from fast transient dynamics to slower, large-scale fluctuations. Existing deep learning (DL) approaches to temporal modeling face challenges in jointly capturing these dynamics over long fMRI time series. Among current DL models, transformers address long-range dependencies by explicitly modeling pairwise interactions through attention, but the associated quadratic computational cost limits effective integration of temporal dependencies across long fMRI sequences. Selective state-space models (SSMs) instead model long-range temporal dependencies implicitly through latent state evolution in a dynamical system, enabling efficient propagation of dependencies over time. However, recent SSM-based approaches for fMRI commonly operate on derived functional connectivity representations and employ single-scale temporal processing. These design choices constrain the ability to jointly represent fast transient dynamics and slower global trends within a single model. We propose NeuroSSM, a selective state-space architecture designed for end-to-end analysis of raw BOLD signals in fMRI time series. NeuroSSM addresses the above limitations through two complementary design components: a multiscale state-space backbone that captures fast and slow dynamics concurrently, and a parallel differencing branch that increases sensitivity to transient state changes. Experiments on clinical and non-clinical datasets demonstrate that NeuroSSM achieves competitive performance and efficiency against state-of-the-art fMRI analysis methods.
Authors: Kalyaan Rao
Abstract: Bayesian model selection commonly relies on Laplace approximation or the Bayesian Information Criterion (BIC), which assume that the effective model dimension equals the number of parameters. Singular learning theory replaces this assumption with the real log canonical threshold (RLCT), an effective dimension that can be strictly smaller in overparameterized or rank-deficient models. We study linear-Gaussian rank models and linear subspace (dictionary) models in which the exact marginal likelihood is available in closed form and the RLCT is analytically tractable. In this setting, we show theoretically and empirically that the error of Laplace/BIC grows linearly with (d/2 minus lambda) times log n, where d is the ambient parameter dimension and lambda is the RLCT. An RLCT-aware correction recovers the correct evidence slope and is invariant to overcomplete reparameterizations that represent the same data subspace. Our results provide a concrete finite-sample characterization of Laplace failure in singular models and demonstrate that evidence slopes can be used as a practical estimator of effective dimension in simple linear settings.
Authors: Jinniao Qiu
Abstract: In this work, we investigate a stochastic control framework for global optimization over both finite-dimensional Euclidean spaces and the Wasserstein space of probability measures. In the Euclidean setting, the original minimization problem is approximated by a family of regularized stochastic control problems; using dynamic programming, we analyze the associated Hamilton--Jacobi--Bellman equations and obtain tractable representations via the Cole--Hopf transform and the Feynman--Kac formula. For optimization over probability measures, we formulate a regularized mean-field control problem characterized by a master equation, and further approximate it by controlled $N$-particle systems. We establish that, as the regularization parameter tends to zero (and as the particle number tends to infinity for the optimization over probability measures), the value of the control problem converges to the global minimum of the original objective. Building on the resulting probabilistic representations, Monte Carlo-based numerical schemes are proposed and numerical experiments are reported to illustrate the practical performance of the methods and to support the theoretical convergence rates.
Authors: Sifatullah Sheikh Urmi, Kirtonia Nuzath Tabassum Arthi, Md Al-Imran
Abstract: The increasing use of artificial intelligence generated deepfakes creates major challenges in maintaining digital authenticity. Four AI-based models, consisting of three CNNs and one Vision Transformer, were evaluated using large face image datasets. Data preprocessing and augmentation techniques improved model performance across different scenarios. VFDNET demonstrated superior accuracy with MobileNetV3, showing efficient performance, thereby demonstrating AI's capabilities for dependable deepfake detection.
Authors: Davis Brown, Juan-Pablo Rivera, Dan Hendrycks, Mantas Mazeika
Abstract: As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration attacks. In this work, we consider exfiltration attacks where an adversary attempts to sneak model weights out of a datacenter over a network. While exfiltration attacks are multi-step cyber attacks, we demonstrate that a single factor, the compressibility of model weights, significantly heightens exfiltration risk for large language models (LLMs). We tailor compression specifically for exfiltration by relaxing decompression constraints and demonstrate that attackers could achieve 16x to 100x compression with minimal trade-offs, reducing the time it would take for an attacker to illicitly transmit model weights from the defender's server from months to days. Finally, we study defenses designed to reduce exfiltration risk in three distinct ways: making models harder to compress, making them harder to 'find,' and tracking provenance for post-attack analysis using forensic watermarks. While all defenses are promising, the forensic watermark defense is both effective and cheap, and therefore is a particularly attractive lever for mitigating weight-exfiltration risk.
Authors: Keith Frankston, Benjamin Howard
Abstract: We introduce a recursive AlphaZero-style Monte--Carlo tree search algorithm, "RMCTS". The advantage of RMCTS over AlphaZero's MCTS-UCB is speed. In RMCTS, the search tree is explored in a breadth-first manner, so that network inferences naturally occur in large batches. This significantly reduces the GPU latency cost. We find that RMCTS is often more than 40 times faster than MCTS-UCB when searching a single root state, and about 3 times faster when searching a large batch of root states. The recursion in RMCTS is based on computing optimized posterior policies at each game state in the search tree, starting from the leaves and working back up to the root. Here we use the posterior policy explored in "Monte--Carlo tree search as regularized policy optimization" (Grill, et al.) Their posterior policy is the unique policy which maximizes the expected reward given estimated action rewards minus a penalty for diverging from the prior policy. The tree explored by RMCTS is not defined in an adaptive manner, as it is in MCTS-UCB. Instead, the RMCTS tree is defined by following prior network policies at each node. This is a disadvantage, but the speedup advantage is more significant, and in practice we find that RMCTS-trained networks match the quality of MCTS-UCB-trained networks in roughly one-third of the training time. We include timing and quality comparisons of RMCTS vs. MCTS-UCB for three games: Connect-4, Dots-and-Boxes, and Othello.
Authors: Songyu Zhang, Aaron Tam, Myungjin Lee, Shixiong Qi, K. K. Ramakrishnan
Abstract: Mixture-of-Experts (MoE) models are increasingly used to serve LLMs at scale, but failures become common as deployment scale grows. Existing systems exhibit poor failure resilience: even a single worker failure triggers a coarse-grained, service-wide restart, discarding accumulated progress and halting the entire inference pipeline during recovery--an approach clearly ill-suited for latency-sensitive, LLM services. We present Tarragon, a resilient MoE inference framework that confines the failures impact to individual workers while allowing the rest of the pipeline to continue making forward progress. Tarragon exploits the natural separation between the attention and expert computation in MoE-based transformers, treating attention workers (AWs) and expert workers (EWs) as distinct failure domains. Tarragon introduces a reconfigurable datapath to mask failures by rerouting requests to healthy workers. On top of this datapath, Tarragon implements a self-healing mechanism that relaxes the tightly synchronized execution of existing MoE frameworks. For stateful AWs, Tarragon performs asynchronous, incremental KV cache checkpointing with per-request restoration, and for stateless EWs, it leverages residual GPU memory to deploy shadow experts. These together keep recovery cost and recomputation overhead extremely low. Our evaluation shows that, compared to state-of-the-art MegaScale-Infer, Tarragon reduces failure-induced stalls by 160-213x (from ~64 s down to 0.3-0.4 s) while preserving performance when no failures occur.
Authors: Hong T. M. Chu
Abstract: Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient information, which provides only a first-order approximation. This paper introduces a novel geometric framework based on the least concave majorants of the growth rate function. Our proposed concave certificate establishes a tight bound of DR risk that remains applicable to non-Lipschitz and non-differentiable losses. We extend this framework to complexity analysis, introducing a deterministic bound that complements standard statistical generalization bound. Furthermore, we utilize this certificate to bound the gap between adversarial and empirical Rademacher complexity, demonstrating that dependencies on input diameter, network width, and depth can be eliminated. For practical application in deep learning, we introduce the adversarial score as a tractable relaxation of the concave certificate that enables efficient and layer-wise analysis of neural networks. We validate our theoretical results in various numerical experiments on classification and regression tasks on real-world data.
Authors: Hongjie Wang, Niraj K. Jha
Abstract: Modern Vision-Language Models (VLMs) achieve impressive performance but are limited by the quadratic complexity of self-attention, which prevents their deployment on edge devices and makes their understanding of high-resolution images and long-context videos prohibitively expensive. To address this challenge, we introduce LinMU (Linear-complexity Multimodal Understanding), a VLM design that achieves linear complexity without using any quadratic-complexity modules while maintaining the performance of global-attention-based VLMs. LinMU replaces every self-attention layer in the VLM with the M-MATE block: a dual-branch module that combines a bidirectional state-space model for global context (Flex-MA branch) with localized Swin-style window attention (Local-Swin branch) for adjacent correlations. To transform a pre-trained VLM into the LinMU architecture, we propose a three-stage distillation framework that (i) initializes both branches with self-attention weights and trains the Flex-MA branch alone, (ii) unfreezes the Local-Swin branch and fine-tunes it jointly with the Flex-MA branch, and (iii) unfreezes the remaining blocks and fine-tunes them using LoRA adapters, while regressing on hidden states and token-level logits of the frozen VLM teacher. On MMMU, TextVQA, LongVideoBench, Video-MME, and other benchmarks, LinMU matches the performance of teacher models, yet reduces Time-To-First-Token (TTFT) by up to 2.7$\times$ and improves token throughput by up to 9.0$\times$ on minute-length videos. Ablations confirm the importance of each distillation stage and the necessity of the two branches of the M-MATE block. The proposed framework demonstrates that state-of-the-art multimodal reasoning can be achieved without quadratic attention, thus opening up avenues for long-context VLMs that can deal with high-resolution images and long videos.
Authors: Hongkun Yang, Lionel Z. Wang, Wei Fan, Yiran Hu, Lixu Wang, Chenyu Liu, Shenghong Fu, Haoyang Li, Xin Xu, Jiexin Zheng, Wei Dong
Abstract: Legal judgment generation is a critical task in legal intelligence. However, existing research in legal judgment generation has predominantly focused on first-instance trials, relying on static fact-to-verdict mappings while neglecting the dialectical nature of appellate (second-instance) review. To address this, we introduce AppellateGen, a benchmark for second-instance legal judgment generation comprising 7,351 case pairs. The task requires models to draft legally binding judgments by reasoning over the initial verdict and evidentiary updates, thereby modeling the causal dependency between trial stages. We further propose a judicial Standard Operating Procedure (SOP)-based Legal Multi-Agent System (SLMAS) to simulate judicial workflows, which decomposes the generation process into discrete stages of issue identification, retrieval, and drafting. Experimental results indicate that while SLMAS improves logical consistency, the complexity of appellate reasoning remains a substantial challenge for current LLMs. The dataset and code are publicly available at: https://anonymous.4open.science/r/AppellateGen-5763.
Authors: Hossam Amer, Maryam Dialameh, Hossein Rajabzadeh, Walid Ahmed, Weiwei Zhang, Yang Liu
Abstract: Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that increasing test-time compute (TTC)-for example through iterative sampling-can allow smaller models to rival or surpass much larger ones at lower overall cost. We introduce TTC-aware training, where an intermediate checkpoint and a corresponding TTC configuration can together match or exceed the accuracy of a fully trained model while requiring substantially fewer training FLOPs. Building on this insight, we propose an early stopping algorithm that jointly selects a checkpoint and TTC configuration to minimize training compute without sacrificing accuracy. To make this practical, we develop an efficient TTC evaluation method that avoids exhaustive search, and we formalize a break-even bound that identifies when increased inference compute compensates for reduced training compute. Experiments demonstrate up to 92\% reductions in training FLOPs while maintaining and sometimes remarkably improving accuracy. These results highlight a new perspective for balancing training and inference compute in model development, enabling faster deployment cycles and more frequent model refreshes. Codes will be publicly released.
Authors: Di Su, Kai Ming Ting, Jie Zhang, Xiaorui Zhang, Xinpeng Li
Abstract: The detection of rare cell types in single-cell transcriptomics data is crucial for elucidating disease pathogenesis and tissue development dynamics. However, a critical gap that persists in current methods is their inability to provide an explanation based on genes for each cell they have detected as rare. We identify three primary sources of this deficiency. First, the anomaly detectors often function as "black boxes", designed to detect anomalies but unable to explain why a cell is anomalous. Second, the standard analytical framework hinders interpretability by relying on dimensionality reduction techniques, such as Principal Component Analysis (PCA), which transform meaningful gene expression data into abstract, uninterpretable features. Finally, existing explanation algorithms cannot be readily applied to this domain, as single-cell data is characterized by high dimensionality, noise, and substantial sparsity. To overcome these limitations, we introduce a framework for explainable anomaly detection in single-cell transcriptomics data which not only identifies individual anomalies, but also provides a visual explanation based on genes that makes an instance anomalous. This framework has two key ingredients that are not existed in current methods applied in this domain. First, it eliminates the PCA step which is deemed to be an essential component in previous studies. Second, it employs the state-of-art anomaly detector and explainer as the efficient and effective means to find each rare cell and the relevant gene subspace in order to provide explanations for each rare cell as well as the typical normal cell associated with the rare cell's closest normal cells.
Authors: Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li
Abstract: Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite increasing advances in foundation model research, the relationship between such large language models (LLMs) and their calibration remains an open area of research. In this work, we look at a critical gap in the calibration of LLMs within multilingual settings, in an attempt to better understand how the data scarcity can potentially lead to different calibration effects and how commonly used techniques can apply in these settings. Our analysis on two multilingual benchmarks, over 29 and 42 languages respectively, reveals that even in low-resource languages, model confidence can increase significantly after instruction-tuning on high-resource language SFT datasets. However, improvements in accuracy are marginal or non-existent, resulting in mis-calibration, highlighting a critical shortcoming of standard SFT for multilingual languages. Furthermore, we observe that the use of label smoothing to be a reasonable method alleviate this concern, again without any need for low-resource SFT data, maintaining better calibration across all languages. Overall, this highlights the importance of multilingual considerations for both training and tuning LLMs in order to improve their reliability and fairness in downstream use.
Authors: Yinan Shen, Yichen Zhang, Wen-Xin Zhou
Abstract: This work investigates the performance of the final iterate produced by stochastic gradient descent (SGD) under temporally dependent data. We consider two complementary sources of dependence: $(i)$ martingale-type dependence in both the covariate and noise processes, which accommodates non-stationary and non-mixing time series data, and $(ii)$ dependence induced by sequential decision making. Our formulation runs in parallel with classical notions of (local) stationarity and strong mixing, while neither framework fully subsumes the other. Remarkably, SGD is shown to automatically accommodate both independent and dependent information under a broad class of stepsize schedules and exploration rate schemes. Non-asymptotically, we show that SGD simultaneously achieves statistically optimal estimation error and regret, extending and improving existing results. In particular, our tail bounds remain sharp even for potentially infinite horizon $T=+\infty$. Asymptotically, the SGD iterates converge to a Gaussian distribution with only an $O_{\PP}(1/\sqrt{t})$ remainder, demonstrating that the supposed estimation-regret trade-off claimed in prior work can in fact be avoided. We further propose a new ``conic'' approximation of the decision region that allows the covariates to have unbounded support. For online sparse regression, we develop a new SGD-based algorithm that uses only $d$ units of storage and requires $O(d)$ flops per iteration, achieving the long term statistical optimality. Intuitively, each incoming observation contributes to estimation accuracy, while aggregated summary statistics guide support recovery.
Authors: Ian Jacob Cabansag, Paul Ntegeka
Abstract: Afrobeats songs compete for attention on streaming platforms, where chart visibility can influence both revenue and cultural impact. This paper examines whether collaborations help songs remain on the charts longer, using daily Nigeria Spotify Top 200 data from 2024. Each track is summarized by the number of days it appears in the Top 200 during the year and its total annual streams in Nigeria. A Bayesian negative binomial regression is applied, with days on chart as the outcome and collaboration status (solo versus multi-artist) and log total streams as predictors. This approach is well suited for overdispersed count data and allows the effect of collaboration to be interpreted while controlling for overall popularity. Posterior inference is conducted using Markov chain Monte Carlo, and results are assessed using rate ratios, posterior probabilities, and predictive checks. The findings indicate that, after accounting for total streams, collaboration tracks tend to spend slightly fewer days on the chart than comparable solo tracks.
Authors: Chenxu Wang, Chaozhuo Li, Pengbo Wang, Litian Zhang, Songyang Liu, Ji Qi, Jiahui Hu, Yushan Cai, Hao Zhao, Rui Pu
Abstract: Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to mitigate this issue through node-level adjustments or coarse suppression, they often overlook the distributed nature of neural information, leading to imprecise interventions. Recognizing that hallucinations propagate through specific forward transmission pathways like an infection, we aim to surgically block this flow using precise structural analysis. To leverage this, we propose Lancet, a novel framework that achieves precise neural intervention by leveraging structural entropy and hallucination difference ratios. Lancet first locates hallucination-prone neurons via gradient-driven contrastive analysis, then maps their propagation pathways by minimizing structural entropy, and finally implements a hierarchical intervention strategy that preserves general model capabilities. Comprehensive evaluations across hallucination benchmark datasets demonstrate that Lancet significantly outperforms state-of-the-art methods, validating the effectiveness of our surgical approach to neural intervention.
Authors: Jay-Anne Bulauan, John Rick Manzanares
Abstract: Ball Mapper is an widely used tool in topological data analysis for summarizing the structure of high-dimensional data through metric-based coverings and graph representations. A central computational bottleneck in Ball Mapper is the construction of the underlying cover, which requires repeated range queries to identify data points within a fixed distance of selected landmarks. As data sets grow in size and dimensionality, naive implementations of this step become increasingly inefficient. In this work, we study practical strategies for accelerating cover construction in Ball Mapper by improving the efficiency of range queries. We integrate two complementary approaches into the Ball Mapper pipeline: hierarchical geometric pruning using ball tree data structures, and hardware-aware distance computation using Facebook AI Similarity Search. We describe the underlying algorithms, discuss their trade-offs with respect to metric flexibility and dimensionality, and provide implementation details relevant to large-scale data analysis. Empirical benchmarks demonstrate that both approaches yield substantial speedups over the baseline implementation, with performance gains depending on data set size, dimensionality, and choice of distance function. These results improve the practical scalability of Ball Mapper without modifying its theoretical formulation and provide guidance for the efficient implementation of metric-based exploratory tools in modern data analysis workflows.
Authors: Jisoo Lee, Sunki Hong
Abstract: Accurate grid load forecasting is safety-critical: under-predictions risk supply shortfalls, while symmetric error metrics mask this operational asymmetry. We introduce a grid-specific evaluation framework--Asymmetric MAPE, Under-Prediction Rate, and Reserve Margin--that directly measures operational risk rather than statistical accuracy alone. Using this framework, we conduct a systematic evaluation of Mamba-based State Space Models for California grid forecasting on a weather-aligned CAISO TAC-area dataset spanning Nov 2023--Nov 2025 (84,498 hourly records across 5 transmission areas). Our analysis reveals that standard accuracy metrics are poor proxies for operational safety: models with identical MAPE can require vastly different reserve margins. We demonstrate that forecast errors are weakly but significantly associated with temperature (r = 0.16, p < 10^{-16}), motivating weather-aware modeling rather than loss function modification alone. The S-Mamba model achieves the lowest Reserve_{99.5}% margin (14.12%) compared to 16.66% for iTransformer, demonstrating superior forecast reliability under a 99.5th-percentile tail-risk reserve proxy.
Authors: Dongrong Li, Tianwei Yu, Xiaodan Fan
Abstract: The Hidden Markov Model (HMM) is a widely-used statistical model for handling sequential data. However, the presence of missing observations in real-world datasets often complicates the application of the model. The EM algorithm and Gibbs samplers can be used to estimate the model, yet suffering from various problems including non-convexity, high computational complexity and slow mixing. In this paper, we propose a collapsed Gibbs sampler that efficiently samples from HMMs' posterior by integrating out both the missing observations and the corresponding latent states. The proposed sampler is fast due to its three advantages. First, it achieves an estimation accuracy that is comparable to existing methods. Second, it can produce a larger Effective Sample Size (ESS) per iteration, which can be justified theoretically and numerically. Third, when the number of missing entries is large, the sampler has a significant smaller computational complexity per iteration compared to other methods, thus is faster computationally. In summary, the proposed sampling algorithm is fast both computationally and theoretically and is particularly advantageous when there are a lot of missing entries. Finally, empirical evaluations based on numerical simulations and real data analysis demonstrate that the proposed algorithm consistently outperforms existing algorithms in terms of time complexity and sampling efficiency (measured in ESS).
Authors: Yilong Wang, Qianli Wang, Nils Feldhus
Abstract: Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating valid counterfactuals with large language models (LLMs) remains challenging, as existing single-pass methods often fail to induce reliable label changes, neglecting LLMs' self-correction capabilities. To explore this untapped potential, we propose iFlip, an iterative refinement approach that leverages three types of feedback, including model confidence, feature attribution, and natural language. Our results show that iFlip achieves an average 57.8% higher validity than the five state-of-the-art baselines, as measured by the label flipping rate. The user study further corroborates that iFlip outperforms baselines in completeness, overall satisfaction, and feasibility. In addition, ablation studies demonstrate that three components are paramount for iFlip to generate valid counterfactuals: leveraging an appropriate number of iterations, pointing to highly attributed words, and early stopping. Finally, counterfactuals generated by iFlip enable effective counterfactual data augmentation, substantially improving model performance and robustness.
Authors: Harshil Darji, Martin Heckelmann, Christina Kratsch, Gerard de Melo
Abstract: The availability of structured legal data is important for advancing Natural Language Processing (NLP) techniques for the German legal system. One of the most widely used datasets, Open Legal Data, provides a large-scale collection of German court decisions. While the metadata in this raw dataset is consistently structured, the decision texts themselves are inconsistently formatted and often lack clearly marked sections. Reliable separation of these sections is important not only for rhetorical role classification but also for downstream tasks such as retrieval and citation analysis. In this work, we introduce a cleaned and sectioned dataset of 251,038 German court decisions derived from the official Open Legal Data dataset. We systematically separated three important sections in German court decisions, namely Tenor (operative part of the decision), Tatbestand (facts of the case), and Entscheidungsgr\"unde (judicial reasoning), which are often inconsistently represented in the original dataset. To ensure the reliability of our extraction process, we used Cochran's formula with a 95% confidence level and a 5% margin of error to draw a statistically representative random sample of 384 cases, and manually verified that all three sections were correctly identified. We also extracted the Rechtsmittelbelehrung (appeal notice) as a separate field, since it is a procedural instruction and not part of the decision itself. The resulting corpus is publicly available in the JSONL format, making it an accessible resource for further research on the German legal system.
Authors: Wentao Bian, Fenglei Xu
Abstract: In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, CLIP's inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their gradients to achieve better generalization. DA-FSS employs the same backbone and pre-trained text encoder as MM-FSS to generate text embeddings, which can increase free modalities' utilization rate and better leverage each modality's information space. To achieve this, we propose a Parallel Expert Refinement module to generate each modal correlation. We also propose a Stacked Arbitration Module (SAM) to perform convolutional fusion and arbitrate correlations for each modality pathway. The Parallel Experts decouple two paths: a Geometric Expert maintains plasticity, and a Semantic Expert ensures stability. They are coordinated via a Decoupled Alignment Module (DAM) that transfers knowledge without propagating confusion. Experiments on popular datasets (S3DIS, ScanNet) demonstrate the superiority of DA-FSS over MM-FSS. Meanwhile, geometric boundaries, completeness, and texture differentiation are all superior to the baseline. The code is available at: https://github.com/MoWenQAQ/DA-FSS.
Authors: Aman Sunesh (New York University), Allan Ma (New York University), Siddarth Nilol (New York University)
Abstract: Large-scale traffic forecasting relies on fixed sensor networks that often exhibit blackouts: contiguous intervals of missing measurements caused by detector or communication failures. These outages are typically handled under a Missing At Random (MAR) assumption, even though blackout events may correlate with unobserved traffic conditions (e.g., congestion or anomalous flow), motivating a Missing Not At Random (MNAR) treatment. We propose a latent state-space framework that jointly models (i) traffic dynamics via a linear dynamical system and (ii) sensor dropout via a Bernoulli observation channel whose probability depends on the latent traffic state. Inference uses an Extended Kalman Filter with Rauch-Tung-Striebel smoothing, and parameters are learned via an approximate EM procedure with a dedicated update for detector-specific missingness parameters. On the Seattle inductive loop detector data, introducing latent dynamics yields large gains over naive baselines, reducing blackout imputation RMSE from 7.02 (LOCF) and 5.02 (linear interpolation + seasonal naive) to 4.23 (MAR LDS), corresponding to about a 64% reduction in MSE relative to LOCF. Explicit MNAR modeling provides a consistent but smaller additional improvement on real data (imputation RMSE 4.20; 0.8% RMSE reduction relative to MAR), with similar modest gains for short-horizon post-blackout forecasts (evaluated at 1, 3, and 6 steps). In controlled synthetic experiments, the MNAR advantage increases as the true missingness dependence on latent state strengthens. Overall, temporal dynamics dominate performance, while MNAR modeling offers a principled refinement that becomes most valuable when missingness is genuinely informative.
Authors: Vanessa Toborek, Sebastian M\"uller, Christian Bauckhage
Abstract: Curriculum Learning (CL) aims to improve the outcome of model training by estimating the difficulty of samples and scheduling them accordingly. In NLP, difficulty is commonly approximated using task-agnostic linguistic heuristics or human intuition, implicitly assuming that these signals correlate with what neural models find difficult to learn. We propose a four-quadrant categorisation of difficulty signals -- human vs. model and task-agnostic vs. task-dependent -- and systematically analyse their interactions on a natural language understanding dataset. We find that task-agnostic features behave largely independently and that only task-dependent features align. These findings challenge common CL intuitions and highlight the need for lightweight, task-dependent difficulty estimators that better reflect model learning behaviour.
Authors: Mikael M{\o}ller H{\o}gsgaard
Abstract: In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from an unknown distribution and the principal's goal is to design a contract that maximizes her expected utility. Specifically, our analysis shows that the simple Empirical Utility Maximization (EUM) algorithm yields an $\varepsilon$-approximation of the optimal linear contract with probability at least $1-\delta$, using just $O(\ln(1/\delta) / \varepsilon^2)$ samples. This result improves upon previously known bounds and matches a lower bound from Duetting et al. [2025] up to constant factors, thereby proving its optimality. Our analysis uses a chaining argument, where the key insight is to leverage a simple structural property of linear contracts: their expected reward is non-decreasing. This property, which holds even though the utility function itself is non-monotone and discontinuous, enables the construction of fine-grained nets required for the chaining argument, which in turn yields the optimal sample complexity. Furthermore, our proof establishes the stronger guarantee of uniform convergence: the empirical utility of every linear contract is a $\varepsilon$-approximation of its true expectation with probability at least $1-\delta$, using the same optimal $O(\ln(1/\delta) / \varepsilon^2)$ sample complexity.
Authors: Wenhui Chu, Aobo Jin, Hardik A. Gohel
Abstract: This research aims to develop a novel deep learning network, GBU-Net, utilizing a group-batch-normalized U-Net framework, specifically designed for the precise semantic segmentation of the left ventricle in short-axis cine MRI scans. The methodology includes a down-sampling pathway for feature extraction and an up-sampling pathway for detail restoration, enhanced for medical imaging. Key modifications include techniques for better contextual understanding crucial in cardiac MRI segmentation. The dataset consists of 805 left ventricular MRI scans from 45 patients, with comparative analysis using established metrics such as the dice coefficient and mean perpendicular distance. GBU-Net significantly improves the accuracy of left ventricle segmentation in cine MRI scans. Its innovative design outperforms existing methods in tests, surpassing standard metrics like the dice coefficient and mean perpendicular distance. The approach is unique in its ability to capture contextual information, often missed in traditional CNN-based segmentation. An ensemble of the GBU-Net attains a 97% dice score on the SunnyBrook testing dataset. GBU-Net offers enhanced precision and contextual understanding in left ventricle segmentation for surgical robotics and medical analysis.
Authors: Fanzhe Fu
Abstract: In the progressive journey toward Artificial General Intelligence (AGI), current evaluation paradigms face an epistemological crisis. Static benchmarks measure knowledge breadth but fail to quantify the depth of belief. While Simhi et al. (2025) defined the CHOKE phenomenon in standard QA, we extend this framework to quantify "Cognitive Conviction" in System 2 reasoning models. We propose Project Aletheia, a cognitive physics framework that employs Tikhonov Regularization to invert the judge's confusion matrix. To validate this methodology without relying on opaque private data, we implement a Synthetic Proxy Protocol. Our preliminary pilot study on 2025 baselines (e.g., DeepSeek-R1, OpenAI o1) suggests that while reasoning models act as a "cognitive buffer," they may exhibit "Defensive OverThinking" under adversarial pressure. Furthermore, we introduce the Aligned Conviction Score (S_aligned) to verify that conviction does not compromise safety. This work serves as a blueprint for measuring AI scientific integrity.
Authors: Tianjun Gu, Chenghua Gong, Jingyu Gong, Zhizhong Zhang, Yuan Xie, Lizhuang Ma, Xin Tan
Abstract: The ability to reason about spatial dynamics is a cornerstone of intelligence, yet current research overlooks the human intent behind spatial changes. To address these limitations, we introduce Teleo-Spatial Intelligence (TSI), a new paradigm that unifies two critical pillars: Physical-Dynamic Reasoning--understanding the physical principles of object interactions--and Intent-Driven Reasoning--inferring the human goals behind these actions. To catalyze research in TSI, we present EscherVerse, consisting of a large-scale, open-world benchmark (Escher-Bench), a dataset (Escher-35k), and models (Escher series). Derived from real-world videos, EscherVerse moves beyond constrained settings to explicitly evaluate an agent's ability to reason about object permanence, state transitions, and trajectory prediction in dynamic, human-centric scenarios. Crucially, it is the first benchmark to systematically assess Intent-Driven Reasoning, challenging models to connect physical events to their underlying human purposes. Our work, including a novel data curation pipeline, provides a foundational resource to advance spatial intelligence from passive scene description toward a holistic, purpose-driven understanding of the world.
Authors: Yazhen Wang
Abstract: Fast computational algorithms are in constant demand, and their development has been driven by advances such as quantum speedup and classical acceleration. This paper intends to study search algorithms based on quantum walks in quantum computation and sampling algorithms based on Langevin dynamics in classical computation. On the quantum side, quantum walk-based search algorithms can achieve quadratic speedups over their classical counterparts. In classical computation, a substantial body of work has focused on gradient acceleration, with gradient-adjusted algorithms derived from underdamped Langevin dynamics providing quadratic acceleration over conventional Langevin algorithms. Since both search and sampling algorithms are designed to address learning tasks, we study learning relationship between coined quantum walks and underdamped Langevin dynamics. Specifically, we show that, in terms of the Le Cam deficiency distance, a quantum walk with randomization is asymptotically equivalent to underdamped Langevin dynamics, whereas the quantum walk without randomization is not asymptotically equivalent due to its high-frequency oscillatory behavior. We further discuss the implications of these equivalence and nonequivalence results for the computational and inferential properties of the associated algorithms in machine learning tasks. Our findings offer new insight into the relationship between quantum walks and underdamped Langevin dynamics, as well as the intrinsic mechanisms underlying quantum speedup and classical gradient acceleration.
Authors: Pierre Beck, Tobias M. Schneider
Abstract: Unstable periodic orbits (UPOs) are the non-chaotic, dynamical building blocks of spatio-temporal chaos, motivating a first-principles based theory for turbulence ever since the discovery of deterministic chaos. Despite their key role in the ergodic theory approach to fluid turbulence, identifying UPOs is challenging for two reasons: chaotic dynamics and the high-dimensionality of the spatial discretization. We address both issues at once by proposing a loop convergence algorithm for UPOs directly within a low-dimensional embedding of the chaotic attractor. The convergence algorithm circumvents time-integration, hence avoiding instabilities from exponential error amplification, and operates on a latent dynamics obtained by pulling back the physical equations using automatic differentiation through the learned embedding function. The interpretable latent dynamics is accurate in a statistical sense, and, crucially, the embedding preserves the internal structure of the attractor, which we demonstrate through an equivalence between the latent and physical UPOs of both a model PDE and the 2D Navier-Stokes equations. This allows us to exploit the collapse of high-dimensional dissipative systems onto a lower dimensional manifold, and identify UPOs in the low-dimensional embedding.
Authors: Alois Duston, Tan Bui-Thanh
Abstract: We introduce and prove a \textbf{Conditional Score Expectation (CSE)} identity: an exact relation for the marginal score of affine diffusion processes that links scores across time via a conditional expectation under the forward dynamics. Motivated by this identity, we propose a CSE-based statistical estimator for the score using a Self-Normalized Importance Sampling (SNIS) procedure with prior samples and forward noise. We analyze its relationship to the standard Tweedie estimator, proving anti-correlation for Gaussian targets and establishing the same behavior for general targets in the small time-step regime. Exploiting this structure, we derive a variance-minimizing blended score estimator given by a state--time dependent convex combination of the CSE and Tweedie estimators. Numerical experiments show that this optimal-blending estimator reduces variance and improves sample quality for a fixed computational budget compared to either baseline. We further extend the framework to Bayesian inverse problems via likelihood-informed SNIS weights, and demonstrate improved reconstruction quality and sample diversity on high-dimensional image reconstruction tasks and PDE-governed inverse problems.
Authors: Maxat Tezekbayev, Rustem Takhanov, Arman Bolatov, Zhenisbek Assylbekov
Abstract: We show that for unconstrained Deep Linear Discriminant Analysis (LDA) classifiers, maximum-likelihood training admits pathological solutions in which class means drift together, covariances collapse, and the learned representation becomes almost non-discriminative. Conversely, cross-entropy training yields excellent accuracy but decouples the head from the underlying generative model, leading to highly inconsistent parameter estimates. To reconcile generative structure with discriminative performance, we introduce the \emph{Discriminative Negative Log-Likelihood} (DNLL) loss, which augments the LDA log-likelihood with a simple penalty on the mixture density. DNLL can be interpreted as standard LDA NLL plus a term that explicitly discourages regions where several classes are simultaneously likely. Deep LDA trained with DNLL produces clean, well-separated latent spaces, matches the test accuracy of softmax classifiers on synthetic data and standard image benchmarks, and yields substantially better calibrated predictive probabilities, restoring a coherent probabilistic interpretation to deep discriminant models.
Authors: Emiliya Khidirova, Oktay Karaku\c{s}
Abstract: Accurate crop yield prediction relies on diverse data streams, including satellite, meteorological, soil, and topographic information. However, despite rapid advances in machine learning, existing approaches remain crop- or region-specific and require data engineering efforts. This limits scalability, reproducibility, and operational deployment. This study introduces UniCrop, a universal and reusable data pipeline designed to automate the acquisition, cleaning, harmonisation, and engineering of multi-source environmental data for crop yield prediction. For any given location, crop type, and temporal window, UniCrop automatically retrieves, harmonises, and engineers over 200 environmental variables (Sentinel-1/2, MODIS, ERA5-Land, NASA POWER, SoilGrids, and SRTM), reducing them to a compact, analysis-ready feature set utilising a structured feature reduction workflow with minimum redundancy maximum relevance (mRMR). To validate, UniCrop was applied to a rice yield dataset comprising 557 field observations. Using only the selected 15 features, four baseline machine learning models (LightGBM, Random Forest, Support Vector Regression, and Elastic Net) were trained. LightGBM achieved the best single-model performance (RMSE = 465.1 kg/ha, $R^2 = 0.6576$), while a constrained ensemble of all baselines further improved accuracy (RMSE = 463.2 kg/ha, $R^2 = 0.6604$). UniCrop contributes a scalable and transparent data-engineering framework that addresses the primary bottleneck in operational crop yield modelling: the preparation of consistent and harmonised multi-source data. By decoupling data specification from implementation and supporting any crop, region, and time frame through simple configuration updates, UniCrop provides a practical foundation for scalable agricultural analytics. The code and implementation documentation are shared in https://github.com/CoDIS-Lab/UniCrop.
Authors: Maxat Tezekbayev, Arman Bolatov, Zhenisbek Assylbekov
Abstract: We revisit Deep Linear Discriminant Analysis (Deep LDA) from a likelihood-based perspective. While classical LDA is a simple Gaussian model with linear decision boundaries, attaching an LDA head to a neural encoder raises the question of how to train the resulting deep classifier by maximum likelihood estimation (MLE). We first show that end-to-end MLE training of an unconstrained Deep LDA model ignores discrimination: when both the LDA parameters and the encoder parameters are learned jointly, the likelihood admits a degenerate solution in which some of the class clusters may heavily overlap or even collapse, and classification performance deteriorates. Batchwise moment re-estimation of the LDA parameters does not remove this failure mode. We then propose a constrained Deep LDA formulation that fixes the class means to the vertices of a regular simplex in the latent space and restricts the shared covariance to be spherical, leaving only the priors and a single variance parameter to be learned along with the encoder. Under these geometric constraints, MLE becomes stable and yields well-separated class clusters in the latent space. On images (Fashion-MNIST, CIFAR-10, CIFAR-100), the resulting Deep LDA models achieve accuracy competitive with softmax baselines while offering a simple, interpretable latent geometry that is clearly visible in two-dimensional projections.
Authors: Chankyu Lee, Woohyun Choi, Sangwook Park
Abstract: This study evaluates the inference performance of various deep learning models under an embedded system environment. In previous works, Multiply-Accumulate operation is typically used to measure computational load of a deep model. According to this study, however, this metric has a limitation to estimate inference time on embedded devices. This paper poses the question of what aspects are overlooked when expressed in terms of Multiply-Accumulate operations. In experiments, an image classification task is performed on an embedded system device using the CIFAR-100 dataset to compare and analyze the inference times of ten deep models with the theoretically calculated Multiply-Accumulate operations for each model. The results highlight the importance of considering additional computations between tensors when optimizing deep learning models for real-time performing in embedded systems.
Authors: Ziheng Chen, Minxuan Hu, Jiayu Yi, Wenxi Sun
Abstract: We extend the Q-learner in Black-Scholes (QLBS) framework by incorporating risk aversion and trading costs, and propose a novel Replication Learning of Option Pricing (RLOP) approach. Both methods are fully compatible with standard reinforcement learning algorithms and operate under market frictions. Using SPY and XOP option data, we evaluate performance along static and dynamic dimensions. Adaptive-QLBS achieves higher static pricing accuracy in implied volatility space, while RLOP delivers superior dynamic hedging performance by reducing shortfall probability. These results highlight the importance of evaluating option pricing models beyond static fit, emphasizing realized hedging outcomes.
Authors: Jiarui Wang, Huichao Chai, Yuanhang Zhang, Zongjin Zhou, Wei Guo, Xingkun Yang, Qiang Tang, Bo Pan, Jiawei Zhu, Ke Cheng, Yuting Yan, Shulan Wang, Yingjie Zhu, Zhengfan Yuan, Jiaqi Huang, Yuhan Zhang, Xiaosong Sun, Zhinan Zhang, Hong Zhu, Yongsheng Zhang, Tiantian Dong, Zhong Xiao, Deliang Liu, Chengzhou Lu, Yuan Sun, Zhiyuan Chen, Xinming Han, Zaizhu Liu, Yaoyuan Wang, Ziyang Zhang, Yong Liu, Jinxin Xu, Yajing Sun, Zhoujun Yu, Wenting Zhou, Qidong Zhang, Zhengyong Zhang, Zhonghai Gu, Yibo Jin, Yongxiang Feng, Pengfei Zuo
Abstract: Real-time recommender systems execute multi-stage cascades (retrieval, pre-processing, fine-grained ranking) under strict tail-latency SLOs, leaving only tens of milliseconds for ranking. Generative recommendation (GR) models can improve quality by consuming long user-behavior sequences, but in production their online sequence length is tightly capped by the ranking-stage P99 budget. We observe that the majority of GR tokens encode user behaviors that are independent of the item candidates, suggesting an opportunity to pre-infer a user-behavior prefix once and reuse it during ranking rather than recomputing it on the critical path. Realizing this idea at industrial scale is non-trivial: the prefix cache must survive across multiple pipeline stages before the final ranking instance is determined, the user population implies cache footprints far beyond a single device, and indiscriminate pre-inference would overload shared resources under high QPS. We present RelayGR, a production system that enables in-HBM relay-race inference for GR. RelayGR selectively pre-infers long-term user prefixes, keeps their KV caches resident in HBM over the request lifecycle, and ensures the subsequent ranking can consume them without remote fetches. RelayGR combines three techniques: 1) a sequence-aware trigger that admits only at-risk requests under a bounded cache footprint and pre-inference load, 2) an affinity-aware router that co-locates cache production and consumption by routing both the auxiliary pre-infer signal and the ranking request to the same instance, and 3) a memory-aware expander that uses server-local DRAM to capture short-term cross-request reuse while avoiding redundant reloads. We implement RelayGR on Huawei Ascend NPUs and evaluate it with real queries. Under a fixed P99 SLO, RelayGR supports up to 1.5$\times$ longer sequences and improves SLO-compliant throughput by up to 3.6$\times$.
Authors: Seung Whan Chung, Youngsoo Choi, Christopher Miller, H. Keo Springer, Kyle T. Sullivan
Abstract: How can we build surrogate solvers that train on small domains but scale to larger ones without intrusive access to PDE operators? Inspired by the Data-Driven Finite Element Method (DD-FEM) framework for modular data-driven solvers, we propose the Latent Space Element Method (LSEM), an element-based latent surrogate assembly approach in which a learned subdomain ("element") model can be tiled and coupled to form a larger computational domain. Each element is a LaSDI latent ODE surrogate trained from snapshots on a local patch, and neighboring elements are coupled through learned directional interaction terms in latent space, avoiding Schwarz iterations and interface residual evaluations. A smooth window-based blending reconstructs a global field from overlapping element predictions, yielding a scalable assembled latent dynamical system. Experiments on the 1D Burgers and Korteweg-de Vries equations show that LSEM maintains predictive accuracy while scaling to spatial domains larger than those seen in training. LSEM offers an interpretable and extensible route toward foundation-model surrogate solvers built from reusable local models.
Authors: Jiwei Guan, Haibo Jin, Haohan Wang
Abstract: Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle perturbations to bypass safety mechanisms and trigger harmful outputs. Existing white-box attacks methods require full model accessibility, suffer from computing costs and exhibit insufficient adversarial transferability, making them impractical for real-world, black-box settings. To address these limitations, we propose a black-box jailbreak attack on LVLMs via Zeroth-Order optimization using Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). ZO-SPSA provides three key advantages: (i) gradient-free approximation by input-output interactions without requiring model knowledge, (ii) model-agnostic optimization without the surrogate model and (iii) lower resource requirements with reduced GPU memory consumption. We evaluate ZO-SPSA on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4, achieving the highest jailbreak success rate of 83.0% on InstructBLIP, while maintaining imperceptible perturbations comparable to white-box methods. Moreover, adversarial examples generated from MiniGPT-4 exhibit strong transferability to other LVLMs, with ASR reaching 64.18%. These findings underscore the real-world feasibility of black-box jailbreaks and expose critical weaknesses in the safety mechanisms of current LVLMs
Authors: Jiakun Jiang, Dewei Xiang, Chenliang Gu, Wei Liu, Binhuan Wang
Abstract: Biclustering is an essential unsupervised machine learning technique for simultaneously clustering rows and columns of a data matrix, with widespread applications in genomics, transcriptomics, and other high-dimensional omics data. Despite its importance, existing biclustering methods struggle to meet the demands of modern large-scale datasets. The challenges stem from the accumulation of noise in high-dimensional features, the limitations of non-convex optimization formulations, and the computational complexity of identifying meaningful biclusters. These issues often result in reduced accuracy and stability as the size of the dataset increases. To overcome these challenges, we propose Sparse Convex Biclustering (SpaCoBi), a novel method that penalizes noise during the biclustering process to improve both accuracy and robustness. By adopting a convex optimization framework and introducing a stability-based tuning criterion, SpaCoBi achieves an optimal balance between cluster fidelity and sparsity. Comprehensive numerical studies, including simulations and an application to mouse olfactory bulb data, demonstrate that SpaCoBi significantly outperforms state-of-the-art methods in accuracy. These results highlight SpaCoBi as a robust and efficient solution for biclustering in high-dimensional and large-scale datasets.
Authors: Yi Fan, Vishnu Jejjala, Yang Lei
Abstract: Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine learning framework for automatically simplifying complex expressions involving multiple elliptic Gamma functions, including the $q$-$\theta$ function and the elliptic Gamma function. The model learns to apply algebraic identities, particularly the SL$(2,\mathbb{Z})$ and SL$(3,\mathbb{Z})$ modular transformations, to reduce heavily scrambled expressions to their canonical forms. Experimental results show that the model achieves over 99\% accuracy on in-distribution tests and maintains robust performance (exceeding 90\% accuracy) under significant extrapolation, such as with deeper scrambling depths. This demonstrates that the model has internalized the underlying algebraic rules of modular transformations rather than merely memorizing training patterns. Our work presents the first successful application of machine learning to perform symbolic simplification using modular identities, offering a new automated tool for computations with special functions in quantum field theory and the string theory.
Authors: Lakshay Sharma, Alex Marin
Abstract: Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of pretraining data. This work introduces Subimage Overlap Prediction, a novel self-supervised pretraining task to aid semantic segmentation in remote sensing imagery that uses significantly lesser pretraining imagery. Given an image, a sub-image is extracted and the model is trained to produce a semantic mask of the location of the extracted sub-image within the original image. We demonstrate that pretraining with this task results in significantly faster convergence, and equal or better performance (measured via mIoU) on downstream segmentation. This gap in convergence and performance widens when labeled training data is reduced. We show this across multiple architecture types, and with multiple downstream datasets. We also show that our method matches or exceeds performance while requiring significantly lesser pretraining data relative to other SSL methods. Code and model weights are provided at \href{https://github.com/sharmalakshay93/subimage-overlap-prediction}{github.com/sharmalakshay93/subimage-overlap-prediction}.
URLs: https://github.com/sharmalakshay93/subimage-overlap-prediction
Authors: Rajiv Chaitanya Muttur
Abstract: Retrieval-Augmented Generation (RAG) systems often rely on fixed top-k document selection mechanisms that ignore downstream generation quality and impose computational overheads. We propose SRAS (Sparse Reward-Aware Selector), a lightweight document selector trained via reinforcement learning (RL) for edge-native RAG deployment. Unlike prior RL-based retrievers that assume large memory and latency budgets, SRAS learns a compact (~0.76MB) policy using Proximal Policy Optimization (PPO), guided by a hybrid reward signal combining Relaxed F1 and BERTScore. Our method operates under tight token and compute constraints, maintaining <1s latency on CPU. SRAS outperforms supervised and random selectors on a synthetic QA benchmark, and generalizes to real-world data, achieving BERTScore F1 of 0.8546 on SQuAD v2 without domain-specific tuning. This work is the first to demonstrate that RL-based document selection can be made ultra-lightweight, latency-aware, and effective for on-device RAG pipelines.
Authors: Valiant Lance D. Dionela, Fatima Kriselle S. Dy, Robin James M. Hombrebueno, Aaron Rae M. Nicolas, Charibeth K. Cheng, Raphael W. Gonda
Abstract: Aspect Extraction (AE) is a key task in Aspect-Based Sentiment Analysis (ABSA), yet it remains difficult to apply in low-resource and code-switched contexts like Taglish, a mix of Tagalog and English commonly used in Filipino e-commerce reviews. This paper introduces a comprehensive AE pipeline designed for Taglish, combining rule-based, large language model (LLM)-based, and fine-tuning techniques to address both aspect identification and extraction. A Hierarchical Aspect Framework (HAF) is developed through multi-method topic modeling, along with a dual-mode tagging scheme for explicit and implicit aspects. For aspect identification, four distinct models are evaluated: a Rule-Based system, a Generative LLM (Gemini 2.0 Flash), and two Fine-Tuned Gemma-3 1B models trained on different datasets (Rule-Based vs. LLM-Annotated). Results indicate that the Generative LLM achieved the highest performance across all tasks (Macro F1 0.91), demonstrating superior capability in handling implicit aspects. In contrast, the fine-tuned models exhibited limited performance due to dataset imbalance and architectural capacity constraints. This work contributes a scalable and linguistically adaptive framework for enhancing ABSA in diverse, code-switched environments.
Authors: Xiaoxue Gao, Zexin Li, Yiming Chen, Nancy F. Chen
Abstract: The emergence of large-scale automatic speech recognition (ASR) models such as Whisper has greatly expanded their adoption across diverse real-world applications. Ensuring robustness against even minor input perturbations is therefore critical for maintaining reliable performance in real-time environments. While prior work has mainly examined accuracy degradation under adversarial attacks, robustness with respect to efficiency remains largely unexplored. This narrow focus provides only a partial understanding of ASR model vulnerabilities. To address this gap, we conduct a comprehensive study of ASR robustness under multiple attack scenarios. We introduce MORE, a multi-objective repetitive doubling encouragement attack, which jointly degrades recognition accuracy and inference efficiency through a hierarchical staged repulsion-anchoring mechanism. Specifically, we reformulate multi-objective adversarial optimization into a hierarchical framework that sequentially achieves the dual objectives. To further amplify effectiveness, we propose a novel repetitive encouragement doubling objective (REDO) that induces duplicative text generation by maintaining accuracy degradation and periodically doubling the predicted sequence length. Overall, MORE compels ASR models to produce incorrect transcriptions at a substantially higher computational cost, triggered by a single adversarial input. Experiments show that MORE consistently yields significantly longer transcriptions while maintaining high word error rates compared to existing baselines, underscoring its effectiveness in multi-objective adversarial attack.
Authors: Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hsiu Hsieh
Abstract: Over-parameterization is commonly used to increase the expressivity of variational quantum circuits (VQCs), yet deeper and more highly parameterized circuits often exhibit poor trainability and limited generalization. In this work, we provide a theoretical explanation for this phenomenon from a function-class perspective. We show that sufficiently expressive, unstructured variational ansatze enter a Haar-like universality class in which both observable expectation values and parameter gradients concentrate exponentially with system size. As a consequence, the hypothesis class induced by such circuits collapses with high probability to a narrow family of near-constant functions, a phenomenon we term simplicity bias, with barren plateaus arising as a consequence rather than the root cause. Using tools from random matrix theory and concentration of measure, we rigorously characterize this universality class and establish uniform hypothesis-class collapse over finite datasets. We further show that this collapse is not unavoidable: tensor-structured VQCs, including tensor-network-based and tensor-hypernetwork parameterizations, lie outside the Haar-like universality class. By restricting the accessible unitary ensemble through bounded tensor rank or bond dimension, these architectures prevent concentration of measure, preserve output variability for local observables, and retain non-degenerate gradient signals even in over-parameterized regimes. Together, our results unify barren plateaus, expressivity limits, and generalization collapse under a single structural mechanism rooted in random-matrix universality, highlighting the central role of architectural inductive bias in variational quantum algorithms.
Authors: Yifan Wu, Yuhan Li, Zhenhua Wang, Zhongle Xie, Dingyu Yang, Ke Chen, Lidan Shou, Bo Tang, Liang Lin, Huan Li, Gang Chen
Abstract: Memory overload is a common form of resource exhaustion in cloud data warehouses. When database queries fail due to memory overload, it not only wastes critical resources such as CPU time but also disrupts the execution of core business processes, as memory-overloading (MO) queries are typically part of complex workflows. If such queries are identified in advance and scheduled to memory-rich serverless clusters, it can prevent resource wastage and query execution failure. Therefore, cloud data warehouses desire an admission control framework with high prediction precision, interpretability, efficiency, and adaptability to effectively identify MO queries. However, existing admission control frameworks primarily focus on scenarios like SLA satisfaction and resource isolation, with limited precision in identifying MO queries. Moreover, there is a lack of publicly available MO-labeled datasets with workloads for training and benchmarking. To tackle these challenges, we propose SafeLoad, the first query admission control framework specifically designed to identify MO queries. Alongside, we release SafeBench, an open-source, industrial-scale benchmark for this task, which includes 150 million real queries. SafeLoad first filters out memory-safe queries using the interpretable discriminative rule. It then applies a hybrid architecture that integrates both a global model and cluster-level models, supplemented by a misprediction correction module to identify MO queries. Additionally, a self-tuning quota management mechanism dynamically adjusts prediction quotas per cluster to improve precision. Experimental results show that SafeLoad achieves state-of-the-art prediction performance with low online and offline time overhead. Specifically, SafeLoad improves precision by up to 66% over the best baseline and reduces wasted CPU time by up to 8.09x compared to scenarios without SafeLoad.
Authors: Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini K. Ratha, Venu Govindaraju
Abstract: Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new concepts sequentially. Existing approaches primarily focus on minimizing interference between concepts, often neglecting the potential for positive inter-concept interactions. In this work, we present Forget Less by Learning from Parents (FLLP), a novel framework that introduces a parent-child inter-concept learning mechanism in hyperbolic space to mitigate forgetting. By embedding concept representations within a Lorentzian manifold, naturally suited to modeling tree-like hierarchies, we define parent-child relationships in which previously learned concepts serve as guidance for adapting to new ones. Our method not only preserves prior knowledge but also supports continual integration of new concepts. We validate FLLP on three public datasets and one synthetic benchmark, showing consistent improvements in both robustness and generalization.
Authors: Mikel Robredo, Matteo Esposito, Fabio Palomba, Rafael Pe\~naloza, Valentina Lenarduzzi
Abstract: Background. Defect prediction has been a highly active topic among researchers in the Empirical Software Engineering field. Previous literature has successfully achieved the most accurate prediction of an incoming fault and identified the features and anomalies that precede it through just-in-time prediction. As software systems evolve continuously, there is a growing need for time-sensitive methods capable of forecasting defects before they manifest. Aim. Our study seeks to explore the effectiveness of time-sensitive techniques for defect forecasting. Moreover, we aim to investigate the early indicators that precede the occurrence of a defect. Method. We will train multiple time-sensitive forecasting techniques to forecast the future bug density of a software project, as well as identify the early symptoms preceding the occurrence of a defect. Expected results. Our expected results are translated into empirical evidence on the effectiveness of our approach for early estimation of bug proneness.
Authors: Yifan Nie, Qiaoxin Li
Abstract: This paper investigates the temporal evolution of high-speed compressible fluids in irregular flow fields using the Fourier Neural Operator (FNO). We reconstruct the irregular flow field point set into sequential format compatible with FNO input requirements, and then embed temporal bundling technique within a recurrent neural network (RNN) for multi-step prediction. We further employ a composite loss function to balance errors across different physical quantities. Experiments are conducted on three different types of irregular flow fields, including orthogonal and non-orthogonal grid configurations. Then we comprehensively analyze the physical component loss curves, flow field visualizations, and physical profiles. Results demonstrate that our approach significantly surpasses traditional numerical methods in computational efficiency while achieving high accuracy, with maximum relative $L_2$ errors of (0.78, 0.57, 0.35)% for ($p$, $T$, $\mathbf{u}$) respectively. This verifies that the method can efficiently and accurately simulate the temporal evolution of high-speed compressible flows in irregular domains.
Authors: Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini Ratha, Venu Govindaraju
Abstract: Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most prior works attempt to mitigate this issue under the sequential learning setting with a fixed order of concept inflow and neglect inter-concept interactions. In this paper, we propose a novel framework - Forget Less by Learning Together (FL2T) - that enables concurrent and order-agnostic concept learning while addressing catastrophic forgetting. Specifically, we introduce a set-invariant inter-concept learning module where proxies guide feature selection across concepts, facilitating improved knowledge retention and transfer. By leveraging inter-concept guidance, our approach preserves old concepts while efficiently incorporating new ones. Extensive experiments, across three datasets, demonstrates that our method significantly improves concept retention and mitigates catastrophic forgetting, highlighting the effectiveness of inter-concept catalytic behavior in incremental concept learning of ten tasks with at least 2% gain on average CLIP Image Alignment scores.
Authors: Ayomide Afolabi, Ebere Ogburu, Symon Kimitei
Abstract: This study evaluates the performance of various classifiers in three distinct models: response, risk, and response-risk, concerning credit card mail campaigns and default prediction. In the response model, the Extra Trees classifier demonstrates the highest recall level (79.1%), emphasizing its effectiveness in identifying potential responders to targeted credit card offers. Conversely, in the risk model, the Random Forest classifier exhibits remarkable specificity of 84.1%, crucial for identifying customers least likely to default. Furthermore, in the multi-class response-risk model, the Random Forest classifier achieves the highest accuracy (83.2%), indicating its efficacy in discerning both potential responders to credit card mail campaign and low-risk credit card users. In this study, we optimized various performance metrics to solve a specific credit risk and mail responsiveness business problem.
Authors: Matthias Bartolo, Dylan Seychell, Gabriel Hili, Matthew Montebello, Carl James Debono, Saviour Formosa, Konstantinos Makantasis
Abstract: This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings.
Authors: Faizan Ahmed, Aniket Dixit, James Brusey
Abstract: Deep reinforcement learning agents often exhibit erratic, high-frequency control behaviors that hinder real-world deployment due to excessive energy consumption and mechanical wear. We systematically investigate action smoothness regularization through higher-order derivative penalties, progressing from theoretical understanding in continuous control benchmarks to practical validation in building energy management. Our comprehensive evaluation across four continuous control environments demonstrates that third-order derivative penalties (jerk minimization) consistently achieve superior smoothness while maintaining competitive performance. We extend these findings to HVAC control systems where smooth policies reduce equipment switching by 60%, translating to significant operational benefits. Our work establishes higher-order action regularization as an effective bridge between RL optimization and operational constraints in energy-critical applications.
Authors: Zhuofan Shi, Hubao A, Yufei Shao, Mengyan Dai, Yadong Yu, Pan Xiang, Dongliang Huang, Hongxu An, Chunxiao Xin, Haiyang Shen, Zhenyu Wang, Yunshan Na, Gang Huang, Xiang Jing
Abstract: Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized and time-consuming tasks. Although LLMs show promise in code generation and domain-specific question answering, their performance in MD scenarios is limited by scarce domain data, the high deployment cost of state-of-the-art LLMs, and low code executability. Building upon our prior MDAgent, we present MDAgent2, the first end-to-end framework capable of performing both knowledge Q&A and code generation within the MD domain. We construct a domain-specific data-construction pipeline that yields three high-quality datasets spanning MD knowledge, question answering, and code generation. Based on these datasets, we adopt a three stage post-training strategy--continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL)--to train two domain-adapted models, MD-Instruct and MD-Code. Furthermore, we introduce MD-GRPO, a closed-loop RL method that leverages simulation outcomes as reward signals and recycles low-reward trajectories for continual refinement. We further build MDAgent2-RUNTIME, a deployable multi-agent system that integrates code generation, execution, evaluation, and self-correction. Together with MD-EvalBench proposed in this work, the first benchmark for LAMMPS code generation and question answering, our models and system achieve performance surpassing several strong baselines.This work systematically demonstrates the adaptability and generalization capability of large language models in industrial simulation tasks, laying a methodological foundation for automatic code generation in AI for Science and industrial-scale simulations. URL: https://github.com/FredericVAN/PKU_MDAgent2
Authors: Utkarsh Singh, Absaar Ali, Adarsh Roy
Abstract: The automotive industry's pursuit of enhanced fuel economy and performance necessitates efficient aerodynamic design. However, traditional evaluation methods such as computational fluid dynamics (CFD) and wind tunnel testing are resource intensive, hindering rapid iteration in the early design stages. Machine learning-based surrogate models offer a promising alternative, yet many existing approaches suffer from high computational complexity, limited interpretability, or insufficient accuracy for detailed geometric inputs. This paper introduces a novel lightweight surrogate model for the prediction of the aerodynamic drag coefficient (Cd) based on a sequential slice-wise processing of the geometry of the 3D vehicle. Inspired by medical imaging, 3D point clouds of vehicles are decomposed into an ordered sequence of 2D cross-sectional slices along the stream-wise axis. Each slice is encoded by a lightweight PointNet2D module, and the sequence of slice embeddings is processed by a bidirectional LSTM to capture longitudinal geometric evolution. The model, trained and evaluated on the DrivAerNet++ dataset, achieves a high coefficient of determination (R^2 > 0.9528) and a low mean absolute error (MAE approx 6.046 x 10^{-3}) in Cd prediction. With an inference time of approximately 0.025 seconds per sample on a consumer-grade GPU, our approach provides fast, accurate, and interpretable aerodynamic feedback, facilitating more agile and informed automotive design exploration.
Authors: Hongyu Zhou, Haoran Sun, Rui Guo, Maokun Li, Fan Yang, Shenheng Xu
Abstract: In this study, we investigate feature-based 2.5D controlled source marine electromagnetic (mCSEM) data inversion using generative priors. Two-and-half dimensional modeling using finite difference method (FDM) is adopted to compute the response of horizontal electric dipole (HED) excitation. Rather than using a neural network to approximate the entire inverse mapping in a black-box manner, we adopt a plug-andplay strategy in which a variational autoencoder (VAE) is used solely to learn prior information on conductivity distributions. During the inversion process, the conductivity model is iteratively updated using the Gauss Newton method, while the model space is constrained by projections onto the learned VAE decoder. This framework preserves explicit control over data misfit and enables flexible adaptation to different survey configurations. Numerical and field experiments demonstrate that the proposed approach effectively incorporates prior information, improves reconstruction accuracy, and exhibits good generalization performance.
Authors: Sunny Gupta, Shounak Das, Amit Sethi
Abstract: Vision language foundation models such as CLIP exhibit impressive zero-shot generalization yet remain vulnerable to spurious correlations across visual and textual modalities. Existing debiasing approaches often address a single modality either visual or textual leading to partial robustness and unstable adaptation under distribution shifts. We propose a bilateral prompt optimization framework (BiPrompt) that simultaneously mitigates non-causal feature reliance in both modalities during test-time adaptation. On the visual side, it employs structured attention-guided erasure to suppress background activations and enforce orthogonal prediction consistency between causal and spurious regions. On the textual side, it introduces balanced prompt normalization, a learnable re-centering mechanism that aligns class embeddings toward an isotropic semantic space. Together, these modules jointly minimize conditional mutual information between spurious cues and predictions, steering the model toward causal, domain invariant reasoning without retraining or domain supervision. Extensive evaluations on real-world and synthetic bias benchmarks demonstrate consistent improvements in both average and worst-group accuracies over prior test-time debiasing methods, establishing a lightweight yet effective path toward trustworthy and causally grounded vision-language adaptation.
Authors: Almaz Ermilov
Abstract: This paper presents FormationEval, an open multiple-choice question benchmark for evaluating language models on petroleum geoscience and subsurface disciplines. The dataset contains 505 questions across seven domains including petrophysics, petroleum geology and reservoir engineering, derived from three authoritative sources using a reasoning model with detailed instructions and a concept-based approach that avoids verbatim copying of copyrighted text. Each question includes source metadata to support traceability and audit. The evaluation covers 72 models from major providers including OpenAI, Anthropic, Google, Meta and open-weight alternatives. The top performers achieve over 97\% accuracy, with Gemini 3 Pro Preview reaching 99.8\%, while tier and domain gaps persist. Among open-weight models, GLM-4.7 leads at 98.6\%, with several DeepSeek, Llama, Qwen and Mistral models also exceeding 93\%. The performance gap between open-weight and closed models is narrower than expected, with several lower-cost open-weight models exceeding 90\% accuracy. Petrophysics emerges as the most challenging domain across all models, while smaller models show wider performance variance. Residual length bias in the dataset (correct answers tend to be longer) is documented along with bias mitigation strategies applied during construction. The benchmark, evaluation code and results are publicly available.
Authors: Cheng Ying Wu, Yen Jui Chang
Abstract: Deploying deep learning models for Fine-Grained Visual Classification (FGVC) on resource-constrained edge devices remains a significant challenge. While deep architectures achieve high accuracy on benchmarks like CUB-200-2011, their computational cost is often prohibitive. Conversely, shallow networks (e.g., AlexNet, VGG) offer efficiency but fail to distinguish visually similar sub-categories. This is because standard Global Average Pooling (GAP) heads capture only first-order statistics, missing the subtle high-order feature interactions required for FGVC. While Bilinear CNNs address this, they suffer from high feature dimensionality and instability during training. To bridge this gap, we propose the Quantum-inspired Interaction Classifier (QuIC). Drawing inspiration from quantum mechanics, QuIC models feature channels as interacting quantum states and captures second-order feature covariance via a learnable observable operator. Designed as a lightweight, plug-and-play module, QuIC supports stable, single-stage end-to-end training without exploding feature dimensions. Experimental results demonstrate that QuIC significantly revitalizes shallow backbones: it boosts the Top-1 accuracy of VGG16 by nearly 20% and outperforms state-of-the-art attention mechanisms (SE-Block) on ResNet18. Qualitative analysis, including t-SNE visualization, further confirms that QuIC resolves ambiguous cases by explicitly attending to fine-grained discriminative features and enforcing compact intra-class clustering.
Authors: Alexander M\"ollers, Julius Hense, Florian Schulz, Timo Milbich, Maximilian Alber, Lukas Ruff
Abstract: In histopathology, pathologists examine both tissue architecture at low magnification and fine-grained morphology at high magnification. Yet, the performance of pathology foundation models across magnifications and the effect of magnification sampling during training remain poorly understood. We model magnification sampling as a multi-source domain adaptation problem and develop a simple theoretical framework that reveals systematic trade-offs between sampling strategies. We show that the widely used discrete uniform sampling of magnifications (0.25, 0.5, 1.0, 2.0 mpp) leads to degradation at intermediate magnifications. We introduce continuous magnification sampling, which removes gaps in magnification coverage while preserving performance at standard scales. Further, we derive sampling distributions that optimize representation quality across magnification scales. To evaluate these strategies, we introduce two new benchmarks (TCGA-MS, BRACS-MS) with appropriate metrics. Our experiments show that continuous sampling substantially improves over discrete sampling at intermediate magnifications, with gains of up to 4 percentage points in balanced classification accuracy, and that optimized distributions can further improve performance. Finally, we evaluate current histopathology foundation models, finding that magnification is a primary driver of performance variation across models. Our work paves the way towards future pathology foundation models that perform reliably across magnifications.
Authors: Svenja Jedhoff, Elizaveta Semenova, Aura Raulo, Anne Meyer, Paul-Christian B\"urkner
Abstract: Graphs arise across diverse domains, from biology and chemistry to social and information networks, as well as in transportation and logistics. Inference on graph-structured data requires methods that are permutation-invariant, scalable across varying sizes and sparsities, and capable of capturing complex long-range dependencies, making posterior estimation on graph parameters particularly challenging. Amortized Bayesian Inference (ABI) is a simulation-based framework that employs generative neural networks to enable fast, likelihood-free posterior inference. We adapt ABI to graph data to address these challenges to perform inference on node-, edge-, and graph-level parameters. Our approach couples permutation-invariant graph encoders with flexible neural posterior estimators in a two-module pipeline: a summary network maps attributed graphs to fixed-length representations, and an inference network approximates the posterior over parameters. In this setting, several neural architectures can serve as the summary network. In this work we evaluate multiple architectures and assess their performance on controlled synthetic settings and two real-world domains - biology and logistics - in terms of recovery and calibration.
Authors: Grigorii Alekseenko, Aleksandr Gordeev, Irina Tolstykh, Bulat Suleimanov, Vladimir Dokholyan, Georgii Fedorov, Sergey Yakubson, Aleksandra Tsybina, Mikhail Chernyshov, Maksim Kuprashevich
Abstract: Instruction-based image editing is among the fastest developing areas in generative AI. Over the past year, the field has reached a new level, with dozens of open-source models released alongside highly capable commercial systems. However, only a limited number of open-source approaches currently achieve real-world quality. In addition, diffusion backbones, the dominant choice for these pipelines, are often large and computationally expensive for many deployments and research settings, with widely used variants typically containing 6B to 20B parameters. This paper presents a compact, high-throughput instruction-based image editing pipeline that uses a modern 2B-parameter Qwen3-VL model to guide the editing process and the 1.6B-parameter diffusion model Sana1.5 for image generation. Our design decisions across architecture, data processing, training configuration, and evaluation target low-cost inference and strict source consistency while maintaining high quality across the major edit categories feasible at this scale. Evaluated on the ImgEdit and GEdit benchmarks, the proposed method matches or exceeds the performance of substantially heavier baselines, including models with several times as many parameters and higher inference cost, and is particularly strong on edits that require preserving the input image, such as an attribute adjustment, object removal, background edits, and targeted replacement. The model fits within 24 GB of GPU memory and generates edited images at up to 2K resolution in approximately 4 seconds on an NVIDIA H100 in BF16, without additional inference optimizations or distillation.
Authors: Annoor Sharara Akhand
Abstract: Convolutional Neural Networks (CNNs) are a standard approach for visual recognition due to their capacity to learn hierarchical representations from raw pixels. In practice, practitioners often choose among (i) training a compact custom CNN from scratch, (ii) using a large pre-trained CNN as a fixed feature extractor, and (iii) performing transfer learning via partial or full fine-tuning of a pre-trained backbone. This report presents a controlled comparison of these three paradigms across five real-world image classification datasets spanning road-surface defect recognition, agricultural variety identification, fruit/leaf disease recognition, pedestrian walkway encroachment recognition, and unauthorized vehicle recognition. Models are evaluated using accuracy and macro F1-score, complemented by efficiency metrics including training time per epoch and parameter counts. The results show that transfer learning consistently yields the strongest predictive performance, while the custom CNN provides an attractive efficiency--accuracy trade-off, especially when compute and memory budgets are constrained.
Authors: Shikun Sun, Liao Qu, Huichao Zhang, Yiheng Liu, Yangyang Song, Xian Li, Xu Wang, Yi Jiang, Daniel K. Du, Xinglong Wu, Jia Jia
Abstract: Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates severe asynchronous policy conflicts. This issue becomes particularly acute in reinforcement learning (RL) scenarios, leading to unstable training and suboptimal alignment. To resolve this, we propose a novel framework to enhance Group Relative Policy Optimization (GRPO) by explicitly managing these conflicts. Our method integrates three synergistic components: 1) a stabilizing intermediate reward to guide early-stage generation; 2) a dynamic time-step reweighting scheme for precise credit assignment; and 3) a novel mask propagation algorithm, derived from principles of Reward Feedback Learning (ReFL), designed to isolate optimization effects both spatially and temporally. Our approach demonstrates significant improvements in sample quality and objective alignment over the vanilla GRPO baseline, enabling robust and effective optimization for VAR models.
Authors: Joel Daniel Andersson, Palak Jain, Satchit Sivakumar
Abstract: We study differentially-private statistics in the fully dynamic continual observation model, where many updates can arrive at each time step and updates to a stream can involve both insertions and deletions of an item. Earlier work (e.g., Jain et al., NeurIPS 2023 for counting distinct elements; Raskhodnikova & Steiner, PODS 2025 for triangle counting with edge updates) reduced the respective cardinality estimation problem to continual counting on the difference stream associated with the true function values on the input stream. In such reductions, a change in the original stream can cause many changes in the difference stream, this poses a challenge for applying private continual counting algorithms to obtain optimal error bounds. We improve the accuracy of several such reductions by studying the associated $\ell_p$-sensitivity vectors of the resulting difference streams and isolating their properties. We demonstrate that our framework gives improved bounds for counting distinct elements, estimating degree histograms, and estimating triangle counts (under a slightly relaxed privacy model), thus offering a general approach to private continual cardinality estimation in streaming settings. Our improved accuracy stems from tight analysis of known factorization mechanisms for the counting matrix in this setting; the key technical challenge is arguing that one can use state-of-the-art factorizations for sensitivity vector sets with the properties we isolate. Empirically and analytically, we demonstrate that our improved error bounds offer a substantial improvement in accuracy for cardinality estimation problems over a large range of parameters.
Authors: Karla N. Robles, Manar D. Samad
Abstract: Polymer-based long-acting injectables (LAIs) have transformed the treatment of chronic diseases by enabling controlled drug delivery, thus reducing dosing frequency and extending therapeutic duration. Achieving controlled drug release from LAIs requires extensive optimization of the complex underlying physicochemical properties. Machine learning (ML) can accelerate LAI development by modeling the complex relationships between LAI properties and drug release. However, recent ML studies have provided limited information on key properties that modulate drug release, due to the lack of custom modeling and analysis tailored to LAI data. This paper presents a novel data transformation and explainable ML approach to synthesize actionable information from 321 LAI formulations by predicting early drug release at 24, 48, and 72 hours, classification of release profile types, and prediction of complete release profiles. These three experiments investigate the contribution and control of LAI material characteristics in early and complete drug release profiles. A strong correlation (>0.65) is observed between the true and predicted drug release in 72 hours, while a 0.87 F1-score is obtained in classifying release profile types. A time-independent ML framework predicts delayed biphasic and triphasic curves with better performance than current time-dependent approaches. Shapley additive explanations reveal the relative influence of material characteristics during early and for complete release which fill several gaps in previous in-vitro and ML-based studies. The novel approach and findings can provide a quantitative strategy and recommendations for scientists to optimize the drug-release dynamics of LAI. The source code for the model implementation is publicly available.
Authors: Salim Khazem
Abstract: Foundation segmentation models such as the Segment Anything Model (SAM) exhibit strong zero-shot generalization through large-scale pretraining, but adapting them to domain-specific semantic segmentation remains challenging, particularly for thin structures (e.g., retinal vessels) and noisy modalities (e.g., SAR imagery). Full fine-tuning is computationally expensive and risks catastrophic forgetting. We propose \textbf{TopoLoRA-SAM}, a topology-aware and parameter-efficient adaptation framework for binary semantic segmentation. TopoLoRA-SAM injects Low-Rank Adaptation (LoRA) into the frozen ViT encoder, augmented with a lightweight spatial convolutional adapter and optional topology-aware supervision via differentiable clDice. We evaluate our approach on five benchmarks spanning retinal vessel segmentation (DRIVE, STARE, CHASE\_DB1), polyp segmentation (Kvasir-SEG), and SAR sea/land segmentation (SL-SSDD), comparing against U-Net, DeepLabV3+, SegFormer, and Mask2Former. TopoLoRA-SAM achieves the best retina-average Dice and the best overall average Dice across datasets, while training only \textbf{5.2\%} of model parameters ($\sim$4.9M). On the challenging CHASE\_DB1 dataset, our method substantially improves segmentation accuracy and robustness, demonstrating that topology-aware parameter-efficient adaptation can match or exceed fully fine-tuned specialist models. Code is available at : https://github.com/salimkhazem/Seglab.git
Authors: Shuozhi Zuo, Yixin Wang
Abstract: Out-of-distribution (OOD) prediction is often approached by restricting models to causal or invariant covariates, avoiding non-causal spurious associations that may be unstable across environments. Despite its theoretical appeal, this strategy frequently underperforms empirical risk minimization (ERM) in practice. We investigate the source of this gap and show that such failures naturally arise when only a subset of the true causes of the outcome is observed. In these settings, non-causal spurious covariates can serve as informative proxies for unobserved causes and substantially improve prediction, except under distribution shifts that break these proxy relationships. Consequently, the optimal set of predictive covariates is neither universal nor necessarily exhibits invariant relationships with the outcome across all environments, but instead depends on the specific type of shift encountered. Crucially, we observe that different covariate shifts induce distinct, observable signatures in the covariate distribution itself. Moreover, these signatures can be extracted from unlabeled data in the target OOD environment and used to assess when proxy covariates remain reliable and when they fail. Building on this observation, we propose an environment-adaptive covariate selection (EACS) algorithm that maps environment-level covariate summaries to environment-specific covariate sets, while allowing the incorporation of prior causal knowledge as constraints. Across simulations and applied datasets, EACS consistently outperforms static causal, invariant, and ERM-based predictors under diverse distribution shifts.
Authors: Alexander Roman, Emilie Panek, Roy T. Forestano, Eyup B. Unlu, Katia Matcheva, Konstantin T. Matchev
Abstract: This study explores the application of autoencoder-based machine learning techniques for anomaly detection to identify exoplanet atmospheres with unconventional chemical signatures using a low-dimensional data representation. We use the Atmospheric Big Challenge (ABC) database, a publicly available dataset with over 100,000 simulated exoplanet spectra, to construct an anomaly detection scenario by defining CO2-rich atmospheres as anomalies and CO2-poor atmospheres as the normal class. We benchmarked four different anomaly detection strategies: Autoencoder Reconstruction Loss, One-Class Support Vector Machine (1 class-SVM), K-means Clustering, and Local Outlier Factor (LOF). Each method was evaluated in both the original spectral space and the autoencoder's latent space using Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) metrics. To test the performance of the different methods under realistic conditions, we introduced Gaussian noise levels ranging from 10 to 50 ppm. Our results indicate that anomaly detection is consistently more effective when performed within the latent space across all noise levels. Specifically, K-means clustering in the latent space emerged as a stable and high-performing method. We demonstrate that this anomaly detection approach is robust to noise levels up to 30 ppm (consistent with realistic space-based observations) and remains viable even at 50 ppm when leveraging latent space representations. On the other hand, the performance of the anomaly detection methods applied directly in the raw spectral space degrades significantly with increasing the level of noise. This suggests that autoencoder-driven dimensionality reduction offers a robust methodology for flagging chemically anomalous targets in large-scale surveys where exhaustive retrievals are computationally prohibitive.
Authors: Shahnawaz Alam, Mohammed Mudassir Uddin, Mohammed Kaif Pasha
Abstract: Farmers in remote areas need quick and reliable methods for identifying plant diseases, yet they often lack access to laboratories or high-performance computing resources. Deep learning models can detect diseases from leaf images with high accuracy, but these models are typically too large and computationally expensive to run on low-cost edge devices such as Raspberry Pi. Furthermore, collecting thousands of labeled disease images for training is both expensive and time-consuming. This paper addresses both challenges by combining neural network pruning -- removing unnecessary parts of the model -- with few-shot learning, which enables the model to learn from limited examples. This paper proposes Disease-Aware Channel Importance Scoring (DACIS), a method that identifies which parts of the neural network are most important for distinguishing between different plant diseases, integrated into a three-stage Prune-then-Meta-Learn-then-Prune (PMP) pipeline. Experiments on PlantVillage and PlantDoc datasets demonstrate that the proposed approach reduces model size by 78\% while maintaining 92.3\% of the original accuracy, with the compressed model running at 7 frames per second on a Raspberry Pi 4, making real-time field diagnosis practical for smallholder farmers.
Authors: Junhwa Song, Keumgang Cha, Junghoon Seo
Abstract: Approaches for appraising feature importance approximations, alternatively referred to as attribution methods, have been established across an extensive array of contexts. The development of resilient techniques for performance benchmarking constitutes a critical concern in the sphere of explainable deep learning. This study scrutinizes the dependability of the RemOve-And-Retrain (ROAR) procedure, which is prevalently employed for gauging the performance of feature importance estimates. The insights gleaned from our theoretical foundation and empirical investigations reveal that attributions containing lesser information about the decision function may yield superior results in ROAR benchmarks, contradicting the original intent of ROAR. This occurrence is similarly observed in the recently introduced variant RemOve-And-Debias (ROAD), and we posit a persistent pattern of blurriness bias in ROAR attribution metrics. Our findings serve as a warning against indiscriminate use on ROAR metrics.
Authors: Natha\"el Da Costa, Marvin Pf\"ortner, Lancelot Da Costa, Philipp Hennig
Abstract: Gaussian processes (GPs) are the most common formalism for defining probability distributions over spaces of functions. While applications of GPs are myriad, a comprehensive understanding of GP sample paths, i.e. the function spaces over which they define a probability measure, is lacking. In practice, GPs are not constructed through a probability measure, but instead through a mean function and a covariance kernel. In this paper we provide necessary and sufficient conditions on the covariance kernel for the sample paths of the corresponding GP to attain a given regularity. We focus primarily on H\"older regularity as it grants particularly straightforward conditions, which simplify further in the cases of stationary and isotropic GPs. We then demonstrate that our results allow for novel and unusually tight characterisations of the sample path regularities of the GPs commonly used in machine learning applications, such as the Mat\'ern GPs.
Authors: Shicong Cen, Jincheng Mei, Hanjun Dai, Dale Schuurmans, Yuejie Chi, Bo Dai
Abstract: Stochastic dominance serves as a general framework for modeling a broad spectrum of decision preferences under uncertainty, with risk aversion as one notable example, as it naturally captures the intrinsic structure of the underlying uncertainty, in contrast to simply resorting to the expectations. Despite theoretical appeal, the application of stochastic dominance in machine learning has been scarce, due to the following challenges: $\textbf{i)}$, the original concept of stochastic dominance only provides a $\textit{partial order}$, and therefore, is not amenable to serve as a general optimality criterion; and $\textbf{ii)}$, an efficient computational recipe remains lacking due to the continuum nature of evaluating stochastic dominance. In this work, we make the first attempt towards establishing a general framework of learning with stochastic dominance. We first generalize the stochastic dominance concept to enable feasible comparisons between any arbitrary pair of random variables. We next develop a simple and computationally efficient approach for finding the optimal solution in terms of stochastic dominance, which can be seamlessly plugged into many learning tasks. Numerical experiments demonstrate that the proposed method achieves comparable performance as standard risk-neutral strategies and obtains better trade-offs against risk across a variety of applications including supervised learning, reinforcement learning, and portfolio optimization.
Authors: Hao Ma, Melanie Zeilinger, Michael Muehlebach
Abstract: We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems. Our problem formulation accommodates constraints that model the evolution of a cyber-physical system, which has, in general, a continuous state and action space, is nonlinear, and where the state is only partially observed. We also incorporate an approximate model of the dynamics as prior knowledge into the learning process and show that even rough estimates of the dynamics can significantly improve the convergence of our algorithms. Our online optimization framework encompasses both gradient descent and quasi-Newton methods, and we provide a unified convergence analysis of our algorithms in a non-convex setting. We also characterize the impact of modeling errors in the system dynamics on the convergence rate of the algorithms. Finally, we evaluate our algorithms in simulations of a flexible beam, a four-legged walking robot, and in real-world experiments with a ping-pong playing robot.
Authors: Susan Athey, Herman Brunborg, Tianyu Du, Ayush Kanodia, Keyon Vafa
Abstract: This paper builds an empirical model that predicts a worker's next occupation as a function of the worker's occupational history. Because histories are sequences of occupations, the covariate space is high-dimensional, and further, the outcome (the next occupation) is a discrete choice that can take on many values. To estimate the parameters of the model, we leverage an approach from generative artificial intelligence. Estimation begins from a ``foundation model'' trained on non-representative data and then ``fine-tunes'' the estimation using data about careers from a representative survey. We convert tabular data from the survey into text files that resemble resumes and fine-tune the parameters of the foundation model, a large language model (LLM), using these text files with the objective of predicting the next token (word). The resulting fine-tuned LLM is used to calculate estimates of worker transition probabilities. Its predictive performance surpasses all prior models, both for the task of granularly predicting the next occupation as well as for specific tasks such as predicting whether the worker changes occupations or stays in the labor force. We quantify the value of fine-tuning and further show that by adding more career data from a different population, fine-tuning smaller LLMs (fewer parameters) surpasses the performance of fine-tuning larger models. When we omit the English language occupational title and replace it with a unique code, predictive performance declines.
Authors: Kazumi Kasaura
Abstract: To find the shortest paths for all pairs on manifolds with infinitesimally defined metrics, we introduce a framework to generate them by predicting midpoints recursively. To learn midpoint prediction, we propose an actor-critic approach. We prove the soundness of our approach and show experimentally that the proposed method outperforms existing methods on several planning tasks, including path planning for agents with complex kinematics and motion planning for multi-degree-of-freedom robot arms.
Authors: Christoffer Olling Back, Jakob Grue Simonsen
Abstract: Event knowledge graphs (EKG) extend the classical notion of a trace to capture multiple, interacting views of a process execution. In this paper, we tackle the open problem of automating EKG discovery from uncurated data through a principled probabilistic framing based on the outcome space resulting from featured-derived partial orders on events. From this we derive an EKG discovery algorithm based on statistical inference rather than an ad hoc or heuristic-based strategy, or relying on manual analysis from domain experts. This approach comes at the computational cost of exploring a large, non-convex hypothesis space. In particular, solving the maximum likelihood term in our objective function involves counting the number of linear extensions of posets, which in general is #P-complete. Fortunately, bound estimates suffice for model comparison, and admit incorporation into a bespoke branch-and-bound algorithm. We establish an upper bound on our objective function which we show to be antitonic w.r.t. search depth for branching rules that are monotonic w.r.t. model inclusion. This allows pruning of large portions of the search space, which we show experimentally leads to rapid convergence toward optimal solutions that are consistent with manually built EKGs.
Authors: Zhenhua Wang, Scott H. Holan, Christopher K. Wikle
Abstract: Spatio-temporal area-level datasets play a critical role in official statistics, providing valuable insights for policy-making and regional planning. Accurate modeling and forecasting of these datasets can be extremely useful for policymakers to develop informed strategies for future planning. Echo State Networks (ESNs) are efficient methods for capturing nonlinear temporal dynamics and generating forecasts. However, ESNs lack a direct mechanism to account for the neighborhood structure inherent in area-level data. Ignoring these spatial relationships can significantly compromise the accuracy and utility of forecasts. In this paper, we incorporate approximate graph spectral filters at the input stage of the ESN, thereby improving forecast accuracy while preserving the model's computational efficiency during training. We demonstrate the effectiveness of our approach using Eurostat's tourism occupancy dataset and show how it can support more informed decision-making in policy and planning contexts.
Authors: Fei Liu, Yiming Yao, Ping Guo, Zhiyuan Yang, Zhe Zhao, Xi Lin, Xialiang Tong, Kun Mao, Zhichao Lu, Zhenkun Wang, Mingxuan Yuan, Qingfu Zhang
Abstract: Algorithm design is crucial for effective problem-solving across various domains. The advent of Large Language Models (LLMs) has notably enhanced the automation and innovation within this field, offering new perspectives and promising solutions. In just a few years, this integration has yielded remarkable progress in areas ranging from combinatorial optimization to scientific discovery. Despite this rapid expansion, a holistic understanding of the field is hindered by the lack of a systematic review, as existing surveys either remain limited to narrow sub-fields or with different objectives. This paper seeks to provide a systematic review of algorithm design with LLMs. We introduce a taxonomy that categorises the roles of LLMs as optimizers, predictors, extractors and designers, analyzing the progress, advantages, and limitations within each category. We further synthesize literature across the three phases of the algorithm design pipeline and across diverse algorithmic applications that define the current landscape. Finally, we outline key open challenges and opportunities to guide future research. To support future research and collaboration, we provide an accompanying repository at: https://github.com/FeiLiu36/LLM4AlgorithmDesign.
Authors: Ahmed A. Elhag, T. Konstantin Rusch, Francesco Di Giovanni, Michael Bronstein
Abstract: Incorporating equivariance as an inductive bias into deep learning architectures to take advantage of the data symmetry has been successful in multiple applications, such as chemistry and dynamical systems. In particular, roto-translations are crucial for effectively modeling geometric graphs and molecules, where understanding the 3D structures enhances generalization. However, strictly equivariant models often pose challenges due to their higher computational complexity. In this paper, we introduce REMUL, a training procedure that learns \emph{approximate} equivariance for unconstrained networks via multitask learning. By formulating equivariance as a tunable objective alongside the primary task loss, REMUL offers a principled way to control the degree of approximate symmetry, relaxing the rigid constraints of traditional equivariant architectures. We show that unconstrained models (which do not build equivariance into the architecture) can learn approximate symmetries by minimizing an additional simple equivariance loss. This enables quantitative control over the trade-off between enforcing equivariance constraints and optimizing for task-specific performance. Our method achieves competitive performance compared to equivariant baselines while being significantly faster (up to 10$\times$ at inference and 2.5$\times$ at training), offering a practical and adaptable approach to leveraging symmetry in unconstrained architectures.
Authors: Hengkai Tan, Xuezhou Xu, Chengyang Ying, Xinyi Mao, Zeyuan Wang, Songming Liu, Xingxing Zhang, Zhizhong Su, Hang Su, Jun Zhu
Abstract: Embodied agents require robust spatial intelligence to execute precise real-world manipulations. However, this remains a significant challenge, as current methods often struggle to accurately position objects in space. Collecting extensive data can help address this issue by enhancing the agent's spatial understanding. Nonetheless, obtaining such data with real robots is prohibitively expensive, and relying on simulation data frequently leads to visual generalization gaps during real-world deployment. To tackle these challenges, we propose ManiBox, a novel bounding-box-guided framework. By decoupling perception from policy generalization, ManiBox effectively reduces the Sim2Real gap, leverages Internet-scale data, and scales our policy data collection in simulation. Specifically, within ManiBox, the RL teacher policy efficiently generates scalable simulation data. The student policy is distilled from this data and takes bounding boxes as input, which is proven sufficient for determining objects' spatial positions, thus enabling zero-shot transfer to real robots. Comprehensive evaluations in both simulated and real-world environments demonstrate that ManiBox exhibits strong spatial generalization and adaptability across various manipulation tasks and settings. Furthermore, our empirical study provides preliminary verification of spatial scaling laws, i.e., the amount of data required for spatial generalization scales with spatial volume following a power-law relationship. At a given spatial volume level, the success rate of manipulation tasks follows Michaelis-Menten kinetics with respect to data volume, exhibiting a saturation effect as data increases. Our videos and code are available at https://thkkk.github.io/manibox
Authors: Nachiket Kapure, Harsh Joshi, Parul Kumari, Rajeshwari Mistri, Manasi Mali
Abstract: The challenges in feature selection, particularly in balancing model accuracy, interpretability, and computational efficiency, remain a critical issue in advancing machine learning methodologies. To address these complexities, this study introduces a novel hybrid approach, the Forward Recursive Adaptive Model Extraction Technique (FRAME), which combines Forward Selection and Recursive Feature Elimination (RFE) to enhance feature selection across diverse datasets. By combining the exploratory capabilities of Forward Selection with the refinement strengths of RFE, FRAME systematically identifies optimal feature subsets, striking a harmonious trade-off between experimentation and precision. A comprehensive evaluation of FRAME is conducted against traditional methods such as SelectKBest and Lasso Regression, using high-dimensional, noisy, and heterogeneous datasets. The results demonstrate that FRAME consistently delivers superior predictive performance based on downstream machine learning evaluation metrics. It efficiently performs dimensionality reduction with strong model performance, thus being especially useful for applications that need interpretable and accurate predictions, e.g., biomedical diagnostics. This research emphasizes the need to evaluate feature selection techniques on diverse datasets to test their robustness and generalizability. The results indicate that FRAME has great potential for further development, especially by incorporating deep learning frameworks for adaptive and real-time feature selection in dynamic settings. By advancing feature selection methodologies, FRAME offers a practical and effective solution to improve machine learning applications across multiple domains.
Authors: Shangqian Gao, Ting Hua, Reza Shirkavand, Chi-Heng Lin, Zheng Tang, Zhengao Li, Longge Yuan, Fangyi Li, Zeyu Zhang, Alireza Ganjdanesh, Lou Qian, Xu Jie, Yen-Chang Hsu
Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained devices or efficiently serving them. Prior approaches have attempted to alleviate these problems by permanently removing less important model structures, yet these methods often result in substantial performance degradation due to the permanent deletion of model parameters. In this work, we tried to mitigate this issue by reducing the number of active parameters without permanently removing them. Specifically, we introduce a differentiable dynamic pruning method that pushes dense models to maintain a fixed number of active parameters by converting their MLP layers into a Mixture of Experts (MoE) architecture. Our method, even without fine-tuning, consistently outperforms previous structural pruning techniques across diverse model families, including Phi-2, LLaMA-2, LLaMA-3, and Qwen-2.5.
Authors: Levente Z\'olyomi, Tianze Wang, Sofiane Ennadir, Oleg Smirnov, Lele Cao
Abstract: The proliferation of digital interactions across diverse domains, such as healthcare, e-commerce, gaming, and finance, has resulted in the generation of vast volumes of event stream (ES) data. ES data comprises continuous sequences of timestamped events that encapsulate detailed contextual information relevant to each domain. While ES data holds significant potential for extracting actionable insights and enhancing decision-making, its effective utilization is hindered by challenges such as the scarcity of labeled data and the fragmented nature of existing research efforts. Self-Supervised Learning (SSL) has emerged as a promising paradigm to address these challenges by enabling the extraction of meaningful representations from unlabeled ES data. In this survey, we systematically review and synthesize SSL methodologies tailored for ES modeling across multiple domains, bridging the gaps between domain-specific approaches that have traditionally operated in isolation. We present a comprehensive taxonomy of SSL techniques, encompassing both predictive and contrastive paradigms, and analyze their applicability and effectiveness within different application contexts. Furthermore, we identify critical gaps in current research and propose a future research agenda aimed at developing scalable, domain-agnostic SSL frameworks for ES modeling. By unifying disparate research efforts and highlighting cross-domain synergies, this survey aims to accelerate innovation, improve reproducibility, and expand the applicability of SSL to diverse real-world ES challenges.
Authors: Yuki Shibukawa, Taira Tsuchiya, Shinsaku Sakaue, Kenji Yamanishi
Abstract: Online structured prediction is a task of sequentially predicting outputs with complex structures based on inputs and past observations, encompassing online classification. Recent studies showed that in the full-information setting, we can achieve finite bounds on the \textit{surrogate regret}, \textit{i.e.,}~the extra target loss relative to the best possible surrogate loss. In practice, however, full-information feedback is often unrealistic as it requires immediate access to the whole structure of complex outputs. Motivated by this, we propose algorithms that work with less demanding feedback, \textit{bandit} and \textit{delayed} feedback. For bandit feedback, by using a standard inverse-weighted gradient estimator, we achieve a surrogate regret bound of $O(\sqrt{KT})$ for the time horizon $T$ and the size of the output set $K$. However, $K$ can be extremely large when outputs are highly complex, resulting in an undesirable bound. To address this issue, we propose another algorithm that achieves a surrogate regret bound of $O(T^{2/3})$, which is independent of $K$. This is achieved with a carefully designed pseudo-inverse matrix estimator. Furthermore, we numerically compare the performance of these algorithms, as well as existing ones. Regarding delayed feedback, we provide algorithms and regret analyses that cover various scenarios, including full-information and bandit feedback, as well as fixed and variable delays.
Authors: Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Debbah
Abstract: Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning chains. Techniques such as inference-time scaling, reinforcement learning, supervised fine-tuning, and distillation have been effectively applied to state-of-the-art models, including DeepSeek-R1, OpenAI o1 and o3, GPT-4o, Qwen-32B, and various Llama variants, significantly enhancing their reasoning capabilities. In this paper, we present a comprehensive review of the top 27 LLMs released between 2023 and 2025, such as Mistral AI Small 3 24B, DeepSeek-R1, Search-o1, QwQ-32B, and Phi-4, and analyze their core innovations and performance improvements. We also provide a detailed overview of recent advancements in multilingual large language models (MLLMs), emphasizing methods that improve cross-lingual reasoning and address the limitations of English-centric training. In parallel, we present a comprehensive review of progress in state space model (SSM)-based architectures, including models such as Mamba, which demonstrate improved efficiency for long-context processing compared to transformer-based approaches. Our analysis covers training strategies including general optimization techniques, mixture-of-experts (MoE) configurations, retrieval-augmented generation (RAG), chain-of-thought prompting, self-improvement methods, and test-time compute scaling and distillation frameworks. Finally, we identify key challenges for future research, including enabling multi-step reasoning without human supervision, improving robustness in chained task execution, balancing structured prompting with generative flexibility, and enhancing the integration of long-context retrieval and external tools.
Authors: Lingyue Fu, Ting Long, Jianghao Lin, Wei Xia, Xinyi Dai, Ruiming Tang, Yasheng Wang, Weinan Zhang, Yong Yu
Abstract: Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences. Existing KT models typically follow a single-step training paradigm, which leads to discrepancies with the multi-step inference process required in real-world simulations, resulting in significant error accumulation. This accumulation of error, coupled with the issue of data sparsity, can substantially degrade the performance of recommendation models in the intelligent tutoring systems. To address these challenges, we propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT), which, for the first time, focuses on the multi-step KT task. More specifically, AdvKT leverages adversarial learning paradigm involving a generator and a discriminator. The generator mimics high-reward responses, effectively reducing error accumulation across multiple steps, while the discriminator provides feedback to generate synthetic data. Additionally, we design specialized data augmentation techniques to enrich the training data with realistic variations, ensuring that the model generalizes well even in scenarios with sparse data. Experiments conducted on four real-world datasets demonstrate the superiority of AdvKT over existing KT models, showcasing its ability to address both error accumulation and data sparsity issues effectively.
Authors: Yoshihiro Yamada
Abstract: Transformers have driven remarkable breakthroughs in natural language processing and computer vision, yet their standard attention mechanism still imposes O(N^2) complexity, hindering scalability to longer sequences. We introduce Circular-convolutional ATtention (CAT), a Fourier-based approach that efficiently applies circular convolutions to reduce complexity without sacrificing representational power. CAT achieves O(NlogN) computations, requires fewer learnable parameters by streamlining fully connected layers, and introduces no additional heavy operations, resulting in consistent accuracy improvements and about a 10% speedup in naive PyTorch implementations. Based on the Engineering-Isomorphic Transformers (EITs) framework, CAT's design not only offers practical efficiency and ease of implementation, but also provides insights to guide the development of future high-performance Transformer architectures. Finally, our ablation studies highlight the key conditions underlying CAT's success, shedding light on broader principles for scalable attention mechanisms.
Authors: Ruicheng Ao, Gan Luo, David Simchi-Levi, Xinshang Wang
Abstract: Large Language Models (LLMs) power many modern applications, but their inference procedure poses unique scheduling challenges: the Key-Value (KV) cache grows dynamically during response generation, and memory overflow triggers eviction that can cascade into system-wide failures. Even when memory capacity exceeds the theoretical requirement, conventional scheduling algorithms fail because they do not account for this dynamic memory growth -- a system that should be stable can become unstable under poor scheduling. This paper formulates LLM inference optimization as a multi-stage online scheduling problem. We develop a fluid dynamics approximation to establish a tractable benchmark and derive the Waiting for Accumulated Inference Threshold (WAIT) algorithm. WAIT uses threshold-based batching to prevent eviction by keeping the system near load balance, achieving near-optimal throughput when output lengths are known. For practical settings where output lengths are unknown at arrival, we introduce Nested WAIT. Rather than predicting output lengths, Nested WAIT classifies prompts on-the-fly: short prompts complete early and exit, while longer prompts naturally advance to later segments. A safety buffer provides high-probability protection against memory overflow with only logarithmic overhead. Theoretical analysis establishes near-optimal performance in the asymptotic regime. Experiments on Llama-7B with an A100 GPU demonstrate that our approach achieves superior throughput and reduced latency compared to vLLM and Sarathi. This work applies operations research principles to establish a theoretical framework for LLM deployment under memory constraints.
Authors: Shangzhe Li, Zhiao Huang, Hao Su
Abstract: Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods often face instability challenges, particularly when relying on adversarial reward or value formulations in world model frameworks. In this work, we propose a novel approach to online imitation learning that addresses these limitations through a reward model based on random network distillation (RND) for density estimation. Our reward model is built on the joint estimation of expert and behavioral distributions within the latent space of the world model. We evaluate our method across diverse benchmarks, including DMControl, Meta-World, and ManiSkill2, showcasing its ability to deliver stable performance and achieve expert-level results in both locomotion and manipulation tasks. Our approach demonstrates improved stability over adversarial methods while maintaining expert-level performance.
Authors: Changhai Zhou, Shiyang Zhang, Yuhua Zhou, Qian Qiao, Jun Gao, Shichao Weng, Weizhong Zhang, Cheng Jin
Abstract: Deploying and fine-tuning Large Language Models (LLMs) on resource-constrained edge devices requires navigating a strict trade-off between memory footprint and task performance. While Quantization-Aware Fine-tuning has emerged as a viable solution, existing paradigms typically decouple quantization and adapter optimization. This separation overlooks a fundamental theoretical constraint we identify as the \textit{Fidelity-Plasticity Trade-off}: a layer's capacity to adapt to new tasks (Plasticity) is inherently constrained by the information capacity of its frozen weights (Fidelity). Aggressively quantizing semantically critical layers creates an information bottleneck that no amount of adapter rank can recover, while high precision in robust syntactic layers wastes valuable memory. To address this, we introduce \textbf{QR-Adaptor}, a unified framework that jointly optimizes per-layer quantization bit-width and LoRA rank. By formulating resource allocation as a multi-objective search aligned with the model's linguistic hierarchy, our method systematically liberates memory from redundancy-heavy layers to reinvest in capacity-critical ones. Extensive experiments demonstrate that QR-Adaptor establishes a new Pareto frontier: notably, a model fine-tuned under a strict 4-bit memory budget achieves performance rivaling 16-bit baselines, demonstrating that precise resource alignment is as critical as model size.
Authors: Yuzhou Zhu, Zheng Zhang, Ruyi Zhang, Liang Zhou
Abstract: Wave-like images--from attosecond streaking spectrograms to optical spectra, audio mel-spectrograms and periodic video frames--encode critical harmonic structures that elude conventional feature extractors. We propose a unified, matrix-equivalent framework that reinterprets convolution and attention as linear transforms on flattened inputs, revealing filter weights as basis vectors spanning latent feature subspaces. To infuse spectral priors we apply elementwise \(\sin(\cdot)\) mappings to each weight matrix. Embedding these transforms into CNN, ViT and Capsule architectures yields Sin-Basis Networks with heightened sensitivity to periodic motifs and built-in invariance to spatial shifts. Experiments on a diverse collection of wave-like image datasets--including 80,000 synthetic attosecond streaking spectrograms, thousands of Raman, photoluminescence and FTIR spectra, mel-spectrograms from AudioSet and cycle-pattern frames from Kinetics--demonstrate substantial gains in reconstruction accuracy, translational robustness and zero-shot cross-domain transfer. Theoretical analysis via matrix isomorphism and Mercer-kernel truncation quantifies how sinusoidal reparametrization enriches expressivity while preserving stability in data-scarce regimes. Sin-Basis Networks thus offer a lightweight, physics-informed approach to deep learning across all wave-form imaging modalities.
Authors: Patrik Kenfack, Samira Ebrahimi Kahou, Ulrich A\"ivodji
Abstract: Transformer-based tabular foundation models have recently demonstrated promising in-context learning (ICL) performance on structured data, emerging as competitive alternatives to gradient-boosted trees. However, the fairness implications of this new paradigm remain largely unexplored. We present the first investigation of fairness in tabular ICL, evaluating three recently proposed foundation models--TabPFNv2, TabICL, and TabDPT--on multiple benchmark datasets. To mitigate biases, we explore three pre-processing fairness-enhancing methods: correlation removal (decorrelating input features from the sensitive attribute), group-balanced sample selection (ensuring equal representation of protected groups in context examples), and uncertainty-based sample selection (prioritizing context examples with high sensitive-attribute prediction uncertainty). Our experiments show that the uncertainty-based strategy consistently improves group fairness metrics (e.g., demographic parity, equalized odds, and equal opportunity) with minimal impact on predictive accuracy. We release our code to facilitate reproducibility https://github.com/patrikken/Fair-TabICL.
Authors: Zichen Liu, Wei Zhang, Tiejun Li
Abstract: Euclidean diffusion models have achieved remarkable success in generative modeling across diverse domains, and they have been extended to manifold cases in recent advances. Instead of explicitly utilizing the structure of special manifolds as studied in previous works, in this paper we investigate direct sampling of the Euclidean diffusion models for general manifold-structured data. We reveal the multiscale singularity of the score function in the ambient space, which hinders the accuracy of diffusion-generated samples. We then present an elaborate theoretical analysis of the singularity structure of the score function by decomposing it along the tangential and normal directions of the manifold. To mitigate the singularity and improve the sampling accuracy, we propose two novel methods: (1) Niso-DM, which reduces the scale discrepancies in the score function by utilizing a non-isotropic noise, and (2) Tango-DM, which trains only the tangential component of the score function using a tangential-only loss function. Numerical experiments demonstrate that our methods achieve superior performance on distributions over various manifolds with complex geometries.
Authors: Yihan Zhu, Gang Liu, Eric Inae, Tengfei Luo, Meng Jiang
Abstract: Polymers are large macromolecules composed of repeating structural units known as monomers and are widely applied in fields such as energy storage, construction, medicine, and aerospace. However, existing graph neural network methods, though effective for small molecules, only model the single unit of polymers and fail to produce consistent vector representations for the true polymer structure with varying numbers of units. To address this challenge, we introduce Graph Repetition Invariance (GRIN), a novel method to learn polymer representations that are invariant to the number of repeating units in their graph representations. GRIN integrates a graph-based maximum spanning tree alignment with repeat-unit augmentation to ensure structural consistency. We provide theoretical guarantees for repetition-invariance from both model and data perspectives, demonstrating that three repeating units are the minimal augmentation required for optimal invariant representation learning. GRIN outperforms state-of-the-art baselines on both homopolymer and copolymer benchmarks, learning stable, repetition-invariant representations that generalize effectively to polymer chains of unseen sizes.
Authors: Xiaotian Zhang, Yue Shang, Entao Yang, Ge Zhang
Abstract: Understanding neural network's (NN) generalizability remains a central question in deep learning research. The special phenomenon of grokking, where NNs abruptly generalize long after the training performance reaches a near-perfect level, offers a unique window to investigate the underlying mechanisms of NNs' generalizability. Here we propose an interpretation for grokking by framing it as a computational glass relaxation: viewing NNs as a physical system where parameters are the degrees of freedom and train loss is the system energy, we find memorization process resembles a rapid cooling of liquid into non-equilibrium glassy state at low temperature and the later generalization is like a slow relaxation towards a more stable configuration. This mapping enables us to sample NNs' Boltzmann entropy (states of density) landscape as a function of training loss and test accuracy. Our experiments in transformers on arithmetic tasks suggests that there is NO entropy barrier in the memorization-to-generalization transition of grokking, challenging previous theory that defines grokking as a first-order phase transition. We identify a high-entropy advantage under grokking, an extension of prior work linking entropy to generalizability but much more significant. Inspired by grokking's far-from-equilibrium nature, we develop a toy optimizer WanD based on Wang-landau molecular dynamics, which can eliminate grokking without any constraints and find high-norm generalizing solutions. This provides strictly-defined counterexamples to theory attributing grokking solely to weight norm evolution towards the Goldilocks zone and also suggests new potential ways for optimizer design.
Authors: Wenhao Dai, Haodong Deng, Mengfei Rong, Xinyu Yang, Hongyu Liu, Fangxin Liu, Hailong Yang, Qianwen Cao, Qingxiao Sun
Abstract: Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask layers introduce sparsity into Transformer to reduce calculations. However, previous works rarely focus on the performance optimization of sparse Transformer. In addition, current static operator fusion schemes fail to adapt to diverse application scenarios. To address the above problems, we propose STOF, a framework that incorporates optimizations for Sparse Transformer that enables flexible masking and Operator Fusion on GPU. For multi-head attention (MHA) structure, STOF maps the computation to row-wise or blockwise kernels with unique storage formats according to analytical modeling. For downstream operators, STOF maps the fusion scheme to compilation templates and determines the optimal running configuration through two-stage searching. The experimental results show that compared to the stateof-the-art work, STOF achieves maximum speedups of 1.6x in MHA computation and 1.4x in end-to-end inference.
Authors: Hsi-Che Lin, Yu-Chu Yu, Kai-Po Chang, Yu-Chiang Frank Wang
Abstract: Open-source foundation models have seen rapid adoption and development, enabling powerful general-purpose capabilities across diverse domains. However, fine-tuning large foundation models for domain-specific or personalized tasks remains prohibitively expensive for most users due to the significant memory overhead beyond that of inference. We introduce EMLoC, an Emulator-based Memory-efficient fine-tuning framework with LoRA Correction, which enables model fine-tuning within the same memory budget required for inference. EMLoC constructs a task-specific light-weight emulator using activation-aware singular value decomposition (SVD) on a small downstream calibration set. Fine-tuning then is performed on this lightweight emulator via LoRA. To tackle the misalignment between the original model and the compressed emulator, we propose a novel compensation algorithm to correct the fine-tuned LoRA module, which thus can be merged into the original model for inference. EMLoC supports flexible compression ratios and standard training pipelines, making it adaptable to a wide range of applications. Extensive experiments demonstrate that EMLoC outperforms other baselines across multiple datasets and modalities. Moreover, without quantization, EMLoC enables fine-tuning of a 38B model, which originally required 95GB of memory, on a single 24GB consumer GPU-bringing efficient and practical model adaptation to individual users.
Authors: Guanming Zhang, David J. Heeger, Stefano Martiniani
Abstract: Contrastive self-supervised learning based on point-wise comparisons has been widely studied for vision tasks. In the visual cortex of the brain, neuronal responses to distinct stimulus classes are organized into geometric structures known as neural manifolds. Accurate classification of stimuli can be achieved by effectively separating these manifolds, akin to solving a packing problem. We introduce Contrastive Learning As Manifold Packing (CLAMP), a self-supervised framework that recasts representation learning as a manifold packing problem. CLAMP introduces a loss function inspired by the potential energy of short-range repulsive particle systems, such as those encountered in the physics of simple liquids and jammed packings. In this framework, each class consists of sub-manifolds embedding multiple augmented views of a single image. The sizes and positions of the sub-manifolds are dynamically optimized by following the gradient of a packing loss. This approach yields interpretable dynamics in the embedding space that parallel jamming physics, and introduces geometrically meaningful hyperparameters within the loss function. Under the standard linear evaluation protocol, which freezes the backbone and trains only a linear classifier, CLAMP achieves competitive performance with state-of-the-art self-supervised models. Furthermore, our analysis reveals that neural manifolds corresponding to different categories emerge naturally and are effectively separated in the learned representation space, highlighting the potential of CLAMP to bridge insights from physics, neural science, and machine learning.
Authors: Vanessa Kosoy
Abstract: We propose a new variant of online learning that we call "ambiguous online learning". In this setting, the learner is allowed to produce multiple predicted labels. Such an "ambiguous prediction" is considered correct when at least one of the labels is correct, and none of the labels are "predictably wrong". The definition of "predictably wrong" comes from a hypothesis class in which hypotheses are also multi-valued. Thus, a prediction is "predictably wrong" if it's not allowed by the (unknown) true hypothesis. In particular, this setting is natural in the context of multivalued dynamical systems, recommendation algorithms and lossless compression. It is also strongly related to so-called "apple tasting". We show that in this setting, there is a trichotomy of mistake bounds: up to logarithmic factors, any hypothesis class has an optimal mistake bound of either Theta(1), Theta(sqrt(N)) or N.
Authors: Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud
Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak sensitive information about the underlying data, raising privacy and security concerns such as susceptibility to data poisoning attacks. In contrast, black box optimization methods, which treat the model as an opaque function, relying solely on function evaluations to guide optimization, offer a promising alternative in scenarios where data access is restricted, adversarial risks are high, or overfitting is a concern. This paper introduces BBoxER, an evolutionary black-box method for LLM post-training that induces an information bottleneck via implicit compression of the training data. Leveraging the tractability of information flow, we provide non-vacuous generalization bounds and strong theoretical guarantees for privacy, robustness to data poisoning attacks, and extraction attacks. In experiments with LLMs, we demonstrate empirically that black-box optimization methods, despite the scalability and computational challenges inherent to black-box approaches, are able to learn, showing how a few iterations of BBoxER improve performance, generalize well on a benchmark of reasoning datasets, and are robust to membership inference attacks. This positions BBoxER as an attractive add-on on top of gradient-based optimization, offering suitability for deployment in restricted or privacy-sensitive environments while also providing non-vacuous generalization guarantees.
Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Abstract: Proxy optimization, where AI systems exploit evaluator weaknesses rather than improve intended objectives, threatens both reinforcement learning (reward hacking) and LLM alignment (evaluator gaming). We introduce the Evaluator Stress Test (EST), an invariance-based framework that detects proxy gaming by separating exploitable sensitivity (e.g., formatting artifacts, physics bugs) from content-driven improvements using controlled perturbations with semantic validity audits. We validate EST across both domains. In RL, across 15 environments and 5 algorithms (2,156 expert-annotated episodes), EST achieves 78.4% precision and 81.7% recall. In LLM alignment, across 4 tasks, 2 model scales, 2 training methods, and 2 judges (1,200 human-annotated instances), EST achieves 74.2% precision and 78.6% recall, with early warning signals that precede quality decline. Cross-domain analysis shows that proxy-true correlation tracking transfers directly between domains, while perturbation design requires domain adaptation. Closed-loop mitigation improves human win-rate by 8.3 points (LLM) and reduces hacking by 54.6% (RL). We release benchmarks for both domains: 2,156 RL episodes and 1,200 LLM instances.
Authors: Jongsoo Lee, Jangwon Kim, Jiseok Jeong, Soohee Han
Abstract: Real-world reinforcement learning applications are often hindered by delayed feedback from environments, which violates the Markov assumption and introduces significant challenges. Although numerous delay-compensating methods have been proposed for environments with constant delays, environments with random delays remain largely unexplored due to their inherent variability and unpredictability. In this study, we propose a simple yet robust agent for decision-making under random delays, termed the conservative agent, which reformulates the random-delay environment into its constant-delay equivalent. This transformation enables any state-of-the-art constant-delay method to be directly extended to the random-delay environments without modifying the algorithmic structure or sacrificing performance. We evaluate the conservative agent-based algorithm on continuous control tasks, and empirical results demonstrate that it significantly outperforms existing baseline algorithms in terms of asymptotic performance and sample efficiency.
Authors: Gnankan Landry Regis N'guessan
Abstract: Conventional deep learning models embed data in Euclidean space $\mathbb{R}^d$, a poor fit for strictly hierarchical objects such as taxa, word senses, or file systems. We introduce van der Put Neural Networks (v-PuNNs), the first architecture whose neurons are characteristic functions of p-adic balls in $\mathbb{Z}_p$. Under our Transparent Ultrametric Representation Learning (TURL) principle every weight is itself a p-adic number, giving exact subtree semantics. A new Finite Hierarchical Approximation Theorem shows that a depth-K v-PuNN with $\sum_{j=0}^{K-1}p^{\,j}$ neurons universally represents any K-level tree. Because gradients vanish in this discrete space, we propose Valuation-Adaptive Perturbation Optimization (VAPO), with a fast deterministic variant (HiPaN-DS) and a moment-based one (HiPaN / Adam-VAPO). On three canonical benchmarks our CPU-only implementation sets new state-of-the-art: WordNet nouns (52,427 leaves) 99.96% leaf accuracy in 16 min; GO molecular-function 96.9% leaf / 100% root in 50 s; NCBI Mammalia Spearman $\rho = -0.96$ with true taxonomic distance. The learned metric is perfectly ultrametric (zero triangle violations), and its fractal and information-theoretic properties are analyzed. Beyond classification we derive structural invariants for quantum systems (HiPaQ) and controllable generative codes for tabular data (Tab-HiPaN). v-PuNNs therefore bridge number theory and deep learning, offering exact, interpretable, and efficient models for hierarchical data.
Authors: Hongze Sun, Wuque Cai, Duo Chen, Quan Tang, Shifeng Mao, Jiayi He, Zhenxing Wang, Yan Cui, Dezhong Yao, Daqing Guo
Abstract: As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models require a substantial number of parameters and incur high computational costs, thus limiting their deployment in resource-constrained environments. To address these challenges, we propose combining synapse pruning with a synergistic learning-based compensation strategy to derive lightweight ST-based models. Specifically, two types of tailored pruning strategies are introduced to reduce redundancy in the weight matrices of ST blocks: an unstructured $\mathrm{L_{1}P}$ method to induce sparse representations, and a structured DSP method to induce low-rank representations. In addition, we propose an enhanced spiking neuron model, termed the synergistic leaky integrate-and-fire (sLIF) neuron, to effectively compensate for model pruning through synergistic learning between synaptic and intrinsic plasticity mechanisms. Extensive experiments on benchmark datasets demonstrate that the proposed methods significantly reduce model size and computational overhead while maintaining competitive performance. These results validate the effectiveness of the proposed pruning and compensation strategies in constructing efficient and high-performing ST-based models.
Authors: Bart van Merri\"enboer, Vincent Dumoulin, Jenny Hamer, Lauren Harrell, Andrea Burns, Tom Denton
Abstract: Perch is a performant pre-trained model for bioacoustics. It was trained in supervised fashion, providing both off-the-shelf classification scores for thousands of vocalizing species as well as strong embeddings for transfer learning. In this new release, Perch 2.0, we expand from training exclusively on avian species to a large multi-taxa dataset. The model is trained with self-distillation using a prototype-learning classifier as well as a new source-prediction training criterion. Perch 2.0 obtains state-of-the-art performance on the BirdSet and BEANS benchmarks. It also outperforms specialized marine models on marine transfer learning tasks, despite having almost no marine training data. We present hypotheses as to why fine-grained species classification is a particularly robust pre-training task for bioacoustics.
Authors: Thorsten Peinemann, Paula Arnold, Sebastian Berndt, Thomas Eisenbarth, Esfandiar Mohammadi
Abstract: Backdoor poisoning attacks are a threat to machine learning models trained on large data collected from untrusted sources; these attacks enable attackers to inject malicious behavior into the model that can be triggered by specially crafted inputs. Prior work has established bounds on the success of backdoor attacks and their impact on the benign learning task, however, an open question is what amount of poison data is needed for a successful backdoor attack. Typical attacks either use few samples but need much information about the data points, or need to poison many data points. In this paper, we formulate the one-poison hypothesis: An adversary with one poison sample and limited background knowledge can inject a backdoor with zero backdooring-error and without significantly impacting the benign learning task performance. Moreover, we prove the one-poison hypothesis for linear regression, linear classification, and 2-layer ReLU neural networks. For adversaries that utilize a direction unused by the clean data distribution for the poison sample, we prove for linear classification and linear regression that the resulting model is functionally equivalent to a model where the poison was excluded from training. We build on prior work on statistical backdoor learning to show that in all other cases, the impact on the benign learning task is still limited. We validate our theoretical results experimentally with realistic benchmark data sets.
Authors: Zhenpeng Su, Leiyu Pan, Xue Bai, Dening Liu, Guanting Dong, Jiaming Huang, Wenping Hu, Fuzheng Zhang, Kun Gai, Guorui Zhou
Abstract: We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks. Although there are already many excellent works related to inference models in the current community, there are still many problems with reproducing high-performance inference models due to incomplete disclosure of training details. This report provides an in-depth analysis of the reasoning model, covering the entire post-training workflow from data preparation and long Chain-of-Thought supervised fine-tuning (long CoT SFT) to reinforcement learning (RL), along with detailed ablation studies for each experimental component. For SFT data, our experiments show that a small number of high-quality data sources are more effective than a large number of diverse data sources, and that difficult samples can achieve better results without accuracy filtering. In addition, we investigate two key issues with current clipping mechanisms in RL: Clipping suppresses critical exploration signals and ignores suboptimal trajectories. To address these challenges, we propose Gradient-Preserving clipping Policy Optimization (GPPO) that gently backpropagates gradients from clipped tokens. GPPO not only enhances the model's exploration capacity but also improves its efficiency in learning from negative samples. Klear-Reasoner exhibits exceptional reasoning abilities in mathematics and programming, scoring 90.5% on AIME 2024, 83.2% on AIME 2025, 66.0% on LiveCodeBench V5 and 58.1% on LiveCodeBench V6.
Authors: Kaiwen Zuo, Zelin Liu, Raman Dutt, Ziyang Wang, Zhongtian Sun, Fan Mo, Pietro Li\`o
Abstract: Large Vision-Language Models (LVLMs) augmented with Retrieval-Augmented Generation (RAG) are increasingly employed in medical AI to enhance factual grounding through external clinical image-text retrieval. However, this reliance creates a significant attack surface. We propose MedThreatRAG, a novel multimodal poisoning framework that systematically probes vulnerabilities in medical RAG systems by injecting adversarial image-text pairs. A key innovation of our approach is the construction of a simulated semi-open attack environment, mimicking real-world medical systems that permit periodic knowledge base updates via user or pipeline contributions. Within this setting, we introduce and emphasize Cross-Modal Conflict Injection (CMCI), which embeds subtle semantic contradictions between medical images and their paired reports. These mismatches degrade retrieval and generation by disrupting cross-modal alignment while remaining sufficiently plausible to evade conventional filters. While basic textual and visual attacks are included for completeness, CMCI demonstrates the most severe degradation. Evaluations on IU-Xray and MIMIC-CXR QA tasks show that MedThreatRAG reduces answer F1 scores by up to 27.66% and lowers LLaVA-Med-1.5 F1 rates to as low as 51.36%. Our findings expose fundamental security gaps in clinical RAG systems and highlight the urgent need for threat-aware design and robust multimodal consistency checks. Finally, we conclude with a concise set of guidelines to inform the safe development of future multimodal medical RAG systems.
Authors: David Kurtenbach, Megan Manly, Zach Metzinger
Abstract: We apply deep learning techniques for anomaly detection to analyze activity of Russian-owned resident space objects (RSO) prior to the Ukraine invasion and assess the results for any findings that can be used as indications and warnings (I&W) of aggressive military behavior for future conflicts. Through analysis of anomalous activity, an understanding of possible tactics and procedures can be established to assess the existence of statistically significant changes in Russian RSO pattern of life/pattern of behavior (PoL/PoB) using publicly available two-line element (TLE) data. This research looks at statistical and deep learning approaches to assess anomalous activity. The deep learning methods assessed are isolation forest (IF), traditional autoencoder (AE), variational autoencoder (VAE), Kolmogorov Arnold Network (KAN), and a novel anchor-loss based autoencoder (Anchor AE). Each model is used to establish a baseline of on-orbit activity based on a five-year data sample. The primary investigation period focuses on the six months leading up to the invasion date of February 24, 2022. Additional analysis looks at RSO activity during an active combat period by sampling TLE data after the invasion date. The deep learning autoencoder models identify anomalies based on reconstruction errors that surpass a threshold sigma. To capture the nuance and unique characteristics of each RSO an individual model was trained for each observed space object. The research made an effort to prioritize explainability and interpretability of the model results thus each observation was assessed for anomalous behavior of the individual six orbital elements versus analyzing the input data as a single monolithic observation. The results demonstrate not only statistically significant anomalies of Russian RSO activity but also details anomalous findings to the individual orbital element.
Authors: Govind Menon, Tianmin Yu
Abstract: We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian submersion from the space of parameters to the space of observables. The foliation of the balanced manifold in the parameter space by group orbits is used to define and compute a Boltzmann entropy. We also show that the Riemannian geometry on the space of observables defined in [2] is obtained by Riemannian submersion of the balanced manifold. The main technical step is an explicit construction of an orthonormal basis for the tangent space of the balanced manifold using the theory of Jacobi matrices.
Authors: Jonas Schmidinger, Viacheslav Barkov, Sebastian Vogel, Martin Atzmueller, Gerard B M Heuvelink
Abstract: Machine learning and geostatistics are two fundamentally different frameworks for predicting and spatially mapping soil properties. Geostatistics leverages the spatial structure of soil properties, while machine learning captures the relationship between available environmental features and soil properties. We propose a hybrid framework that enriches ML with spatial context through engineering of 'spatial lag' features from ordinary kriging. We call this approach 'kriging prior regression' (KpR), as it follows the inverse logic of regression kriging. To evaluate this approach, we assessed both the point and probabilistic prediction performance of KpR, using the TabPFN model across six fieldscale datasets from LimeSoDa. These datasets included soil organic carbon, clay content, and pH, along with features derived from remote sensing and in-situ proximal soil sensing. KpR with TabPFN demonstrated reliable uncertainty estimates and more accurate predictions in comparison to several other spatial techniques (e.g., regression/residual kriging with TabPFN), as well as to established non-spatial machine learning algorithms (e.g., random forest). Most notably, it significantly improved the average R2 by around 30% compared to machine learning algorithms without spatial context. This improvement was due to the strong prediction performance of the TabPFN algorithm itself and the complementary spatial information provided by KpR features. TabPFN is particularly effective for prediction tasks with small sample sizes, common in precision agriculture, whereas KpR can compensate for weak relationships between sensing features and soil properties when proximal soil sensing data are limited. Hence, we conclude that KpR with TabPFN is a very robust and versatile modelling framework for digital soil mapping in precision agriculture.
Authors: Kuiye Ding, Fanda Fan, Chunyi Hou, Zheya Wang, Lei Wang, Zhengxin Yang, Jianfeng Zhan
Abstract: Multivariate time series forecasting is essential in domains such as finance, transportation, climate, and energy. However, existing patch-based methods typically adopt fixed-length segmentation, overlooking the heterogeneity of local temporal dynamics and the decoding heterogeneity of forecasting. Such designs lose details in information-dense regions, introduce redundancy in stable segments, and fail to capture the distinct complexities of short-term and long-term horizons. We propose TimeMosaic, a forecasting framework that aims to address temporal heterogeneity. TimeMosaic employs adaptive patch embedding to dynamically adjust granularity according to local information density, balancing motif reuse with structural clarity while preserving temporal continuity. In addition, it introduces segment-wise decoding that treats each prediction horizon as a related subtask and adapts to horizon-specific difficulty and information requirements, rather than applying a single uniform decoder. Extensive evaluations on benchmark datasets demonstrate that TimeMosaic delivers consistent improvements over existing methods, and our model trained on the large-scale corpus with 321 billion observations achieves performance competitive with state-of-the-art TSFMs.
Authors: Erkan Karabulut, Daniel Daza, Paul Groth, Victoria Degeler
Abstract: Association Rule Mining (ARM) aims to discover patterns between features in datasets in the form of propositional rules, supporting both knowledge discovery and interpretable machine learning in high-stakes decision-making. However, in high-dimensional settings, rule explosion and computational overhead render popular algorithmic approaches impractical without effective search space reduction, challenges that propagate to downstream tasks. Neurosymbolic methods, such as Aerial+, have recently been proposed to address the rule explosion in ARM. While they tackle the high dimensionality of the data, they also inherit limitations of neural networks, particularly reduced performance in low-data regimes. This paper makes three key contributions to association rule discovery in high-dimensional tabular data. First, we empirically show that Aerial+ scales one to two orders of magnitude better than state-of-the-art algorithmic and neurosymbolic baselines across five real-world datasets. Second, we introduce the novel problem of ARM in high-dimensional, low-data settings, such as gene expression data from the biomedicine domain with around 18k features and 50 samples. Third, we propose two fine-tuning approaches to Aerial+ using tabular foundation models. Our proposed approaches are shown to significantly improve rule quality on five real-world datasets, demonstrating their effectiveness in low-data, high-dimensional scenarios.
Authors: Houliang Zhou, Rong Zhou, Yangying Liu, Kanhao Zhao, Li Shen, Brian Y. Chen, Yu Zhang, Lifang He, Alzheimer's Disease Neuroimaging Initiative
Abstract: Identifying objective neuroimaging biomarkers to forecast Alzheimer's disease (AD) progression is crucial for timely intervention. However, this task remains challenging due to the complex dysfunctions in the spatio-temporal characteristics of underlying brain networks, which are often overlooked by existing methods. To address these limitations, we develop an interpretable spatio-temporal graph neural network framework to predict future AD progression, leveraging dual Stochastic Differential Equations (SDEs) to model the irregularly-sampled longitudinal functional magnetic resonance imaging (fMRI) data. We validate our approach on two independent cohorts, including the Open Access Series of Imaging Studies (OASIS-3) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our framework effectively learns sparse regional and connective importance probabilities, enabling the identification of key brain circuit abnormalities associated with disease progression. Notably, we detect the parahippocampal cortex, prefrontal cortex, and parietal lobule as salient regions, with significant disruptions in the ventral attention, dorsal attention, and default mode networks. These abnormalities correlate strongly with longitudinal AD-related clinical symptoms. Moreover, our interpretability strategy reveals both established and novel neural systems-level and sex-specific biomarkers, offering new insights into the neurobiological mechanisms underlying AD progression. Our findings highlight the potential of spatio-temporal graph-based learning for early, individualized prediction of AD progression, even in the context of irregularly-sampled longitudinal imaging data.
Authors: Xiangchen Song, Jiaqi Sun, Zijian Li, Yujia Zheng, Kun Zhang
Abstract: Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoencoders (SAEs) were developed to extract interpretable features from LLMs but lack temporal dependency modeling, instantaneous relation representation, and more importantly theoretical guarantees, undermining both the theoretical foundations and the practical confidence necessary for subsequent analyses. While causal representation learning (CRL) offers theoretically grounded approaches for uncovering latent concepts, existing methods cannot scale to LLMs' rich conceptual space due to inefficient computation. To bridge the gap, we introduce an identifiable temporal causal representation learning framework specifically designed for LLMs' high-dimensional concept space, capturing both time-delayed and instantaneous causal relations. Our approach provides theoretical guarantees and demonstrates efficacy on synthetic datasets scaled to match real-world complexity. By extending SAE techniques with our temporal causal framework, we successfully discover meaningful concept relationships in LLM activations. Our findings show that modeling both temporal and instantaneous conceptual relationships advances the interpretability of LLMs.
Authors: Liangjian Wen, Qun Dai, Jianzhuang Liu, Jiangtao Zheng, Yong Dai, Dongkai Wang, Zhao Kang, Jun Wang, Zenglin Xu, Jiang Duan
Abstract: In multimodal representation learning, synergistic interactions between modalities not only provide complementary information but also create unique outcomes through specific interaction patterns that no single modality could achieve alone. Existing methods may struggle to effectively capture the full spectrum of synergistic information, leading to suboptimal performance in tasks where such interactions are critical. This is particularly problematic because synergistic information constitutes the fundamental value proposition of multimodal representation. To address this challenge, we introduce InfMasking, a contrastive synergistic information extraction method designed to enhance synergistic information through an Infinite Masking strategy. InfMasking stochastically occludes most features from each modality during fusion, preserving only partial information to create representations with varied synergistic patterns. Unmasked fused representations are then aligned with masked ones through mutual information maximization to encode comprehensive synergistic information. This infinite masking strategy enables capturing richer interactions by exposing the model to diverse partial modality combinations during training. As computing mutual information estimates with infinite masking is computationally prohibitive, we derive an InfMasking loss to approximate this calculation. Through controlled experiments, we demonstrate that InfMasking effectively enhances synergistic information between modalities. In evaluations on large-scale real-world datasets, InfMasking achieves state-of-the-art performance across seven benchmarks. Code is released at https://github.com/brightest66/InfMasking.
Authors: Xing Han, Hsing-Huan Chung, Joydeep Ghosh, Paul Pu Liang, Suchi Saria
Abstract: Modern applications increasingly involve dozens of heterogeneous input streams, such as clinical sensors, wearables, imaging, and text, each with distinct measurement models, sampling rates, and noise characteristics. This \textit{massively multimodal} setting, where each sensor constitutes a separate modality, fundamentally differs from conventional multimodal learning focused on two or three modalities. As modality count grows, capturing their complex, time-varying dependencies becomes essential yet challenging. Mixture-of-Experts (MoE) architectures are naturally suited for this setting, their sparse routing mechanism enables efficient scaling across many modalities. Existing MoE architectures route tokens based on similarity alone, overlooking the rich temporal dependencies across modalities. We propose a framework that explicitly quantifies temporal dependencies between modality pairs across multiple time lags and uses these to guide MoE routing. A dependency-aware router dispatches tokens to specialized experts based on interaction type. This principled routing enables experts to learn generalizable dependency-processing skills. Experiments across healthcare, activity recognition, and affective computing benchmarks demonstrate substantial performance gains and interpretable routing patterns aligned with domain knowledge.
Authors: Xiang Zhang, Kun Wei, Xu Yang, Jiahua Li, Su Yan, Cheng Deng
Abstract: As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data. However, existing methods not only rely on the retained dataset to preserve model utility, but also suffer from cumulative catastrophic utility loss under continuous unlearning requests. To solve this dilemma, we propose a novel method, called Rotation Control Unlearning (RCU), which leverages the rotational salience weight of RCU to quantify and control the unlearning degree in the continuous unlearning process. The skew symmetric loss is designed to construct the existence of the cognitive rotation space, where the changes of rotational angle can simulate the continuous unlearning process. Furthermore, we design an orthogonal rotation axes regularization to enforce mutually perpendicular rotation directions for continuous unlearning requests, effectively minimizing interference and addressing cumulative catastrophic utility loss. Experiments on multiple datasets confirm that our method without retained dataset achieves SOTA performance.
Authors: Yihang Lu, Xianwei Meng, Enhong Chen
Abstract: Neural Forecasters (NFs) have become a cornerstone of Long-term Time Series Forecasting (LTSF). However, recent progress has been hampered by an overemphasis on architectural complexity at the expense of fundamental forecasting principles. In this work, we revisit the principles of LTSF. We begin by formulating a Variance Reduction Hypothesis (VRH), positing that generating and combining multiple forecasts is essential to reducing the inherent uncertainty of NFs. Guided by this, we propose Boosted Direct Output (BDO), a streamlined paradigm that synergistically hybridizes the causal structure of Auto-Regressive (AR) with the stability of Direct Output (DO), while implicitly realizing the principle of forecast combination within a single network. Furthermore, we address the critical validation-test generalization gap by employing parameter smoothing to stabilize optimization. Extensive experiments demonstrate that these trivial yet principled improvements enable a direct temporal MLP to outperform recent, complex state-of-the-art models in nearly all benchmarks, without relying on intricate inductive biases. Finally, we empirically verify our hypothesis, establishing a dynamic performance bound that highlights promising directions for future research. The code for review is available at: https://anonymous.4open.science/r/ReNF-A151.
Authors: K\"ur\c{s}at Tekb{\i}y{\i}k, G\"une\c{s} Karabulut Kurt, Antoine Lesage-Landry
Abstract: Unmanned aerial vehicle (UAV) communications demand accurate yet interpretable air-to-ground (A2G) channel models that can adapt to nonstationary propagation environments. While deterministic models offer interpretability and deep learning (DL) models provide accuracy, both approaches suffer from either rigidity or a lack of explainability. To bridge this gap, we propose the Physics-Inspired Kolmogorov-Arnold Network (PIKAN) that embeds physical principles (e.g., free-space path loss, two-ray reflections) into the learning process. Unlike physics-informed neural networks (PINNs), PIKAN is more flexible for applying physical information because it introduces them as flexible inductive biases. Thus, it enables a more flexible training process. Experiments on UAV A2G measurement data show that PIKAN achieves comparable accuracy to DL models while providing symbolic and explainable expressions aligned with propagation laws. Remarkably, PIKAN achieves this performance with only 232 parameters, making it up to 37 times lighter than multilayer perceptron (MLP) baselines with thousands of parameters, without sacrificing correlation with measurements and also providing symbolic expressions. These results highlight PIKAN as an efficient, interpretable, and scalable solution for UAV channel modelling in beyond-5G and 6G networks.
Authors: Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Abstract: We introduce Sequential-EDFL (Empirical Dynamic Formal Lift), which applies anytime-valid sequential testing to language model generation stopping. Our approach tracks information lift, defined as the log-likelihood ratio between the full model and deliberately weakened "skeleton" baselines, using self-normalized empirical-Bernstein e-processes that provide formal delta-level error control regardless of stopping time. This delta guarantee controls premature stopping when information lift is insufficient relative to the skeleton, and it does not imply delta control of factual incorrectness or hallucinations. We handle unknown centering through online mean estimation, combine multiple parameters via mixture e-processes, and support adaptive resets under distributional drift. On six benchmarks, Sequential-EDFL reduces generation length by 22 to 28 percent relative to sequential baselines while maintaining delta-level control with 12 percent computational overhead. We introduce automated skeletons (distilled submodels and randomized logits) and show robustness across skeleton families. Composing EDFL with a lightweight correctness gate (sentence boundaries plus a verifier) improves end-task correctness while preserving anytime-valid guarantees by only delaying stopping. Our certificates control information sufficiency, not factual correctness. Specifically, 10.9 percent of stopped sequences remain incorrect even with the gate (13.2 to 22.7 percent without it). EDFL serves as a first-stage filter that can reduce verification burden: when applied to stopped sequences, the gate validates 83 percent of stops, requiring full verification only for the remaining 17 percent, plus all non-stopped sequences. EDFL is not a standalone solution for safety-critical domains.
Authors: Wiktor Jan Hoffmann, Sonia Laguna, Moritz Vandenhirtz, Emanuele Palumbo, Julia E. Vogt
Abstract: Concept Bottleneck Models (CBMs) are interpretable models that predict the target variable through high-level human-understandable concepts, allowing users to intervene on mispredicted concepts to adjust the final output. While recent work has shown that modeling dependencies between concepts can improve CBM performance, especially under interventions, such approaches typically require retraining the entire model, which may be infeasible when access to the original data or compute is limited. In this paper, we introduce Post-hoc Stochastic Concept Bottleneck Models (PSCBMs), a lightweight method that augments any pre-trained CBM with a multivariate normal distribution over concepts by adding only a small covariance-prediction module, without retraining the backbone model. We propose two training strategies and show on real-world data that PSCBMs consistently match or improve both concept and target accuracy over standard CBMs at test time. Furthermore, we show that due to the modeling of concept dependencies, PSCBMs perform much better than CBMs under interventions, while remaining far more efficient than retraining a similar stochastic model from scratch.
Authors: Michael Y. Hu, Benjamin Van Durme, Jacob Andreas, Harsh Jhamtani
Abstract: Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness of such agents in environments where interaction is costly (for example, when they interact with humans or reset physical systems). While a number of existing LM agent architectures incorporate various mechanisms for experience storage and reflection, they make limited use of LMs' abilities to directly generate or reason about full counterfactual trajectories. We introduce ECHO (Experience Consolidation via Hindsight Optimization), a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents. ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts, effectively creating synthetic positive examples from unsuccessful interactions. Our approach consists of two components: a hindsight rule that uses the language model itself to identify relevant subgoals and generate optimized trajectories, and an update rule that maintains compressed trajectory representations in memory. We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation. Across both domains, ECHO outperforms vanilla language agent baselines by up to 80%; in XMiniGrid, it also outperforms a number of sophisticated agent architectures including Reflexion and AWM, demonstrating faster adaptation to novel environments through more effective utilization of past experiences.
Authors: Hongkai Zheng, Austin Wang, Zihui Wu, Zhengyu Huang, Ricardo Baptista, Yisong Yue
Abstract: Derivative-free Bayesian inversion is an important task in many science and engineering applications, particularly when computing the forward model derivative is computationally and practically challenging. In this paper, we introduce Blade, which can produce accurate and well-calibrated posteriors for Bayesian inversion using an ensemble of interacting particles. Blade leverages powerful data-driven priors based on diffusion models, and can handle nonlinear forward models that permit only black-box access (i.e., derivative-free). Theoretically, we establish a non-asymptotic convergence analysis to characterize the effects of forward model and prior estimation errors. Empirically, Blade achieves superior performance compared to existing derivative-free Bayesian inversion methods on various inverse problems, including challenging highly nonlinear fluid dynamics.
Authors: Omer Haq
Abstract: Modern probabilistic regressors often remain overconfident under distribution shift. We present Functional Distribution Networks (FDN), an input-conditioned distribution over network weights that induces predictive mixtures whose dispersion adapts to the input. FDN is trained with a beta-ELBO and Monte Carlo sampling. We further propose an evaluation protocol that cleanly separates interpolation from extrapolation and stresses OOD sanity checks (e.g., that predictive likelihood degrades under shift while in-distribution accuracy and calibration are maintained). On standard regression tasks, we benchmark against strong Bayesian, ensemble, dropout, and hypernetwork baselines under matched parameter and update budgets, and assess accuracy, calibration, and shift-awareness with standard diagnostics. Together, the framework and protocol aim to make OOD-aware, well-calibrated neural regression practical and modular.
Authors: Su Liu, Xin Hu, Shurong Wen, Chengyi Chen, Jiaqi Liu, Lanruo Wang, Jiexi Xu
Abstract: Physiologically Based Pharmacokinetic (PBPK) modeling is a key tool in drug development for predicting drug concentration dynamics across organs. Traditional PBPK approaches rely on ordinary differential equations with simplifying assumptions that limit their ability to capture nonlinear and system-level physiological interactions. In this work, we investigate data-driven PBPK modeling using deep learning. We implement two baseline architectures -- a multilayer perceptron (MLP) and a long short-term memory (LSTM) network -- and propose a Dynamic Graph Neural Network (Dynamic GNN) that explicitly models inter-organ interactions through recurrent message passing on a physiological graph. Experiments on a multi-organ pharmacokinetic dataset show that the Dynamic GNN achieves the lowest mean absolute percentage error (MAPE) of 15.7% among all models, demonstrating improved relative accuracy despite slightly higher absolute error compared to the MLP baseline. The model attains an R2 of 0.9342 with more stable error behavior and better captures inter-organ pharmacokinetic relationships. These results highlight the importance of structure-aware modeling for PBPK applications and demonstrate that the proposed Dynamic GNN offers a scalable, equation-free alternative for data-driven pharmacokinetic prediction.
Authors: Zhichao Wang
Abstract: I propose \textbf{G}roup-relative \textbf{I}mplicit \textbf{F}ine \textbf{T}uning (GIFT), a novel reinforcement learning framework for aligning LLMs. Instead of directly maximizing cumulative rewards like PPO or GRPO, GIFT minimizes the discrepancy between implicit and explicit reward models. It combines three key ideas: (1) the online multi-response generation and normalization of GRPO, (2) the implicit reward formulation of DPO, and (3) the implicit-explicit reward alignment principle of UNA. By jointly normalizing the implicit and explicit rewards, GIFT eliminates an otherwise intractable term that prevents effective use of implicit rewards. This normalization transforms the complex reward maximization objective into a simple mean squared error (MSE) loss between the normalized reward functions, converting a non-convex optimization problem into a convex, stable, and analytically differentiable formulation. Unlike offline methods such as DPO and UNA, GIFT remains on-policy and thus retains exploration capability. Compared to GRPO, it requires fewer hyperparameters, converges faster, and generalizes better with significantly reduced training overfitting. Empirically, GIFT achieves superior reasoning and alignment performance on mathematical benchmarks while remaining computationally efficient.
Authors: James Josep Perry, Pablo Garcia-Conde Ortiz, George Konstantinou, Cornelie Vergouwen, Edlyn Santha Kumaran, Morteza Moradi
Abstract: Health indicators (HIs) are central to diagnosing and prognosing the condition of aerospace composite structures, enabling efficient maintenance and operational safety. However, extracting reliable HIs remains challenging due to variability in material properties, stochastic damage evolution, and diverse damage modes. Manufacturing defects (e.g., disbonds) and in-service incidents (e.g., bird strikes) further complicate this process. This study presents a comprehensive data-driven framework that learns HIs via two learning approaches integrated with multi-domain signal processing. Because ground-truth HIs are unavailable, a semi-supervised and an unsupervised approach are proposed: (i) a diversity deep semi-supervised anomaly detection (Diversity-DeepSAD) approach augmented with continuous auxiliary labels used as hypothetical damage proxies, which overcomes the limitation of prior binary labels that only distinguish healthy and failed states while neglecting intermediate degradation, and (ii) a degradation-trend-constrained variational autoencoder (DTC-VAE), in which the monotonicity criterion is embedded via an explicit trend constraint. Guided waves with multiple excitation frequencies are used to monitor single-stiffener composite structures under fatigue loading. Time, frequency, and time-frequency representations are explored, and per-frequency HIs are fused via unsupervised ensemble learning to mitigate frequency dependence and reduce variance. Using fast Fourier transform features, the augmented Diversity-DeepSAD model achieved 81.6% performance, while DTC-VAE delivered the most consistent HIs with 92.3% performance, outperforming existing baselines.
Authors: Pedro P. Sanchez, Damian Machlanski, Steven McDonagh, Sotirios A. Tsaftaris
Abstract: Predicting causal structure from time series data is crucial for understanding complex phenomena in physiology, brain connectivity, climate dynamics, and socio-economic behaviour. Causal discovery in time series is hindered by the combinatorial complexity of identifying true causal relationships, especially as the number of variables and time points grow. A common approach to simplify the task is the so-called ordering-based methods. Traditional ordering methods inherently limit the representational capacity of the resulting model. In this work, we fix this issue by leveraging multiple valid causal orderings, instead of a single one as standard practice. We propose DOTS (Diffusion Ordered Temporal Structure), using diffusion-based causal discovery for temporal data. By integrating multiple orderings, DOTS effectively recovers the transitive closure of the underlying directed acyclic graph, mitigating spurious artifacts inherent in single-ordering approaches. We formalise the problem under standard assumptions such as stationarity and the additive noise model, and leverage score matching with diffusion processes to enable efficient Hessian estimation. Extensive experiments validate the approach. Empirical evaluations on synthetic and real-world datasets demonstrate that DOTS outperforms state-of-the-art baselines, offering a scalable and robust approach to temporal causal discovery. On synthetic benchmarks ($d{=}\!3-\!6$ variables, $T{=}200\!-\!5{,}000$ samples), DOTS improves mean window-graph $F1$ from $0.63$ (best baseline) to $0.81$. On the CausalTime real-world benchmark ($d{=}20\!-\!36$), while baselines remain the best on individual datasets, DOTS attains the highest average summary-graph $F1$ while halving runtime relative to graph-optimisation methods. These results establish DOTS as a scalable and accurate solution for temporal causal discovery.
Authors: Amir Noorizadegan, Sifan Wang, Leevan Ling, Juan P. Dominguez-Morales
Abstract: Kolmogorov-Arnold Networks (KANs), whose design is inspired-rather than dictated-by the Kolmogorov superposition theorem, have emerged as a structured alternative to MLPs. This review provides a systematic and comprehensive overview of the rapidly expanding KAN literature. The review is organized around three core themes: (i) clarifying the relationships between KANs and Kolmogorov superposition theory (KST), MLPs, and classical kernel methods; (ii) analyzing basis functions as a central design axis; and (iii) summarizing recent advances in accuracy, efficiency, regularization, and convergence. Finally, we provide a practical "Choose-Your-KAN" guide and outline open research challenges and future directions. The accompanying GitHub repository serves as a structured reference for ongoing KAN research.
Authors: Chenming Tang, Hsiu-Yuan Huang, Weijie Liu, Saiyong Yang, Yunfang Wu
Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of language models (LMs) recently. However, existing RLVR approaches merely train LMs based on their own generated on-policy responses and are constrained by the initial capability of LMs, thus prone to exploration stagnation, in which LMs fail to solve more training problems and cannot further learn from the training data. Some work tries to address this by leveraging off-policy solutions to training problems, but relies on external expert guidance that is limited in availability and scalability. In this work, we propose LTE (Learning to reason from Trial and Error), an approach that hints LMs with their previously self-made mistakes, not requiring any external expert guidance. Experiments validate the effectiveness of LTE, which outperforms the normal group relative policy optimization (GRPO) by 5.02 in Pass@1 and 9.96 in Pass@k on average across six mathematical reasoning benchmarks for Qwen3-8B-Base and even performs better than methods that require external gold solutions as guidance after aligning the experimental setup. Further analysis confirms that LTE successfully mitigates exploration stagnation and enhances both exploitation and exploration during training. Our code is available at https://anonymous.4open.science/r/Learning-from-Trial-and-Error.
URLs: https://anonymous.4open.science/r/Learning-from-Trial-and-Error.
Authors: Xinyuan Song, Ziye Ma
Abstract: In this paper we study how the choice of loss functions of non-convex optimization problems affects their robustness and optimization landscape, through the study of noisy matrix sensing. In traditional regression tasks, mean squared error (MSE) loss is a common choice, but it can be unreliable for non-Gaussian or heavy-tailed noise. To address this issue, we adopt a robust loss based on nonparametric regression, which uses a kernel-based estimate of the residual density and maximizes the estimated log-likelihood. This robust formulation coincides with the MSE loss under Gaussian errors but remains stable under more general settings. We further examine how this robust loss reshapes the optimization landscape by analyzing the upper-bound of restricted isometry property (RIP) constants for spurious local minima to disappear. Through theoretical and empirical analysis, we show that this new loss excels at handling large noise and remains robust across diverse noise distributions. This work offers initial insights into enhancing the robustness of machine learning tasks through simply changing the loss, guided by an intuitive and broadly applicable analytical framework.
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: Bin Wang, Boxiang Tao, Haifeng Jing, Hongbo Dou, Zijian Wang
Abstract: Model-based reinforcement learning (MBRL) typically relies on modeling environment dynamics for data efficiency. However, due to the accumulation of model errors over long-horizon rollouts, such methods often face challenges in maintaining modeling stability. To address this, we propose CtrlFlow, a trajectory-level synthetic method using conditional flow matching (CFM), which directly modeling the distribution of trajectories from initial states to high-return terminal states without explicitly modeling the environment transition function. Our method ensures optimal trajectory sampling by minimizing the control energy governed by the non-linear Controllability Gramian Matrix, while the generated diverse trajectory data significantly enhances the robustness and cross-task generalization of policy learning. In online settings, CtrlFlow demonstrates the better performance on common MuJoCo benchmark tasks than dynamics models and achieves superior sample efficiency compared to standard MBRL methods.
Authors: Xiaoyu Fan, Lin Guo, Ruizhen Jia, Yang Tian, Zhihao Yang, Weihao Li, Boxue Tian
Abstract: Artificial Intelligence (AI)-aided drug discovery is an active research field, yet AI models often exhibit poor accuracy in regression tasks for molecular property prediction, and perform catastrophically poorly for out-of-distribution (OOD) molecules. Here, we present MolRuleLoss, a substructure-substitution-rule-informed framework that improves the accuracy and generalizability of multiple molecular property regression models (MPRMs) such as GEM and UniMol for diverse molecular property prediction tasks. MolRuleLoss incorporates partial derivative constraints for substructure substitution rules (SSRs) into an MPRM's loss function. When using GEM models for predicting lipophilicity, water solubility, and solvation-free energy (using lipophilicity, ESOL, and freeSolv datasets from MoleculeNet), the root mean squared error (RMSE) values with and without MolRuleLoss were 0.587 vs. 0.660, 0.777 vs. 0.798, and 1.252 vs. 1.877, respectively, representing 2.6-33.3% performance improvements. We show that both the number and the quality of SSRs contribute to the magnitude of prediction accuracy gains obtained upon adding MolRuleLoss to an MPRM. MolRuleLoss improved the generalizability of MPRMs for "activity cliff" molecules in a lipophilicity prediction task and improved the generalizability of MPRMs for OOD molecules in a melting point prediction task. In a molecular weight prediction task for OOD molecules, MolRuleLoss reduced the RMSE value of a GEM model from 29.507 to 0.007. We also provide a formal demonstration that the upper bound of the variation for property change of SSRs is positively correlated with an MPRM's error. Together, we show that using the MolRuleLoss framework as a bolt-on boosts the prediction accuracy and generalizability of multiple MPRMs, supporting diverse applications in areas like cheminformatics and AI-aided drug discovery.
Authors: Alexander W. Goodall, Edwin Hamel-De le Court, Francesco Belardinelli
Abstract: Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we leverage new results from off-policy evaluation; it has recently been shown that well-designed behaviour policies can be used to collect off-policy data for provably lower variance return estimates. This result is surprising as it means collecting data on-policy is not variance optimal. We extend this key insight to the online reinforcement learning setting, where both policy evaluation and improvement are interleaved to learn optimal policies. Off-policy RL has been well studied (e.g., IMPALA), with correct and truncated importance weighted samples for de-biasing and managing variance appropriately. Generally these approaches are concerned with reconciling data collected from multiple workers in parallel, while the policy is updated asynchronously, mismatch between the workers and policy is corrected in a mathematically sound way. Here we consider only one worker - the behaviour policy, which is used to collect data for policy improvement, with provably lower variance return estimates. In our experiments we extend two policy-gradient methods with this regime, demonstrating better sample efficiency and performance over a diverse set of environments.
Authors: Dahao Tang, Nan Yang, Yanli Li, Zhiyu Zhu, Zhibo Jin, Dong Yuan
Abstract: Selecting an appropriate look-back horizon remains a fundamental challenge in time series forecasting (TSF), particularly in the federated learning scenarios where data is decentralized, heterogeneous, and often non-independent. While recent work has explored horizon selection by preserving forecasting-relevant information in an intrinsic space, these approaches are primarily restricted to centralized and independently distributed settings. This paper presents a principled framework for adaptive horizon selection in federated time series forecasting through an intrinsic space formulation. We introduce a synthetic data generator (SDG) that captures essential temporal structures in client data, including autoregressive dependencies, seasonality, and trend, while incorporating client-specific heterogeneity. Building on this model, we define a transformation that maps time series windows into an intrinsic representation space with well-defined geometric and statistical properties. We then derive a decomposition of the forecasting loss into a Bayesian term, which reflects irreducible uncertainty, and an approximation term, which accounts for finite-sample effects and limited model capacity. Our analysis shows that while increasing the look-back horizon improves the identifiability of deterministic patterns, it also increases approximation error due to higher model complexity and reduced sample efficiency. We prove that the total forecasting loss is minimized at the smallest horizon where the irreducible loss starts to saturate, while the approximation loss continues to rise. This work provides a rigorous theoretical foundation for adaptive horizon selection for time series forecasting in federated learning.
Authors: Nguyen Duc Minh Quang, Chang Liu, Huy-Trung Nguyen, Shuangyang Li, Derrick Wing Kwan Ng, Wei Xiang
Abstract: Low-altitude wireless networks (LAWN) are rapidly expanding with the growing deployment of unmanned aerial vehicles (UAVs) for logistics, surveillance, and emergency response. Reliable connectivity remains a critical yet challenging task due to three-dimensional (3D) mobility, time-varying user density, and limited power budgets. The transmit power of base stations (BSs) fluctuates dynamically according to user locations and traffic demands, leading to a highly non-stationary 3D radio environment. Radio maps (RMs) have emerged as an effective means to characterize spatial power distributions and support radio-aware network optimization. However, most existing works construct static or offline RMs, overlooking real-time power variations and spatio-temporal dependencies in multi-UAV networks. To overcome this limitation, we propose a 3D dynamic radio map (3D-DRM) framework that learns and predicts the spatio-temporal evolution of received power. Specially, a Vision Transformer (ViT) encoder extracts high-dimensional spatial representations from 3D RMs, while a Transformer-based module models sequential dependencies to predict future power distributions. Experiments unveil that 3D-DRM accurately captures fast-varying power dynamics and substantially outperforms baseline models in both RM reconstruction and short-term prediction.
Authors: Chungpa Lee, Thomas Zeng, Jongwon Jeong, Jy-yong Sohn, Kangwook Lee
Abstract: Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of LLM judgments induce bias in naive evaluation scores. We propose a simple plug-in framework that corrects this bias and constructs confidence intervals accounting for uncertainty from both the test dataset and a human-evaluated calibration dataset, enabling statistically sound and practical LLM-based evaluation. Building on this framework, we introduce an adaptive calibration strategy for constructing the calibration dataset to reduce uncertainty in the estimated score. Notably, we characterize the regimes in which LLM-based evaluation within our framework produces more reliable estimates than fully human evaluation. Moreover, our framework is more robust to distribution shift between the test and calibration datasets than existing approaches.
Authors: Alex Ning, Vainateya Rangaraju, Yen-Ling Kuo
Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in Transformer-based language models through dimensionality reduction. We capture layerwise activations at multiple points within Transformer blocks and enable systematic analysis through Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). We demonstrate experiments on GPT-2 and LLaMa models, where we uncover interesting geometric patterns in latent space. Notably, we identify a clear separation between attention and MLP component outputs across intermediate layers, a pattern not documented in prior work to our knowledge. We also characterize the high norm of latent states at the initial sequence position and visualize the layerwise evolution of latent states. Additionally, we demonstrate the high-dimensional helical structure of GPT-2's positional embeddings and the sequence-wise geometric patterns in LLaMa. We make our code available at https://github.com/Vainateya/Feature_Geometry_Visualization.
URLs: https://github.com/Vainateya/Feature_Geometry_Visualization.
Authors: Alper Y{\i}ld{\i}r{\i}m, \.Ibrahim Y\"uceda\u{g}
Abstract: Conventional deep learning paradigms rely on metabolically expensive magnitude-based representations, rendering them fundamentally incompatible with passive photonic hardware. We introduce PRISM, a sequence modeling architecture that bridges high-level reasoning and physical constraints by enforcing an Iso-Energetic (Unity Gain) principle, compelling the network to encode semantic information exclusively in the phase angle. Validated on the WMT14 translation benchmark, PRISM achieves a 0.799 COMET score, demonstrating that phase-based reasoning competes with standard Transformers (0.821) and functionally matches unconstrained spectral baselines like FNet (0.805), despite enforcing strict energy constraints and requiring 11.5% fewer parameters. Furthermore, to verify hardware feasibility, we simulate a Holographic Backpropagation mechanism on a noisy, 4-bit optical correlator. Ablation studies reveal a substantial performance gain (48.4% vs. 62.4%) over a frozen baseline, proving that the proposed phase-steering mechanism actively optimizes physical parameters under strict energy constraints. These results establish an existence proof that ultra-low-power, passive optical hardware can support high-level linguistic intelligence without sacrificing representational capacity.
Authors: Bei Zhou, Cesare Corrado, Shuang Qian, Maximilian Balmus, Angela W. C. Lee, Cristobal Rodero, Caroline Roney, Marco J. W. Gotte, Luuk H. G. A. Hopman, Mengyun Qiao, Steven Niederer
Abstract: Learning biophysically accurate solution operators for cardiac electrophysiology is fundamentally challenged by geometric variability across patient-specific heart anatomies. Most existing neural operator approaches are limited to structured or weakly deformed domains, restricting their applicability to realistic atrial and ventricular geometries. Here, we introduce a unified operator-learning framework that projects inputs and outputs onto a standardised anatomical coordinate system, decoupling electrophysiological dynamics from mesh topology. This formulation enables geometry-independent learning while preserving physiologically meaningful spatial organisation, and allows predictions to be interpolated back onto patient-specific geometries for anatomical interpretation. To support large-scale training within the framework, we develop a GPU-accelerated electrophysiology solver and generate over 300,000 high-fidelity simulations across diverse patient-specific left atrial geometries with varied pacing and conduction properties. Within this anatomical coordinate domain, we design a neural operator to predict full-field local activation time maps, achieving a mean absolute error of 5.1 ms and an inference time of 0.12 ms per sample, outperforming existing operator learning and convolutional baselines. We further validate the framework on ventricular geometries, demonstrating robust generalisation beyond the atrial setting. Together, this framework establishes a scalable foundation for fast, geometry-invariant cardiac electrophysiology modelling, with potential relevance for real-time and population-scale clinical workflows.
Authors: Xinyue Ai, Yutong He, Albert Gu, Ruslan Salakhutdinov, J Zico Kolter, Nicholas Matthew Boffi, Max Simchowitz
Abstract: Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet paradoxically, some of today's best generative models -- diffusion and flow-based models -- still require hundreds to thousands of neural function evaluations (NFEs) to compute a single likelihood. While recent distillation methods have successfully accelerated sampling to just a few steps, they achieve this at the cost of likelihood tractability: existing approaches either abandon likelihood computation entirely or still require expensive integration over full trajectories. We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude. Our key insight is that in continuous normalizing flows, the coupled ODEs for sampling and likelihood are computed from a shared underlying velocity field, allowing us to jointly distill both the sampling trajectory and cumulative divergence using a single model. F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head. Experiments demonstrate F2D2's capability of achieving accurate log-likelihood with few-step evaluations while maintaining high sample quality, solving a long-standing computational bottleneck in flow-based generative models. As an application of our approach, we propose a lightweight self-guidance method that enables a 2-step MeanFlow to outperform a 1024 step flow matching model with only a single additional backward NFE.
Authors: Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
Abstract: Popular offline reinforcement learning (RL) methods rely on conservatism, either by penalizing out-of-dataset actions or by restricting rollout horizons. In this work, we question the universality of this principle and instead revisit a complementary one: a Bayesian perspective. Rather than enforcing conservatism, the Bayesian approach tackles epistemic uncertainty in offline data by modeling a posterior distribution over plausible world models and training a history-dependent agent to maximize expected rewards, enabling test-time generalization. We first illustrate, in a bandit setting, that Bayesianism excels on low-quality datasets where conservatism fails. We then scale this principle to realistic tasks and show that long-horizon planning is critical for reducing value overestimation once conservatism is removed. To make this feasible, we introduce key design choices for performing and learning from long-horizon rollouts while controlling compounding errors. These yield our algorithm, NEUBAY, grounded in the neutral Bayesian principle. On D4RL and NeoRL benchmarks, NEUBAY generally matches or surpasses leading conservative algorithms, achieving new state-of-the-art on 7 datasets. Notably, it succeeds with rollout horizons of several hundred steps, contrary to dominant practice. Finally, we characterize datasets by quality and coverage, showing when NEUBAY is preferable to conservative methods. Together, we argue NEUBAY lays the foundation for a new practical direction in offline and model-based RL.
Authors: Hiroki Hasegawa, Yukihiko Okada
Abstract: This study proposes Interaction Tensor SHAP (IT-SHAP), a tensor algebraic formulation of the Shapley Taylor Interaction Index (STII) that makes its computational structure explicit. STII extends the Shapley value to higher order interactions, but its exponential combinatorial definition makes direct computation intractable at scale. We reformulate STII as a linear transformation acting on a value function and derive an explicit algebraic representation of its weight tensor. This weight tensor is shown to possess a multilinear structure induced by discrete finite difference operators. When the value function admits a Tensor Train representation, higher order interaction indices can be computed in the parallel complexity class NC squared. In contrast, under general tensor network representations without structural assumptions, the same computation is proven to be P sharp hard. The main contributions are threefold. First, we establish an exact Tensor Train representation of the STII weight tensor. Second, we develop a parallelizable evaluation algorithm with explicit complexity bounds under the Tensor Train assumption. Third, we prove that computational intractability is unavoidable in the absence of such structure. These results demonstrate that the computational difficulty of higher order interaction analysis is determined by the underlying algebraic representation rather than by the interaction index itself, providing a theoretical foundation for scalable interpretation of high dimensional models.
Authors: Kesheng Chen, Yamin Hu, Zhenqian Zhu, Wenjian Luo, Yiya Diao
Abstract: Constructing a Pareto set is pivotal for navigating the capability--efficiency trade-offs in Large Language Models (LLMs). However, existing merging techniques remain inadequate for this task. Coarse-grained, model-level methods yield only a sparse set of suboptimal solutions, while fine-grained, layer-wise approaches suffer from the curse of dimensionality, rendering the search space computationally intractable. To resolve this dichotomy, we propose Structural Importance Prior Bayesian Model Merging (SIP-BMM), a framework that automatically constructs the LLM Pareto set. SIP-BMM renders high-dimensional layer-wise search tractable by introducing an importance-aware Sparse Axis-Aligned Subspace Bayesian Optimization (SAASBO) strategy. By leveraging a structural importance prior derived from task-vector differences, our method guides SAASBO to automatically identify critical layers, thereby dramatically reducing the effective dimensionality without sacrificing the granularity of full-model control. The entire process is automated within an evolutionary loop driven by the Log-Noisy Expected Hypervolume Improvement ($q$NEHVI) acquisition function. Experiments demonstrate that SIP-BMM discovers a stronger and denser Pareto front than competitive baselines, enabling agile model selection tailored to diverse operational constraints. Code is available at: https://github.com/MiLab-HITSZ/2026-SIPBMM.
Authors: Yizhou Zhang
Abstract: Neural scaling laws and double-descent phenomena suggest that deep-network training obeys a simple macroscopic structure despite highly nonlinear optimization dynamics. We derive such structure directly from gradient descent in function space. For mean-squared error loss, the training error evolves as $\dot e_t=-M(t)e_t$ with $M(t)=J_{\theta(t)}J_{\theta(t)}^{\!*}$, a time-dependent self-adjoint operator induced by the network Jacobian. Using Kato perturbation theory, we obtain an exact system of coupled modewise ODEs in the instantaneous eigenbasis of $M(t)$. To extract macroscopic behavior, we introduce a logarithmic spectral-shell coarse-graining and track quadratic error energy across shells. Microscopic interactions within each shell cancel identically at the energy level, so shell energies evolve only through dissipation and external inter-shell interactions. We formalize this via a \emph{renormalizable shell-dynamics} assumption, under which cumulative microscopic effects reduce to a controlled net flux across shell boundaries. Assuming an effective power-law spectral transport in a relevant resolution range, the shell dynamics admits a self-similar solution with a moving resolution frontier and explicit scaling exponents. This framework explains neural scaling laws and double descent, and unifies lazy (NTK-like) training and feature learning as two limits of the same spectral-shell dynamics.
Authors: Zhijie Zhong, Zhiwen Yu, Pengyu Li, Jianming Lv, C. L. Philip Chen, Min Chen
Abstract: Radio path loss prediction (RPP) is critical for optimizing 5G networks and enabling IoT, smart city, and similar applications. However, current deep learning-based RPP methods lack proactive environmental modeling, struggle with realistic multi-transmitter scenarios, and generalize poorly under distribution shifts, particularly when training/testing environments differ in building density or transmitter configurations. This paper identifies three key issues: (1) passive environmental modeling that overlooks transmitters and key environmental features; (2) overemphasis on single-transmitter scenarios despite real-world multi-transmitter prevalence; (3) excessive focus on in-distribution performance while neglecting distribution shift challenges. To address these, we propose PathFinder, a novel architecture that actively models buildings and transmitters via disentangled feature encoding and integrates Mask-Guided Low-rank Attention to independently focus on receiver and building regions. We also introduce a Transmitter-Oriented Mixup strategy for robust training and a new benchmark, single-to-multi-transmitter RPP (S2MT-RPP), tailored to evaluate extrapolation performance (multi-transmitter testing after single-transmitter training). Experimental results show PathFinder outperforms state-of-the-art methods significantly, especially in challenging multi-transmitter scenarios. Our code and project site are publicly available at: https://emorzz1g.github.io/PathFinder/.
Authors: Zhengxu Yan, Han Li, Yuming Feng
Abstract: The accelerating pace of scientific publication makes it difficult to identify truly original research among incremental work. We propose a framework for estimating the conceptual novelty of research papers by combining semantic representation learning with retrieval-based comparison against prior literature. We model novelty as both a binary classification task (novel vs. non-novel) and a pairwise ranking task (comparative novelty), enabling absolute and relative assessments. Experiments benchmark three model scales, ranging from compact domain-specific encoders to a zero-shot frontier model. Results show that fine-tuned lightweight models outperform larger zero-shot models despite their smaller parameter count, indicating that task-specific supervision matters more than scale for conceptual novelty estimation. We further deploy the best-performing model as an online system for public interaction and real-time novelty scoring.
Authors: Liam Collins, Bhuvesh Kumar, Clark Mingxuan Ju, Tong Zhao, Donald Loveland, Leonardo Neves, Neil Shah
Abstract: Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.
Authors: Yizhou Zhang
Abstract: Empirical power--law scaling has been widely observed across modern deep learning systems, yet its theoretical origins and scope of validity remain incompletely understood. The Generalized Resolution--Shell Dynamics (GRSD) framework models learning as spectral energy transport across logarithmic resolution shells, providing a coarse--grained dynamical description of training. Within GRSD, power--law scaling corresponds to a particularly simple renormalized shell dynamics; however, such behavior is not automatic and requires additional structural properties of the learning process. In this work, we identify a set of sufficient conditions under which the GRSD shell dynamics admits a renormalizable coarse--grained description. These conditions constrain the learning configuration at multiple levels, including boundedness of gradient propagation in the computation graph, weak functional incoherence at initialization, controlled Jacobian evolution along training, and log--shift invariance of renormalized shell couplings. We further show that power--law scaling does not follow from renormalizability alone, but instead arises as a rigidity consequence: once log--shift invariance is combined with the intrinsic time--rescaling covariance of gradient flow, the renormalized GRSD velocity field is forced into a power--law form.
Authors: Wenlong Tang
Abstract: This study proposes a multi-agent language framework that enables continual strategy evolution without fine-tuning the language model's parameters. The core idea is to liberate the latent vectors of abstract concepts from traditional static semantic representations, allowing them to be continuously updated through environmental interaction and reinforcement feedback. We construct a dual-loop architecture: the behavior loop adjusts action preferences based on environmental rewards, while the language loop updates the external latent vectors by reflecting on the semantic embeddings of generated text. Together, these mechanisms allow agents to develop stable and disentangled strategic styles over long-horizon multi-round interactions. Experiments show that agents' latent spaces exhibit clear convergence trajectories under reflection-driven updates, along with structured shifts at critical moments. Moreover, the system demonstrates an emergent ability to implicitly infer and continually adapt to emotional agents, even without shared rewards. These results indicate that, without modifying model parameters, an external latent space can provide language agents with a low-cost, scalable, and interpretable form of abstract strategic representation.
Authors: Zachary Izzo, Iain Melvin
Abstract: We study the problem of subgroup discovery for survival analysis, where the goal is to find an interpretable subset of the data on which a Cox model is highly accurate. Our work is the first to study this particular subgroup problem, for which we make several contributions. Subgroup discovery methods generally require a "quality function" in order to sift through and select the most advantageous subgroups. We first examine why existing natural choices for quality functions are insufficient to solve the subgroup discovery problem for the Cox model. To address the shortcomings of existing metrics, we introduce two technical innovations: the *expected prediction entropy (EPE)*, a novel metric for evaluating survival models which predict a hazard function; and the *conditional rank statistics (CRS)*, a statistical object which quantifies the deviation of an individual point to the distribution of survival times in an existing subgroup. We study the EPE and CRS theoretically and show that they can solve many of the problems with existing metrics. We introduce a total of eight algorithms for the Cox subgroup discovery problem. The main algorithm is able to take advantage of both the EPE and the CRS, allowing us to give theoretical correctness results for this algorithm in a well-specified setting. We evaluate all of the proposed methods empirically on both synthetic and real data. The experiments confirm our theory, showing that our contributions allow for the recovery of a ground-truth subgroup in well-specified cases, as well as leading to better model fit compared to naively fitting the Cox model to the whole dataset in practical settings. Lastly, we conduct a case study on jet engine simulation data from NASA. The discovered subgroups uncover known nonlinearities/homogeneity in the data, and which suggest design choices which have been mirrored in practice.
Authors: Gnankan Landry Regis N'guessan
Abstract: Standard neural network architectures employ fixed activation functions (ReLU, tanh, sigmoid) that are poorly suited for approximating functions with singular or fractional power behavior, a structure that arises ubiquitously in physics, including boundary layers, fracture mechanics, and corner singularities. We introduce M\"untz-Sz\'asz Networks (MSN), a novel architecture that replaces fixed smooth activations with learnable fractional power bases grounded in classical approximation theory. Each MSN edge computes $\phi(x) = \sum_k a_k |x|^{\mu_k} + \sum_k b_k \mathrm{sign}(x)|x|^{\lambda_k}$, where the exponents $\{\mu_k, \lambda_k\}$ are learned alongside the coefficients. We prove that MSN inherits universal approximation from the M\"untz-Sz\'asz theorem and establish novel approximation rates: for functions of the form $|x|^\alpha$, MSN achieves error $\mathcal{O}(|\mu - \alpha|^2)$ with a single learned exponent, whereas standard MLPs require $\mathcal{O}(\epsilon^{-1/\alpha})$ neurons for comparable accuracy. On supervised regression with singular target functions, MSN achieves 5-8x lower error than MLPs with 10x fewer parameters. Physics-informed neural networks (PINNs) represent a particularly demanding application for singular function approximation; on PINN benchmarks including a singular ODE and stiff boundary-layer problems, MSN achieves 3-6x improvement while learning interpretable exponents that match the known solution structure. Our results demonstrate that theory-guided architectural design can yield dramatic improvements for scientifically-motivated function classes.
Authors: Jiacheng Li, Jianchao Tan, Zhidong Yang, Feiye Huo, Yerui Sun, Yuchen Xie, Xunliang Cai
Abstract: Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method. However, its linear adaptation process limits its expressive power. This means there is a gap between the expressive power of linear training and non-linear training. To bridge this gap, we propose AFA-LoRA, a novel training strategy that brings non-linear expressivity to LoRA while maintaining its seamless mergeability. Our key innovation is an annealed activation function that transitions from a non-linear to a linear transformation during training, allowing the adapter to initially adopt stronger representational capabilities before converging to a mergeable linear form. We implement our method on supervised fine-tuning, reinforcement learning, and speculative decoding. The results show that AFA-LoRA reduces the performance gap between LoRA and full-parameter training. This work enables a more powerful and practical paradigm of parameter-efficient adaptation.
Authors: Shuai Chen, Yang Song, Chen Wang, Ziran Wang
Abstract: Electronic nose (E-nose) systems face two interconnected challenges in open-set gas recognition: feature distribution shift caused by signal drift and decision boundary failure induced by unknown gas interference. Existing methods predominantly rely on Euclidean distance or conventional classifiers, failing to account for anisotropic feature distributions and dynamic signal intensity variations. To address these issues, this study proposes the Spherical Normalization coupled Mahalanobis (SNM) module, a universal post-processing module for open-set gas recognition. First, it achieves geometric decoupling through cascaded batch and L2 normalization, projecting features onto a unit hypersphere to eliminate signal intensity fluctuations. Second, it utilizes Mahalanobis distance to construct adaptive ellipsoidal decision boundaries that conform to the anisotropic feature geometry. The architecture-agnostic SNM-Module seamlessly integrates with mainstream backbones including Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Transformer. Experiments on the public Vergara dataset demonstrate that the Transformer+SNM configuration achieves near-theoretical-limit performance in discriminating among multiple target gases, with an AUROC of 0.9977 and an unknown gas detection rate of 99.57% at 5% false positive rate, significantly outperforming state-of-the-art methods with a 3.0% AUROC improvement and 91.0% standard deviation reduction compared to Class Anchor Clustering (CAC). The module maintains exceptional robustness across five sensor positions, with standard deviations below 0.0028. This work effectively addresses the critical challenge of simultaneously achieving high accuracy and high stability in open-set gas recognition, providing solid support for industrial E-nose deployment.
Authors: Qianyi Chen, Bo Li
Abstract: While conformal prediction provides robust marginal coverage guarantees, achieving reliable conditional coverage for specific inputs remains challenging. Although exact distribution-free conditional coverage is impossible with finite samples, recent work has focused on improving the conditional coverage of standard conformal procedures. Distinct from approaches that target relaxed notions of conditional coverage, we directly minimize the mean squared error of conditional coverage by refining the quantile regression components that underpin many conformal methods. Leveraging a Taylor expansion, we derive a sharp surrogate objective for quantile regression: a density-weighted pinball loss, where the weights are given by the conditional density of the conformity score evaluated at the true quantile. We propose a three-headed quantile network that estimates these weights via finite differences using auxiliary quantile levels at \(1-\alpha \pm \delta\), subsequently fine-tuning the central quantile by optimizing the weighted loss. We provide a theoretical analysis with exact non-asymptotic guarantees characterizing the resulting excess risk. Extensive experiments on diverse high-dimensional real-world datasets demonstrate remarkable improvements in conditional coverage performance.
Authors: Rodrigo Pereira David
Abstract: Laplace approximations are among the simplest and most practical methods for approximate Bayesian inference in neural networks, yet their Euclidean formulation struggles with the highly anisotropic, curved loss surfaces and large symmetry groups that characterize modern deep models. Recent work has proposed Riemannian and geometric Gaussian approximations to adapt to this structure. Building on these ideas, we introduce the Tubular Riemannian Laplace (TRL) approximation. TRL explicitly models the posterior as a probabilistic tube that follows a low-loss valley induced by functional symmetries, using a Fisher/Gauss-Newton metric to separate prior-dominated tangential uncertainty from data-dominated transverse uncertainty. We interpret TRL as a scalable reparametrised Gaussian approximation that utilizes implicit curvature estimates to operate in high-dimensional parameter spaces. Our empirical evaluation on ResNet-18 (CIFAR-10 and CIFAR-100) demonstrates that TRL achieves excellent calibration, matching or exceeding the reliability of Deep Ensembles (in terms of ECE) while requiring only a fraction (1/5) of the training cost. TRL effectively bridges the gap between single-model efficiency and ensemble-grade reliability.
Authors: Hyunjun Kim
Abstract: Causal discovery from observational data remains fundamentally limited by identifiability constraints. Recent work has explored leveraging Large Language Models (LLMs) as sources of prior causal knowledge, but existing approaches rely on heuristic integration that lacks theoretical grounding. We introduce HOLOGRAPH, a framework that formalizes LLM-guided causal discovery through sheaf theory--representing local causal beliefs as sections of a presheaf over variable subsets. Our key insight is that coherent global causal structure corresponds to the existence of a global section, while topological obstructions manifest as non-vanishing sheaf cohomology. We propose the Algebraic Latent Projection to handle hidden confounders and Natural Gradient Descent on the belief manifold for principled optimization. Experiments on synthetic and real-world benchmarks demonstrate that HOLOGRAPH provides rigorous mathematical foundations while achieving competitive performance on causal discovery tasks with 50-100 variables. Our sheaf-theoretic analysis reveals that while Identity, Transitivity, and Gluing axioms are satisfied to numerical precision (<10^{-6}), the Locality axiom fails for larger graphs, suggesting fundamental non-local coupling in latent variable projections. Code is available at [https://github.com/hyunjun1121/holograph](https://github.com/hyunjun1121/holograph).
URLs: https://github.com/hyunjun1121/holograph](https://github.com/hyunjun1121/holograph).
Authors: Xingwei Qu, Shaowen Wang, Zihao Huang, Kai Hua, Fan Yin, Rui-Jie Zhu, Jundong Zhou, Qiyang Min, Zihao Wang, Yizhi Li, Tianyu Zhang, He Xing, Zheng Zhang, Yuxuan Song, Tianyu Zheng, Zhiyuan Zeng, Chenghua Lin, Ge Zhang, Wenhao Huang
Abstract: Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating computation to semantically critical transitions. We propose $\textbf{Dynamic Large Concept Models (DLCM)}$, a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts computation from tokens to a compressed concept space where reasoning is more efficient. DLCM discovers variable-length concepts end-to-end without relying on predefined linguistic units. Hierarchical compression fundamentally changes scaling behavior. We introduce the first $\textbf{compression-aware scaling law}$, which disentangles token-level capacity, concept-level reasoning capacity, and compression ratio, enabling principled compute allocation under fixed FLOPs. To stably train this heterogeneous architecture, we further develop a $\textbf{decoupled $\mu$P parametrization}$ that supports zero-shot hyperparameter transfer across widths and compression regimes. At a practical setting ($R=4$, corresponding to an average of four tokens per concept), DLCM reallocates roughly one-third of inference compute into a higher-capacity reasoning backbone, achieving a $\textbf{+2.69$\%$ average improvement}$ across 12 zero-shot benchmarks under matched inference FLOPs.
Authors: Malikussaid, Septian Caesar Floresko, Ade Romadhony, Isman Kurniawan, Warih Maharani, Hilal Hudan Nuha
Abstract: Lipophilicity (logP) prediction remains central to drug discovery, yet linear regression models for this task frequently violate statistical assumptions in ways that invalidate their reported performance metrics. We analyzed 426,850 bioactive molecules from a rigorously curated intersection of PubChem, ChEMBL, and eMolecules databases, revealing severe heteroskedasticity in linear models predicting computed logP values (XLOGP3): residual variance increases 4.2-fold in lipophilic regions (logP greater than 5) compared to balanced regions (logP 2 to 4). Classical remediation strategies (Weighted Least Squares and Box-Cox transformation) failed to resolve this violation (Breusch-Pagan p-value less than 0.0001 for all variants). Tree-based ensemble methods (Random Forest R-squared of 0.764, XGBoost R-squared of 0.765) proved inherently robust to heteroskedasticity while delivering superior predictive performance. SHAP analysis resolved a critical multicollinearity paradox: despite a weak bivariate correlation of 0.146, molecular weight emerged as the single most important predictor (mean absolute SHAP value of 0.573), with its effect suppressed in simple correlations by confounding with topological polar surface area (TPSA). These findings demonstrate that standard linear models face fundamental challenges for computed lipophilicity prediction and provide a principled framework for interpreting ensemble models in QSAR applications.
Authors: Nikhil Chandak, Shashwat Goel, Ameya Prabhu, Moritz Hardt, Jonas Geiping
Abstract: High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. To scale up training data, we synthesize novel forecasting questions from global events reported in daily news, using a fully automated, careful curation recipe. We train the Qwen3 thinking models on our dataset, OpenForesight. To prevent leakage of future information during training and evaluation, we use an offline news corpus, both for data generation and retrieval in our forecasting system. Guided by a small validation set, we show the benefits of retrieval, and an improved reward function for reinforcement learning (RL). Once we obtain our final forecasting system, we perform held-out testing between May to August 2025. Our specialized model, OpenForecaster 8B, matches much larger proprietary models, with our training improving the accuracy, calibration, and consistency of predictions. We find calibration improvements from forecasting training generalize across popular benchmarks. We open-source all our models, code, and data to make research on language model forecasting broadly accessible.
Authors: Erin Carson, Xinye Chen
Abstract: We propose a reinforcement learning (RL) framework for adaptive precision tuning of linear solvers, and can be extended to general algorithms. The framework is formulated as a contextual bandit problem and solved using incremental action-value estimation with a discretized state space to select optimal precision configurations for computational steps, balancing precision and computational efficiency. To verify its effectiveness, we apply the framework to iterative refinement for solving linear systems $Ax = b$. In this application, our approach dynamically chooses precisions based on calculated features from the system. In detail, a Q-table maps discretized features (e.g., approximate condition number and matrix norm)to actions (chosen precision configurations for specific steps), optimized via an epsilon-greedy strategy to maximize a multi-objective reward balancing accuracy and computational cost. Empirical results demonstrate effective precision selection, reducing computational cost while maintaining accuracy comparable to double-precision baselines. The framework generalizes to diverse out-of-sample data and offers insight into utilizing RL precision selection for other numerical algorithms, advancing mixed-precision numerical methods in scientific computing. To the best of our knowledge, this is the first work on precision autotuning with RL and verified on unseen datasets.
Authors: Nathan TeBlunthuis, Benjamin Mako Hill, Aaron Halfaker
Abstract: Online community moderators often rely on social signals such as whether or not a user has an account or a profile page as clues that users may cause problems. Reliance on these clues can lead to "overprofiling'' bias when moderators focus on these signals but overlook the misbehavior of others. We propose that algorithmic flagging systems deployed to improve the efficiency of moderation work can also make moderation actions more fair to these users by reducing reliance on social signals and making norm violations by everyone else more visible. We analyze moderator behavior in Wikipedia as mediated by RCFilters, a system which displays social signals and algorithmic flags, and estimate the causal effect of being flagged on moderator actions. We show that algorithmically flagged edits are reverted more often, especially those by established editors with positive social signals, and that flagging decreases the likelihood that moderation actions will be undone. Our results suggest that algorithmic flagging systems can lead to increased fairness in some contexts but that the relationship is complex and contingent.
Authors: Zhuangyan Fang, Ruiqi Zhao, Yue Liu, Yangbo He
Abstract: Pairwise causal background knowledge about the existence or absence of causal edges and paths is frequently encountered in observational studies. Such constraints allow the shared directed and undirected edges in the constrained subclass of Markov equivalent DAGs to be represented as a causal maximally partially directed acyclic graph (MPDAG). In this paper, we first provide a sound and complete graphical characterization of causal MPDAGs and introduce a minimal representation of a causal MPDAG. Then, we give a unified representation for three types of pairwise causal background knowledge, including direct, ancestral and non-ancestral causal knowledge, by introducing a novel concept called direct causal clause (DCC). Using DCCs, we study the consistency and equivalence of pairwise causal background knowledge and show that any pairwise causal background knowledge set can be uniquely and equivalently decomposed into the causal MPDAG representing the refined Markov equivalence class and a minimal residual set of DCCs. Polynomial-time algorithms are also provided for checking consistency and equivalence, as well as for finding the decomposed MPDAG and the residual DCCs. Finally, with pairwise causal background knowledge, we prove a sufficient and necessary condition to identify causal effects and surprisingly find that the identifiability of causal effects only depends on the decomposed MPDAG. We also develop a local IDA-type algorithm to estimate the possible values of an unidentifiable effect. Simulations suggest that pairwise causal background knowledge can significantly improve the identifiability of causal effects.
Authors: Zhiwei Wang, Fa Zhang, Cong Zheng, Xianghong Hu, Mingxuan Cai, Can Yang
Abstract: In various practical situations, matrix factorization methods suffer from poor data quality, such as high data sparsity and low signal-to-noise ratio (SNR). Here, we consider a matrix factorization problem by utilizing auxiliary information, which is massively available in real-world applications, to overcome the challenges caused by poor data quality. Unlike existing methods that mainly rely on simple linear models to combine auxiliary information with the main data matrix, we propose to integrate gradient boosted trees in the probabilistic matrix factorization framework to effectively leverage auxiliary information (MFAI). Thus, MFAI naturally inherits several salient features of gradient boosted trees, such as the capability of flexibly modeling nonlinear relationships and robustness to irrelevant features and missing values in auxiliary information. The parameters in MFAI can be automatically determined under the empirical Bayes framework, making it adaptive to the utilization of auxiliary information and immune to overfitting. Moreover, MFAI is computationally efficient and scalable to large datasets by exploiting variational inference. We demonstrate the advantages of MFAI through comprehensive numerical results from simulation studies and real data analyses. Our approach is implemented in the R package mfair available at https://github.com/YangLabHKUST/mfair.
Authors: Gopi Krishna Jha, Anthony Thomas, Nilesh Jain, Sameh Gobriel, Tajana Rosing, Ravi Iyer
Abstract: Deep learning-based recommendation systems (e.g., DLRMs) are widely used AI models to provide high-quality personalized recommendations. Training data used for modern recommendation systems commonly includes categorical features taking on tens-of-millions of possible distinct values. These categorical tokens are typically assigned learned vector representations, that are stored in large embedding tables, on the order of 100s of GB. Storing and accessing these tables represent a substantial burden in commercial deployments. Our work proposes MEM-REC, a novel alternative representation approach for embedding tables. MEM-REC leverages bloom filters and hashing methods to encode categorical features using two cache-friendly embedding tables. The first table (token embedding) contains raw embeddings (i.e. learned vector representation), and the second table (weight embedding), which is much smaller, contains weights to scale these raw embeddings to provide better discriminative capability to each data point. We provide a detailed architecture, design and analysis of MEM-REC addressing trade-offs in accuracy and computation requirements, in comparison with state-of-the-art techniques. We show that MEM-REC can not only maintain the recommendation quality and significantly reduce the memory footprint for commercial scale recommendation models but can also improve the embedding latency. In particular, based on our results, MEM-REC compresses the MLPerf CriteoTB benchmark DLRM model size by 2900x and performs up to 3.4x faster embeddings while achieving the same AUC as that of the full uncompressed model.
Authors: Yiqiang Yi, Xu Wan, Yatao Bian, Le Ou-Yang, Peilin Zhao
Abstract: Predicting the docking between proteins and ligands is a crucial and challenging task for drug discovery. However, traditional docking methods mainly rely on scoring functions, and deep learning-based docking approaches usually neglect the 3D spatial information of proteins and ligands, as well as the graph-level features of ligands, which limits their performance. To address these limitations, we propose an equivariant transformer neural network for protein-ligand docking pose prediction. Our approach involves the fusion of ligand graph-level features by feature processing, followed by the learning of ligand and protein representations using our proposed TAMformer module. Additionally, we employ an iterative optimization approach based on the predicted distance matrix to generate refined ligand poses. The experimental results on real datasets show that our model can achieve state-of-the-art performance.
Authors: Eric Petermann, Peter Bossew, Joachim Kemski, Valeria Gruber, Nils Suhr, Bernd Hoffmann
Abstract: Accurate knowledge of indoor radon concentration is crucial for assessing radon-related health effects or identifying radon-prone areas. Indoor radon concentration at the national scale is usually estimated on the basis of extensive measurement campaigns. However, characteristics of the sampled households often differ from the characteristics of the target population owing to the large number of relevant factors that control the indoor radon concentration, such as the availability of geogenic radon or floor level. We propose a model-based approach that allows a more realistic estimation of indoor radon distribution with a higher spatial resolution than a purely data-based approach. A modeling approach was used by applying a quantile regression forest to estimate the probability distribution function of indoor radon for each floor level of each residential building in Germany. Based on the estimated probability distribution function,a probabilistic Monte Carlo sampling technique was applied, enabling the combination and population weighting of floor-level predictions. In this way,the uncertainty of the individual predictions is effectively propagated into the estimate of variability at the aggregated level. The results show an approximate lognormal distribution of indoor radon in dwellings in Germany with an arithmetic mean of 63 Bq/m3, a geometric mean of 41 Bq/m3, and a 95th percentile of 180 Bq/m3. The exceedance probabilities for 100 and 300 Bq/m3 are 12.5% (10.5 million people affected) and 2.2 % (1.9 million people affected), respectively. The advantages of our approach are that it yields a) an accurate estimation of indoor radon concentration even if the survey is not fully representative with respect to floor level and radon concentration in soil, and b) an estimate of the indoor radon distribution with a much higher spatial resolution than basic descriptive statistics.
Authors: Mohammad Amin Sharifi Kolarijani, Peyman Mohajerin Esfahani
Abstract: Recent control algorithms for Markov decision processes (MDPs) have been designed using an implicit analogy with well-established optimization algorithms. In this paper, we adopt the quasi-Newton method (QNM) from convex optimization to introduce a novel control algorithm coined as quasi-policy iteration (QPI). In particular, QPI is based on a novel approximation of the ``Hessian'' matrix in the policy iteration algorithm, which exploits two linear structural constraints specific to MDPs and allows for the incorporation of prior information on the transition probability kernel. While the proposed algorithm has the same computational complexity as value iteration, it exhibits an empirical convergence behavior similar to that of QNM with a low sensitivity to the discount factor.
Authors: Stefana Anita, Gabriel Turinici
Abstract: Although Multi Armed Bandit (MAB) on one hand and the policy gradient approach on the other hand are among the most used frameworks of Reinforcement Learning, the theoretical properties of the policy gradient algorithm used for MAB have not been given enough attention. We investigate in this work the convergence of such a procedure for the situation when a $L2$ regularization term is present jointly with the 'softmax' parametrization. We prove convergence under appropriate technical hypotheses and test numerically the procedure including situations beyond the theoretical setting. The tests show that a time dependent regularized procedure can improve over the canonical approach especially when the initial guess is far from the solution.
Authors: Joachim Bona-Pellissier (MaLGA), Fran\c{c}ois Malgouyres (IMT), Fran\c{c}ois Bachoc (LPP)
Abstract: Neural networks with a large number of parameters often do not overfit, owing to implicit regularization that favors \lq good\rq{} networks. Other related and puzzling phenomena include properties of flat minima, saddle-to-saddle dynamics, and neuron alignment. To investigate these phenomena, we study the local geometry of deep ReLU neural networks. We show that, for a fixed architecture, as the weights vary, the image of a sample $X$ forms a set whose local dimension changes. The parameter space is partitioned into regions where this local dimension remains constant. The local dimension is invariant under the natural symmetries of ReLU networks (i.e., positive rescalings and neuron permutations). We establish then that the network's geometry induces a regularization, with the local dimension serving as a key measure of regularity. Moreover, we relate the local dimension to a new notion of flatness of minima and to saddle-to-saddle dynamics. For shallow networks, we also show that the local dimension is connected to the number of linear regions perceived by $X$, offering insight into the effects of regularization. This is further supported by experiments and linked to neuron alignment. Our analysis offers, for the first time, a simple and unified geometric explanation that applies to all learning contexts for these phenomena, which are usually studied in isolation. Finally, we explore the practical computation of the local dimension and present experiments on the MNIST dataset, which highlight geometry-induced regularization in this setting.
Authors: Pengzhan Jin
Abstract: We point out that (continuous or discontinuous) piecewise linear functions on a convex polytope mesh can be represented by two-hidden-layer ReLU neural networks in a weak sense. In addition, the numbers of neurons of the two hidden layers required to weakly represent are accurately given based on the numbers of polytopes and hyperplanes involved in this mesh. The results naturally hold for constant and linear finite element functions. Such weak representation establishes a bridge between two-hidden-layer ReLU neural networks and finite element functions, and leads to a perspective for analyzing approximation capability of ReLU neural networks in $L^p$ norm via finite element functions. Moreover, we discuss the strict representation for tensor finite element functions via the recent tensor neural networks.
Authors: Huajie Qian, Donghao Ying, Henry Lam, Wotao Yin
Abstract: Ensemble learning is a popular technique to improve the accuracy of machine learning models. It traditionally hinges on the rationale that aggregating multiple weak models can lead to better models with lower variance and hence higher stability, especially for discontinuous base learners. In this paper, we provide a new perspective on ensembling. By selecting the most frequently generated model from the base learner when repeatedly applied to subsamples, we can attain exponentially decaying tails for the excess risk, even if the base learner suffers from slow (i.e., polynomial) decay rates. This tail enhancement power of ensembling applies to base learners that have reasonable predictive power to begin with and is stronger than variance reduction in the sense of exhibiting rate improvement. We demonstrate how our ensemble methods can substantially improve out-of-sample performances in a range of numerical examples involving heavy-tailed data or intrinsically slow rates.
Authors: Hai-Vy Nguyen, Fabrice Gamboa, Sixin Zhang, Reda Chhaibi, Serge Gratton, Thierry Giaccone
Abstract: Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two complementary objectives. First, we introduce a loss function applied at the penultimate layer that explicitly enforces intra-class compactness and increases the margin to analytically defined decision boundaries. This enhances feature discriminativeness and class separability for clean data. Second, we propose a class-wise feature alignment mechanism that brings noisy data clusters closer to their clean counterparts. Furthermore, we provide a theoretical analysis demonstrating that improving feature stability under additive Gaussian noise implicitly reduces the curvature of the softmax loss landscape in input space, as measured by Hessian eigenvalues.This thus naturally enhances robustness without explicit curvature penalties. Conversely, we also theoretically show that lower curvatures lead to more robust models. We validate the effectiveness of our method on standard benchmarks and our custom dataset. Our approach significantly reinforces model robustness to various perturbations while maintaining high accuracy on clean data, advancing the understanding and practice of noise-robust deep learning.
Authors: Xuan Son Nguyen, Shuo Yang, Aymeric Histace
Abstract: Deep neural networks (DNNs) on Riemannian manifolds have garnered increasing interest in various applied areas. For instance, DNNs on spherical and hyperbolic manifolds have been designed to solve a wide range of computer vision and nature language processing tasks. One of the key factors that contribute to the success of these networks is that spherical and hyperbolic manifolds have the rich algebraic structures of gyrogroups and gyrovector spaces. This enables principled and effective generalizations of the most successful DNNs to these manifolds. Recently, some works have shown that many concepts in the theory of gyrogroups and gyrovector spaces can also be generalized to matrix manifolds such as Symmetric Positive Definite (SPD) and Grassmann manifolds. As a result, some building blocks for SPD and Grassmann neural networks, e.g., isometric models and multinomial logistic regression (MLR) can be derived in a way that is fully analogous to their spherical and hyperbolic counterparts. Building upon these works, we design fully-connected (FC) and convolutional layers for SPD neural networks. We also develop MLR on Symmetric Positive Semi-definite (SPSD) manifolds, and propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective. We demonstrate the effectiveness of the proposed approach in the human action recognition and node classification tasks.
Authors: Yi-Cheng Lin, Tzu-Quan Lin, Hsi-Che Lin, Andy T. Liu, Hung-yi Lee
Abstract: Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where algorithms potentially amplify disparate properties between social groups present in the data used for training. Bias in SSL models can perpetuate injustice by automating discriminatory patterns and reinforcing inequitable systems. This work reveals that prevalent SSL models inadvertently acquire biased associations. We probe how various factors, such as model architecture, size, and training methodologies, influence the propagation of social bias within these models. Finally, we explore the efficacy of debiasing SSL models through regularization techniques, specifically via model compression. Our findings reveal that employing techniques such as row-pruning and training wider, shallower models can effectively mitigate social bias within SSL model.
Authors: Jiung Lee, Hongseok Namkoong, Yibo Zeng
Abstract: To leverage prediction models to make optimal scheduling decisions in service systems, we must understand how predictive errors impact congestion due to externalities on the delay of other jobs. Motivated by applications where prediction models interact with human servers (e.g., content moderation), we consider a large queueing system comprising of many single server queues where the class of a job is estimated using a prediction model. By characterizing the impact of mispredictions on congestion cost in heavy traffic, we design an index-based policy that incorporates the predicted class information in a near-optimal manner. Our theoretical results guide the design of predictive models by providing a simple model selection procedure with downstream queueing performance as a central concern, and offer novel insights on how to design queueing systems with AI-based triage. We illustrate our framework on a content moderation task based on real online comments, where we construct toxicity classifiers by finetuning large language models.
Authors: Jafar Abbaszadeh Chekan, Cedric Langbort
Abstract: We propose a computationally efficient algorithm that achieves anytime regret of order $\mathcal{O}(\sqrt{t})$, with explicit dependence on the system dimensions and on the solution of the Discrete Algebraic Riccati Equation (DARE). Our approach builds on the SDP-based framework of \cite{cohen2019learning}, using an appropriately tuned regularization and a sufficiently accurate initial estimate to construct confidence ellipsoids for control design. A carefully designed input-perturbation mechanism is incorporated to ensure anytime performance. We develop two variants of the algorithm. The first enforces a notion of strong sequential stability, requiring each policy to be stabilizing and successive policies to remain close. However, enforcing this notion results in a suboptimal regret scaling. The second removes the sequential-stability requirement and instead requires only that each generated policy be stabilizing. Closed-loop stability is then preserved through a dwell-time-inspired policy-update rule, adapting ideas from switched-systems control to carefully balance exploration and exploitation. This class of algorithms also addresses key shortcomings of most existing approaches including certainty-equivalence-based methods which typically guarantee stability only in the Lyapunov sense and lack explicit uniform high-probability bounds on the state trajectory expressed in system-theoretic terms. Our analysis explicitly characterizes the trade-off between state amplification and regret, and shows that partially relaxing the sequential-stability requirement yields optimal regret. Finally, our method eliminates the need for any a priori bound on the norm of the DARE solution, an assumption required by all existing computationally efficient optimism in the face of uncertainty (OFU) based algorithms, and thereby removes the reliance of regret guarantees on such external inputs.
Authors: Haoran Zhan, Yingcun Xia
Abstract: Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that the test error curve of neural networks decreases monotonically as model size grows and eventually converges to a non-zero constant. This work aims to explain the theoretical mechanism underlying this tail behavior and study the statistical consistency of deep overparameterized neural networks in many different learning tasks including regression and classification. Firstly, we prove that as the number of parameters increases, the approximation error decreases monotonically, while explicit or implicit regularization (e.g., weight decay) keeps the generalization error existing but bounded. Consequently, the overall error curve eventually converges to a constant determined by the bounded generalization error and the optimization error. Secondly, we prove that deep overparameterized neural networks are statistical consistency across multiple learning tasks if regularization technique is used. Our theoretical findings coincide with numerical experiments and provide a perspective for understanding the generalization behavior of overparameterized neural networks.
Authors: Deeksha M. Shama, Archana Venkataraman
Abstract: Deep learning is advancing EEG processing for automated epileptic seizure detection and onset zone localization, yet its performance relies heavily on high-quality annotated training data. However, scalp EEG is susceptible to high noise levels, which in turn leads to imprecise annotations of the seizure timing and characteristics. This "label noise" presents a significant challenge in model training and generalization. In this paper, we introduce Bayesian UncertaiNty-aware Deep Learning (BUNDL), a novel algorithm that informs a deep learning model of label ambiguities, thereby enhancing the robustness of seizure detection systems. By integrating domain knowledge into an underlying Bayesian framework, we derive a novel KL-divergence-based loss function that capitalizes on uncertainty to better learn seizure characteristics from scalp EEG. Thus, BUNDL offers a straightforward and model-agnostic method for training deep neural networks with noisy training labels that does not add any parameters to existing architectures. Additionally, we explore the impact of improved detection system on the task of automated onset zone localization. We validate BUNDL using a comprehensive simulated EEG dataset and two publicly available datasets collected by Temple University Hospital (TUH) and Boston Children's Hospital (CHB-MIT). Results show that BUNDL consistently identifies noisy labels and improves the robustness of three base models under various label noise conditions. We also evaluate cross-site generalizability and quantify computational cost of all methods. Ultimately, BUNDL presents as a reliable method that can be seamlessly integrated with existing deep models used in clinical practice, enabling the training of trustworthy models for epilepsy evaluation.
Authors: Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
Abstract: Transformers have revolutionized Computer Vision (CV) through self-attention mechanisms. However, their complexity makes latent token representations difficult to interpret. We introduce ULTra, a framework for interpreting Transformer embeddings and uncovering meaningful semantic patterns within them. ULTra enables unsupervised semantic segmentation using pre-trained models without requiring fine-tuning. Additionally, we propose a self-supervised training approach that refines segmentation performance by learning an external transformation matrix without modifying the underlying model. Our method achieves state-of-the-art performance in unsupervised semantic segmentation, outperforming existing segmentation methods. Furthermore, we validate ULTra for model interpretation on both synthetic and real-world scenarios, including Object Selection and interpretable text summarization using LLMs, demonstrating its broad applicability in explaining the semantic structure of latent token representations.
Authors: Qiao Liu, Wing Hung Wong
Abstract: Causal inference in observational studies with high-dimensional covariates presents significant challenges. We introduce CausalBGM, an AI-powered Bayesian generative modeling approach that captures the causal relationship among covariates, treatment, and outcome. The core innovation is to estimate the individual treatment effect (ITE) by learning the individual-specific distribution of a low-dimensional latent feature set (e.g., latent confounders) that drives changes in both treatment and outcome. This individualized posterior representation yields estimates of the individual treatment effect (ITE) together with well-calibrated posterior intervals while mitigating confounding effect. CausalBGM is fitted through an iterative algorithm to update the model parameters and the latent features until convergence. This framework leverages the power of AI to capture complex dependencies among variables while adhering to the Bayesian principles. Extensive experiments demonstrate that CausalBGM consistently outperforms state-of-the-art methods, particularly in scenarios with high-dimensional covariates and large-scale datasets. By addressing key limitations of existing methods, CausalBGM emerges as a robust and promising framework for advancing causal inference in a wide range of modern applications. The code for CausalBGM is available at https://github.com/liuq-lab/bayesgm. The tutorial for CausalBGM is available at https://causalbgm.readthedocs.io.
URLs: https://github.com/liuq-lab/bayesgm., https://causalbgm.readthedocs.io.
Authors: Hao Wang, Zhichao Chen, Licheng Pan, Xiaoyu Jiang, Yichen Song, Qunshan He, Xinggao Liu
Abstract: The process monitoring task is characterized by stringent demands for accuracy and efficiency. Current transformer-based methods, characterized by self-attention for temporal fusion, exhibit limitations in accurately understanding the semantic context and efficiently processing monitoring logs, rendering them inadequate for process monitoring. To address these limitations, we introduce DeepFilter, which revises the self-attention mechanism to improve both accuracy and efficiency. As a straightforward yet versatile approach, DeepFilter provides an instrumental baseline for practitioners in process monitoring, whether initiating new projects or enhancing existing capabilities.
Authors: DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, J. L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y. X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Zhen Zhang
Abstract: General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labeled reasoning trajectories. The proposed RL framework facilitates the emergent development of advanced reasoning patterns, such as self-reflection, verification, and dynamic strategy adaptation. Consequently, the trained model achieves superior performance on verifiable tasks such as mathematics, coding competitions, and STEM fields, surpassing its counterparts trained via conventional supervised learning on human demonstrations. Moreover, the emergent reasoning patterns exhibited by these large-scale models can be systematically harnessed to guide and enhance the reasoning capabilities of smaller models.
Authors: Adriana Valentina Costache, Silviu Florin Gheorghe, Eduard Gabriel Poesina, Paul Irofti, Radu Tudor Ionescu
Abstract: The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e.~the distribution of the test data changes over time, which hinders the application of conventional ML models. One domain where the distribution shift naturally occurs is text classification, since people always find new topics to discuss. To this end, we survey research articles studying open-set text classification and related tasks. We divide the methods in this area based on the constraints that define the kind of distribution shift and the corresponding problem formulation, i.e.~learning with the Universum, zero-shot learning, and open-set learning. We next discuss the predominant mitigation approaches for each problem setup. Finally, we identify several future work directions, aiming to push the boundaries beyond the state of the art. Interestingly, we find that continual learning can solve many of the issues caused by the shifting class distribution. We maintain a list of relevant papers at https://github.com/Eduard6421/Open-Set-Survey.
Authors: Michele Fiori, Davide Mor, Gabriele Civitarese, Claudio Bettini
Abstract: Sensor-based Human Activity Recognition (HAR) in smart home environments is crucial for several applications, especially in the healthcare domain. The majority of the existing approaches leverage deep learning models. While these approaches are effective, the rationale behind their outputs is opaque. Recently, eXplainable Artificial Intelligence (XAI) approaches emerged to provide intuitive explanations to the output of HAR models. To the best of our knowledge, these approaches leverage classic deep models like CNNs or RNNs. Recently, Graph Neural Networks (GNNs) proved to be effective for sensor-based HAR. However, existing approaches are not designed with explainability in mind. In this work, we propose the first explainable Graph Neural Network explicitly designed for smart home HAR. Our results on two public datasets show that this approach provides better explanations than state-of-the-art methods while also slightly improving the recognition rate.
Authors: Gopi Krishna Jha, Sameh Gobriel, Liubov Talamanova, Nilesh Jain
Abstract: Key-value (KV) caching has emerged as a crucial optimization technique for accelerating inference in large language models (LLMs). By allowing the attention operation to scale linearly rather than quadratically with the total sequence length, KV caching significantly enhances generation throughput. However, due to large context lengths in the modern LLMs, the memory footprint of the KV is a huge bottleneck for model deployment directly impacting the model's batch size, hindering its ability to deliver high-throughput. Existing research addresses this challenge using several techniques, such as discarding low-attention tokens, quantization, and matrix approximation which typically lead to a negative impact on the model accuracy. In this paper, We propose KVCrush technology which can be combined with many KV compression technologies to improve the model accuracy at a much smaller memory. KVCrush provides an alternate representation scheme for key-value states, along with a low-overhead token pruning algorithm that accounts for the token distribution in the KV cache, which in turn allows for a a smaller footprint while maintaining the accuracy of the model. Based on our results, KVCrush reduces LongBench KV Cache size by 4x with less than 1% accuracy drop and achieves state-of-the-art average accuracy with minimal overhead, incurring less than 0.5% total inference latency. KVCrush not only outperforms the accuracy of state-of-the-art importance-based token retention schemes but is also compatible with typical practical LLM deployments using KV cache paging schemes such as vLLM and mixed precision quantization.
Authors: Jirui Yang, Zheyu Lin, Zhihui Lu, Yinggui Wang, Lei Wang, Tao Wei, Qiang Duan, Xin Du, Shuhan Yang
Abstract: Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores inference-time defenses, existing methods rely on static interventions on intermediate representations, which often degrade generation quality and impair adherence to task instructions, reducing system usability in EI settings. We propose a dynamic defense framework. For each EI inference request, we dynamically construct a task-specific safety-semantic subspace, project its hidden state to the most relevant direction, and apply SLERP rotation for adaptive safety control. At comparable defense success rates, our method preserves generation quality, improves usability, reduces tuning cost, and strengthens robustness in EI scenarios.
Authors: Luyang Fang, Xiaowei Yu, Jiazhang Cai, Yongkai Chen, Shushan Wu, Zhengliang Liu, Zhenyuan Yang, Haoran Lu, Xilin Gong, Yufang Liu, Terry Ma, Wei Ruan, Ali Abbasi, Jing Zhang, Tao Wang, Ehsan Latif, Weihang You, Hanqi Jiang, Wei Liu, Wei Zhang, Soheil Kolouri, Xiaoming Zhai, Dajiang Zhu, Wenxuan Zhong, Tianming Liu, Ping Ma
Abstract: The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary paradigms: Knowledge Distillation (KD) and Dataset Distillation (DD), both aimed at compressing LLMs while preserving their advanced reasoning capabilities and linguistic diversity. We first examine key methodologies in KD, such as task-specific alignment, rationale-based training, and multi-teacher frameworks, alongside DD techniques that synthesize compact, high-impact datasets through optimization-based gradient matching, latent space regularization, and generative synthesis. Building on these foundations, we explore how integrating KD and DD can produce more effective and scalable compression strategies. Together, these approaches address persistent challenges in model scalability, architectural heterogeneity, and the preservation of emergent LLM abilities. We further highlight applications across domains such as healthcare and education, where distillation enables efficient deployment without sacrificing performance. Despite substantial progress, open challenges remain in preserving emergent reasoning and linguistic diversity, enabling efficient adaptation to continually evolving teacher models and datasets, and establishing comprehensive evaluation protocols. By synthesizing methodological innovations, theoretical foundations, and practical insights, our survey charts a path toward sustainable, resource-efficient LLMs through the tighter integration of KD and DD principles.
Authors: Danial Ramezani, Tai Dinh
Abstract: Fantasy football is a billion-dollar industry with millions of participants. Under a fixed budget, managers select squads to maximize future Fantasy Premier League (FPL) points. This study formulates lineup selection as data-driven optimization and develops deterministic and robust mixed-integer linear programs that choose the starting eleven, bench, and captain under budget, formation, and club-quota constraints (maximum three players per club). The objective is parameterized by a hybrid scoring metric that combines realized FPL points with predictions from a linear regression model trained on match-performance features identified using exploratory data analysis techniques. The study benchmarks alternative objectives and cost estimators, including simple and recency-weighted averages, exponential smoothing, autoregressive integrated moving average (ARIMA), and Monte Carlo simulation. Experiments on the 2023/24 Premier League season show that ARIMA with a constrained budget and a rolling window yields the most consistent out-of-sample performance; weighted averages and Monte Carlo are also competitive. Robust variants and hybrid scoring metrics improve some objectives but are not uniformly superior. The framework provides transparent decision support for fantasy roster construction and extends to FPL chips, multi-week rolling-horizon transfer planning, and week-by-week dynamic captaincy.
Authors: Donald Flynn, Diego Granziol
Abstract: Backdoor and data-poisoning attacks can flip predictions with tiny training corruptions, yet a sharp theory linking poisoning strength, overparameterization, and regularization is lacking. We analyze ridge least squares with an unpenalized intercept in the high-dimensional regime \(p,n\to\infty\), \(p/n\to c\). Targeted poisoning is modelled by shifting a \(\theta\)-fraction of one class by a direction \(\mathbf{v}\) and relabelling. Using resolvent techniques and deterministic equivalents from random matrix theory, we derive closed-form limits for the poisoned score explicit in the model parameters. The formulas yield scaling laws, recover the interpolation threshold as \(c\to1\) in the ridgeless limit, and show that the weights align with the poisoning direction. Synthetic experiments match theory across sweeps of the parameters and MNIST backdoor tests show qualitatively consistent trends. The results provide a tractable framework for quantifying poisoning in linear models.
Authors: M. S\"uzen
Abstract: A proposition that connects randomness and compression is put forward via Gibbs entropy over set of measurement vectors associated with a compression process. The proposition states that a lossy compression process is equivalent to {\it directed randomness} that preserves information content. The proposition originated from the observed behavior in newly proposed {\it Dual Tomographic Compression} (DTC) compress-train framework. This is akin to tomographic reconstruction of layer weight matrices via building compressed sensed projections, via so-called {\it weight rays}. This tomographic approach is applied to previous and next layers in a dual fashion, that triggers neuronal-level pruning. This novel model compress-train scheme appears in iterative fashion and acts as a smart neural architecture search: also called {\it compression aware training}. The experiments demonstrated the utility of this dual-tomography during training: method accelerates and supports lottery ticket hypothesis. However, random compress-train iterations having similar performance demonstrated the connection between randomness and compression from statistical physics perspective, we formulated the so-called {\it Gibbs randomness-compression proposition}, signifying randomness-compression relationship via Gibbs entropy. The proposition is supported with the experimental evidence, resulting in very high correlation between learning performance vs. Gibbs entropy over compression ratios. Practically, the DTC framework provides a promising approach for massively energy- and resource-efficient deep learning training.
Authors: Yu (Eric), Qian, Wilson S. Geisler, Xue-Xin Wei
Abstract: Previous studies have compared neural activities in the visual cortex to representations in deep neural networks trained on image classification. Interestingly, while some suggest that their representations are highly similar, others argued the opposite. Here, we propose a new approach to characterize the similarity of the decision strategies of two observers (models or brains) using decision variable correlation (DVC). DVC quantifies the image-by-image correlation between the decoded decisions based on the internal neural representations in a classification task. Thus, it can capture task-relevant information rather than general representational alignment. We evaluate DVC using monkey V4/IT recordings and network models trained on image classification tasks. We find that model-model similarity is comparable to monkey-monkey similarity, whereas model-monkey similarity is consistently lower. Strikingly, DVC decreases with increasing network performance on ImageNet-1k. Adversarial training does not improve model-monkey similarity in task-relevant dimensions assessed using DVC, although it markedly increases the model-model similarity. Similarly, pre-training on larger datasets does not improve model-monkey similarity. These results suggest a divergence between the task-relevant representations in monkey V4/IT and those learned by models trained on image classification tasks.
Authors: Xin Chen, Jason M. Klusowski, Yan Shuo Tan, Chang Yu
Abstract: Feature subsampling is a core component of random forests and other ensemble methods. While recent theory suggests that this randomization acts solely as a variance reduction mechanism analogous to ridge regularization, these results largely rely on base learners optimized via ordinary least squares. We investigate the effects of feature subsampling on greedy forward selection, a model that better captures the adaptive nature of decision trees. Assuming an orthogonal design, we prove that ensembling with feature subsampling can reduce both bias and variance, contrasting with the pure variance reduction of convex base learners. More precisely, we show that both the training error and degrees of freedom can be non-monotonic in the subsampling rate, breaking the analogy with standard shrinkage methods like the lasso or ridge regression. Furthermore, we characterize the exact asymptotic behavior of the estimator, showing that it adaptively reweights OLS coefficients based on their rank, with weights that are well-approximated by a logistic function. These results elucidate the distinct role of algorithmic randomization when interleaved with greedy optimization.
Authors: Jaime Hieu Do, Trung-Hoang Le, Hady W. Lauw
Abstract: In the online digital realm, recommendation systems are ubiquitous and play a crucial role in enhancing user experience. These systems leverage user preferences to provide personalized recommendations, thereby helping users navigate through the paradox of choice. This work focuses on personalized sequential recommendation, where the system considers not only a user's immediate, evolving session context, but also their cumulative historical behavior to provide highly relevant and timely recommendations. Through an empirical study conducted on diverse real-world datasets, we have observed and quantified the existence and impact of both short-term (immediate and transient) and long-term (enduring and stable) preferences on users' historical interactions. Building on these insights, we propose a framework that combines short- and long-term preferences to enhance recommendation performance, namely Compositions of Variant Experts (CoVE). This novel framework dynamically integrates short- and long-term preferences through the use of different specialized recommendation models (i.e., experts). Extensive experiments showcase the effectiveness of the proposed methods and ablation studies further investigate the impact of variant expert types.
Authors: Suqing Liu, Xuan Bi, Tianxi Li
Abstract: Differential privacy is a well-established framework for safeguarding sensitive information in data. While extensively applied across various domains, its application to network data -- particularly at the node level -- remains underexplored. Existing methods for node-level privacy either focus exclusively on query-based approaches, which restrict output to pre-specified network statistics, or fail to preserve key structural properties of the network. In this work, we propose GRAND (Graph Release with Assured Node Differential privacy), which is, to the best of our knowledge, the first network release mechanism that releases networks while ensuring node-level differential privacy and preserving structural properties. Under a broad class of latent space models, we show that the released network asymptotically follows the same distribution as the original network. The effectiveness of the approach is evaluated through extensive experiments on both synthetic and real-world datasets.
Authors: Louise Largeau, Tom Beucler, David Leutwyler, Gregoire Mariethoz, Valerie Chavez-Demoulin, Erwan Koch
Abstract: The coarse spatial resolution of gridded climate models, such as general circulation models, limits their direct use in projecting socially relevant variables like extreme precipitation. Most downscaling methods estimate the conditional distributions of extremes by generating large ensembles, complicating the assessment of robustness under distributional transformations, such as those induced by climate change. To better understand and potentially improve robustness, we propose super-resolving the parameters of the target variable's probability distribution directly using analytically tractable mappings. Within a perfect-model framework over Switzerland, we demonstrate that vector generalized linear and additive models can super-resolve the generalized extreme value distribution of summer hourly precipitation extremes from coarse precipitation fields and topography. We introduce the notion of a "robustness gap", defined as the difference in predictive error between present-trained and future-trained models, and use it to diagnose how model structure affects the generalization of each quantile to a pseudo-global warming scenario. By evaluating multiple model configurations, we also identify an upper limit on the super-resolution factor based on the spatial auto- and cross-correlation of precipitation and elevation, beyond which coarse precipitation loses predictive value. Our framework is broadly applicable to variables governed by parametric distributions and offers a model-agnostic diagnostic for understanding when and why empirical downscaling generalizes to climate change and extremes.
Authors: Jian Yao, Ran Cheng, Kay Chen Tan
Abstract: Recent advances in reinforcement learning (RL) have led to substantial improvements in the mathematical reasoning abilities of LLMs, as measured by standard benchmarks. Yet these gains often persist even when models are trained with flawed signals, such as random or inverted rewards. This raises a fundamental question: do such improvements reflect genuine reasoning, or are they merely artifacts of overfitting to benchmark-specific patterns? To answer this question, we adopt an evaluation-centric perspective and highlight two critical shortcomings in existing protocols. First, benchmark contamination arises because test problems are publicly available, thereby increasing the risk of data leakage. Second, evaluation fragility results from reliance on single-instance assessments, which are sensitive to stochastic outputs and fail to capture reasoning consistency. These limitations suggest the need for a new evaluation paradigm that can probe reasoning ability beyond memorization and one-off success. As response, we propose VAR-MATH, a symbolic evaluation framework that converts fixed numerical problems into parameterized templates and requires models to solve multiple instantiations of each. This design enforces consistency across structurally equivalent variants, mitigates contamination, and enhances robustness through bootstrapped metrics. We apply VAR-MATH to transform three popular benchmarks, AMC23, AIME24, and AIME25, into their symbolic counterparts, VAR-AMC23, VAR-AIME24, and VAR-AIME25. Experimental results show substantial performance drops for RL-trained models on these variabilized benchmarks, especially for smaller models, with average declines of 47.9\% on AMC23, 58.8\% on AIME24, and 72.9\% on AIME25. These findings indicate that some existing RL methods rely on superficial heuristics and fail to generalize beyond specific numerical forms.
Authors: Hei Shing Cheung, Boya Zhang, Jonathan H. Chan
Abstract: We present a lightweight latent diffusion model for vocal-conditioned musical accompaniment generation that addresses critical limitations in existing music AI systems. Our approach introduces a novel soft alignment attention mechanism that adaptively combines local and global temporal dependencies based on diffusion timesteps, enabling efficient capture of multi-scale musical structure. Operating in the compressed latent space of a pre-trained variational autoencoder, the model achieves a 220 times parameter reduction compared to state-of-the-art systems while delivering 52 times faster inference. Experimental evaluation demonstrates competitive performance with only 15M parameters, outperforming OpenAI Jukebox in production quality and content unity while maintaining reasonable musical coherence. The ultra-lightweight architecture enables real-time deployment on consumer hardware, making AI-assisted music creation accessible for interactive applications and resource-constrained environments.
Authors: Qian-Rui Lee, Daw-Wei Wang
Abstract: We propose a machine learning framework based on Flow Matching (FM) to identify critical properties in many-body systems efficiently. Using the 2D XY model as a benchmark, we demonstrate that a single network, trained only on configurations from a small ($32\times 32$) lattice at sparse temperature points, effectively generalizes across both temperature and system size. This dual generalization enables two primary applications for large-scale computational physics: (i) a rapid "train-small, predict-large" strategy to locate phase transition points for significantly larger systems ($128\times 128$) without retraining, facilitating efficient finite-size scaling analysis; and (ii) the fast generation of high-fidelity, decorrelated initial spin configurations for large-scale Monte Carlo simulations, providing a robust starting point that bypasses the long thermalization times of traditional samplers. These capabilities arise from the combination of the Flow Matching framework, which learns stable probability-flow vector fields, and the inductive biases of the U-Net architecture that capture scale-invariant local correlations. Our approach offers a scalable and efficient tool for exploring the thermodynamic limit, serving as both a rapid explorer for phase boundaries and a high-performance initializer for high-precision studies.
Authors: Abdul Rehman Akbar, Usama Sajjad, Ziyu Su, Wencheng Li, Fei Xing, Jimmy Ruiz, Wei Chen, Muhammad Khalid Khan Niazi
Abstract: Recurrence remains a major clinical challenge in surgically resected invasive lung adenocarcinoma, where existing grading and staging systems fail to capture the cellular complexity that underlies tumor aggressiveness. We present PathRosetta, a novel AI model that conceptualizes histopathology as a language, where cells serve as words, spatial neighborhoods form syntactic structures, and tissue architecture composes sentences. By learning this language of histopathology, PathRosetta predicts five-year recurrence directly from hematoxylin-and-eosin (H&E) slides, treating them as documents representing the state of the disease. In a multi-cohort dataset of 289 patients (600 slides), PathRosetta achieved an area under the curve (AUC) of 0.78 +- 0.04 on the internal cohort, significantly outperforming IASLC grading (AUC:0.71), AJCC staging (AUC:0.64), and other state-of-the-art AI models (AUC:0.62-0.67). It yielded a hazard ratio of 9.54 and a concordance index of 0.70, generalized robustly to external TCGA (AUC:0.75) and CPTAC (AUC:0.76) cohorts, and performed consistently across demographic and clinical subgroups. Beyond whole-slide prediction, PathRosetta uncovered prognostic subgroups within individual cell types, revealing that even within benign epithelial, stromal, or other cells, distinct morpho-spatial phenotypes correspond to divergent outcomes. Moreover, because the model explicitly understands what it is looking at, including cell types, cellular neighborhoods, and higher-order tissue morphology, it is inherently interpretable and can articulate the rationale behind its predictions. These findings establish that representing histopathology as a language enables interpretable and generalizable prognostication from routine histology.
Authors: Jiajie He, Min-Chun Chen, Xintong Chen, Xinyang Fang, Yuechun Gu, Keke Chen
Abstract: Large language models (LLMs) based recommender systems (RecSys) can adapt to different domains flexibly. It utilizes in-context learning (ICL), i.e., prompts, to customize the recommendation functions, which include sensitive historical user-specific item interactions, encompassing implicit feedback such as clicked items and explicit product reviews. Such private information may be exposed by novel privacy attacks. However, no study has been conducted on this important issue. We design several membership inference attacks (MIAs) aimed to revealing whether system prompts include victims' historical interactions. The attacks are \emph{Similarity, Memorization, Inquiry, and Poisoning attacks}, each utilizing unique features of LLMs or RecSys. We have carefully evaluated them on five of the latest open-source LLMs and three well-known RecSys benchmark datasets. The results confirm that the MIA threat to LLM RecSys is realistic: inquiry and poisoning attacks show significantly high attack advantages. We also discussed possible methods to mitigate such MIA threats. We have also analyzed the factors affecting these attacks, such as the number of shots in system prompts, the position of the victim in the shots, the number of poisoning items in the prompt,etc.
Authors: Tyler E. Maltba, Ben S. Southworth, Jeffrey R. Haack, Marc L. Klasky
Abstract: Continued progress in inertial confinement fusion (ICF) requires solving inverse problems relating experimental observations to simulation input parameters, followed by design optimization. However, such high-dimensional dynamic PDE-constrained optimization problems are extremely challenging or even intractable. It has been recently shown that inverse problems can be solved by only considering certain robust features. Here we consider the ICF capsule's deuterium-tritium (DT) interface, and construct a causal, dynamic, multifidelity reduced-order surrogate that maps from a time-dependent radiation temperature drive to the interface's radius and velocity dynamics. The surrogate targets an ODE embedding of DT interface dynamics, and is constructed by learning a controller for a base analytical model using low- and high-fidelity simulation training data with respect to radiation energy group structure. After demonstrating excellent accuracy of the surrogate interface model, we use machine learning (ML) models with surrogate-generated data to solve inverse problems optimizing radiation temperature drive to reproduce observed interface dynamics. For sparse snapshots in time, the ML model further characterizes the most informative times at which to sample dynamics. Altogether we demonstrate how operator learning, causal architectures, and physical inductive bias can be integrated to accelerate discovery, design, and diagnostics in high-energy-density systems.
Authors: Alexandra Carpentier (LMO, CELESTE), Simone Maria Giancola (LMO, CELESTE), Christophe Giraud (LMO, CELESTE), Nicolas Verzelen (MISTEA)
Abstract: Low-degree polynomials have emerged as a powerful paradigm for providing evidence of statistical-computational gaps across a variety of high-dimensional statistical models [Wein25]. For detection problems -- where the goal is to test a planted distribution $\mathbb{P}'$ against a null distribution $\mathbb{P}$ with independent components -- the standard approach is to bound the advantage using an $\mathbb{L}^2(\mathbb{P})$-orthonormal family of polynomials. However, this method breaks down for estimation tasks or more complex testing problems where $\mathbb{P}$ has some planted structures, so that no simple $\mathbb{L}^2(\mathbb{P})$-orthogonal polynomial family is available. To address this challenge, several technical workarounds have been proposed [SW22,SW25], though their implementation can be delicate. In this work, we propose a more direct proof strategy. Focusing on random graph models, we construct a basis of polynomials that is almost orthonormal under $\mathbb{P}$, in precisely those regimes where statistical-computational gaps arise. This almost orthonormal basis not only yields a direct route to establishing low-degree lower bounds, but also allows us to explicitly identify the polynomials that optimize the low-degree criterion. This, in turn, provides insights into the design of optimal polynomial-time algorithms. We illustrate the effectiveness of our approach by recovering known low-degree lower bounds, and establishing new ones for problems such as hidden subcliques, stochastic block models, and seriation models.
Authors: Rani Naaman, Felipe Gohring de Magalhaes, Jean-Yves Ouattara, Gabriela Nicolescu
Abstract: The emerging field of Quantum Machine Learning (QML) has shown promising advantages in accelerating processing speed and effectively handling the high dimensionality associated with complex datasets. Quantum Computing (QC) enables more efficient data manipulation through the quantum properties of superposition and entanglement. In this paper, we present a novel approach combining quantum and classical machine learning techniques to explore the impact of quantum properties for anomaly detection in Automatic Dependent Surveillance-Broadcast (ADS-B) data. We compare the performance of a Hybrid-Fully Connected Quantum Neural Network (H-FQNN) with different loss functions and use a publicly available ADS-B dataset to evaluate the performance. The results demonstrate competitive performance in detecting anomalies, with accuracies ranging from 90.17% to 94.05%, comparable to the performance of a traditional Fully Connected Neural Network (FNN) model, which achieved accuracies between 91.50% and 93.37%.
Authors: Pittawat Taveekitworachai, Natpatchara Pongjirapat, Krittaphas Chaisutyakorn, Piyalitt Ittichaiwong, Tossaporn Saengja, Kunat Pipatanakul
Abstract: Medical reasoning models (MRMs) achieve superior performance on medical benchmarks compared to medical LLMs; however, high accuracy alone is insufficient for practical deployment. One of such requirements for real-world application is robustness to varying output constraints. Specifically, posing the same medical question while requesting different answer formats should not affect the underlying correctness of the response. We investigate this phenomenon in this paper, focusing on MRMs. To quantify this behavior, we propose the metric answer-format robustness: the ability to reliably generate correct outputs across varying specified formats. We examine three representative formats: multiple-choice, open-ended question-answering, and ranked lists. Across 15 proprietary and open-weight models, we observe substantial variation in format robustness (35-100%). Furthermore, we conduct controlled fine-tuning experiments on a shared backbone with matched training data to isolate the effects of the fine-tuning paradigm. We find that supervised fine-tuning yields more stable behavior across formats, whereas reinforcement fine-tuning often exhibits higher cross-format brittleness, with the degree of instability strongly dependent on reward design. Overall, answer-format robustness in MRMs is trainable yet brittle and requires careful evaluation for practical medical use.
Authors: Linxiao Zeng, Haoyun Deng, Kangyuan Shu, Shizhen Wang
Abstract: Large language models achieve strong machine translation quality but incur high inference cost and latency, posing challenges for simultaneous translation. Re-translation provides a practical solution for off-the-shelf LLMs by repeatedly regenerating the target output as the source input grows, but it suffers from substantial redundant computation. We propose Self-Speculative Biased Decoding (SSBD), a simple and tuning-free inference method that accelerates re-translation by exploiting temporal coherence in streaming translation. SSBD reuses the model's previous output as a speculative draft for the updated input, verifies the draft efficiently in a single forward pass with a lightweight bias, and resumes autoregressive decoding only from the first divergence. We further introduce a display-only masking strategy that hides unstable suffixes from the user interface while retaining them in the draft for verification and potential acceptance. Experiments show that SSBD achieves substantial speedup over standard re-translation while maintaining comparable translation quality, without architectural changes, auxiliary models, or extra fine-tuning.
Authors: Antonio Norelli, Michael Bronstein
Abstract: A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conceal a secret manuscript. This uncanny state of affairs is now possible thanks to Large Language Models, and in this paper we present Calgacus, a simple and efficient protocol to achieve it. We show that even modest 8-billion-parameter open-source LLMs are sufficient to obtain high-quality results, and a message as long as this abstract can be encoded and decoded locally on a laptop in seconds. The existence of such a protocol demonstrates a radical decoupling of text from authorial intent, further eroding trust in written communication, already shaken by the rise of LLM chatbots. We illustrate this with a concrete scenario: a company could covertly deploy an unfiltered LLM by encoding its answers within the compliant responses of a safe model. This possibility raises urgent questions for AI safety and challenges our understanding of what it means for a Large Language Model to know something. -- Un testo di senso compiuto pu\`o essere nascosto all'interno di un altro testo completamente diverso, eppure coerente e plausibile, della stessa lunghezza. Ad esempio, un tweet che celebra un leader politico potrebbe celare un tweet che lo critica duramente, o un'anonima recensione di un prodotto potrebbe in realt\`a codificare un manoscritto segreto. Questa sconcertante possibilit\`a \`e oggi alla nostra portata grazie ai Large Language Models (LLM); in questo articolo presentiamo Calgacus, un protocollo semplice ed efficiente per realizzarla. Mostriamo che anche modesti LLM open-source da 8 miliardi di parametri sono sufficienti per ottenere risultati di alta qualit\`a, e che un messaggio lungo quanto questo abstract pu\`o essere codificato e decodificato su un comune portatile in pochi secondi. L'esistenza di tale protocollo dimostra un radicale disaccoppiamento del testo dall'intento del suo autore, erodendo ulteriormente la fiducia nella comunicazione scritta, gi\`a scossa dall'ascesa dei chatbot basati su LLMs. Illustriamo ci\`o con uno scenario concreto: un'azienda potrebbe offrire pubblicamente i servizi di un LLM senza filtri nascondendo le sue risposte all'interno di risposte apparentemente innocue generate da un LLM considerato sicuro. Questa possibilit\`a solleva questioni urgenti per la sicurezza dell'Intelligenza Artificiale e sfida la nostra comprensione di cosa significhi, per un Large Language Model, sapere qualcosa.
Authors: Jessica Doohan, Lucas Kook, Kevin Burke
Abstract: Neural networks have become a popular tool in predictive modelling, more commonly associated with machine learning and artificial intelligence than with statistics. Generalised Additive Models (GAMs) are flexible non-linear statistical models that retain interpretability. Both are state-of-the-art in their own right, with their respective advantages and disadvantages. This paper analyses how these two model classes have performed on real-world tabular data. Following PRISMA guidelines, we conducted a systematic review of papers that performed empirical comparisons of GAMs and neural networks. Eligible papers were identified, yielding 143 papers, with 430 datasets. Key attributes at both paper and dataset levels were extracted and reported. Beyond summarising comparisons, we analyse reported performance metrics using mixed-effects modelling to investigate potential characteristics that can explain and quantify observed differences, including application area, study year, sample size, number of predictors, and neural network complexity. Across datasets, no consistent evidence of superiority was found for either GAMs or neural networks when considering the most frequently reported metrics (RMSE, $R^2$, and AUC). Neural networks tended to outperform in larger datasets and in those with more predictors, but this advantage narrowed over time. Conversely, GAMs remained competitive, particularly in smaller data settings, while retaining interpretability. Reporting of dataset characteristics and neural network complexity was incomplete in much of the literature, limiting transparency and reproducibility. This review highlights that GAMs and neural networks should be viewed as complementary approaches rather than competitors. For many tabular applications, the performance trade-off is modest, and interpretability may favour GAMs.
Authors: Eric Xue, Ruiyi Zhang, Pengtao Xie
Abstract: Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at inference time. Recent work has emphasized stealthy attacks that stress-test data-curation defenses using stylized artifacts or token-level perturbations as triggers, but this focus leaves a more practically relevant threat model underexplored: backdoors tied to naturally occurring semantic concepts. We introduce SteganoBackdoor, an optimization-based framework that constructs SteganoPoisons, steganographic poisoned training examples in which a backdoor payload is distributed across a fluent sentence while exhibiting no representational overlap with the inference-time semantic trigger. Across diverse model architectures, SteganoBackdoor achieves high attack success under constrained poisoning budgets and remains effective under conservative data-level filtering, highlighting a blind spot in existing data-curation defenses.
Authors: Valentina S\'anchez, \c{C}i\c{c}ek G\"uven, Koen Haak, Theodore Papamarkou, Gonzalo N\'apoles, Marie \v{S}af\'a\v{r} Postma
Abstract: We propose a framework for constructing combinatorial complexes (CCs) from fMRI time series data that captures both pairwise and higher-order neural interactions through information-theoretic measures, bridging topological deep learning and network neuroscience. Current graph-based representations of brain networks systematically miss the higher-order dependencies that characterize neural complexity, where information processing often involves synergistic interactions that cannot be decomposed into pairwise relationships. Unlike topological lifting approaches that map relational structures into higher-order domains, our method directly constructs CCs from statistical dependencies in the data. Our CCs generalize graphs by incorporating higher-order cells that represent collective dependencies among brain regions, naturally accommodating the multi-scale, hierarchical nature of neural processing. The framework constructs data-driven combinatorial complexes using O-information and S-information measures computed from fMRI signals, preserving both pairwise connections and higher-order cells (e.g., triplets, quadruplets) based on synergistic dependencies. Using NetSim simulations as a controlled proof-of-concept dataset, we demonstrate our CC construction pipeline and show how both pairwise and higher-order dependencies in neural time series can be quantified and represented within a unified structure. This work provides a framework for brain network representation that preserves fundamental higher-order structure invisible to traditional graph methods, and enables the application of topological deep learning (TDL) architectures to neural data.
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: Wencheng Cai, Xuchao Gao, Congying Han, Mingqiang Li, Tiande Guo
Abstract: The fast deployment of cognitive radar to counter jamming remains a critical challenge in modern warfare, where more efficient deployment leads to quicker detection of targets. Existing methods are primarily based on evolutionary algorithms, which are time-consuming and prone to falling into local optima. We tackle these drawbacks via the efficient inference of neural networks and propose a brand new framework: Fast Anti-Jamming Radar Deployment Algorithm (FARDA). We first model the radar deployment problem as an end-to-end task and design deep reinforcement learning algorithms to solve it, where we develop integrated neural modules to perceive heatmap information and a brand new reward format. Empirical results demonstrate that our method achieves coverage comparable to evolutionary algorithms while deploying radars approximately 7,000 times faster. Further ablation experiments confirm the necessity of each component of FARDA.
Authors: Francisco Ribeiro, Claudio Spiess, Prem Devanbu, Sarah Nadi
Abstract: Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output of the generation process. Inspired by findings that LLMs internally encode concepts like truthfulness, this paper explores if LLMs similarly represent code correctness. Specifically, we identify a correctness representation inside LLMs by contrasting the hidden states between pairs of correct and incorrect code for the same programming tasks. By experimenting on four LLMs, we show that exploiting this extracted correctness representation outperforms standard log-likelihood ranking, as well as verbalized model confidence. Furthermore, we explore how this internal correctness signal can be used to select higher-quality code samples, without requiring test execution. Ultimately, this work demonstrates how leveraging internal representations can enhance code generation systems and make LLMs more reliable, thus improving confidence in automatically generated code.
Authors: Jikai Jin, Vasilis Syrgkanis
Abstract: We establish a general statistical optimality theory for estimation problems where the target parameter is a linear functional of an unknown nuisance component that must be estimated from data. This formulation covers many causal and predictive parameters and has applications to numerous disciplines. We adopt the structure-agnostic framework introduced by \citet{balakrishnan2023fundamental}, which poses no structural properties on the nuisance functions other than access to black-box estimators that achieve some statistical estimation rate. This framework is particularly appealing when one is only willing to consider estimation strategies that use non-parametric regression and classification oracles as black-box sub-processes. Within this framework, we first prove the statistical optimality of the celebrated and widely used doubly robust estimators for the Average Treatment Effect (ATE), the most central parameter in causal inference. We then characterize the minimax optimal rate under the general formulation. Notably, we differentiate between two regimes in which double robustness can and cannot be achieved and in which first-order debiasing yields different error rates. Our result implies that first-order debiasing is simultaneously optimal in both regimes. We instantiate our theory by deriving optimal error rates that recover existing results and extend to various settings of interest, including the case when the nuisance is defined by generalized regressions and when covariate shift exists for training and test distribution.
Authors: Tony Wang, Kyle Feinstein, Sheryl Chen
Abstract: We study how a central bank should dynamically set short-term nominal interest rates to stabilize inflation and unemployment when macroeconomic relationships are uncertain and time-varying. We model monetary policy as a sequential decision-making problem where the central bank observes macroeconomic conditions quarterly and chooses interest rate adjustments. Using publicly accessible historical Federal Reserve Economic Data (FRED), we construct a linear-Gaussian transition model and implement a discrete-action Markov Decision Process with a quadratic loss reward function. We chose to compare nine different reinforcement learning style approaches against Taylor Rule and naive baselines, including tabular Q-learning variants, SARSA, Actor-Critic, Deep Q-Networks, Bayesian Q-learning with uncertainty quantification, and POMDP formulations with partial observability. Notably, despite its simplicity, standard tabular Q-learning achieved the best performance (-615.13 +- 309.58 mean return), outperforming both enhanced RL methods and traditional policy rules. Our results suggest that while sophisticated RL techniques show promise for monetary policy applications, simpler approaches may be more robust in this domain, highlighting important challenges in applying modern RL to macroeconomic policy.
Authors: G\"okdeniz G\"ulmez
Abstract: We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections with regularized layer selection. Our approach addresses the fundamental limitation of existing methods that compromise model quality while attempting to modify specific behavioral patterns. Through dynamic layer optimization, regularized projection matrices, and adaptive scaling mechanisms, we achieve theoretically superior weight modification while minimizing quality degradation in unrelated domains. We validate our method through the gabliterated-v1 model series (0.6B to 4B parameters) available on Hugging Face, demonstrating practical applicability across multiple model scales.
Authors: Zhaosong Lu, Sanyou Mei
Abstract: In this paper we study a nonconvex-strongly-concave constrained minimax problem. Specifically, we propose a first-order augmented Lagrangian method for solving it, whose subproblems are nonconvex-strongly-concave unconstrained minimax problems and suitably solved by a first-order method developed in this paper that leverages the strong concavity structure. Under suitable assumptions, the proposed method achieves an operation complexity of $O(\varepsilon^{-3.5}\log\varepsilon^{-1})$, measured in terms of its fundamental operations, for finding an $\varepsilon$-KKT solution of the constrained minimax problem, which improves the previous best-known operation complexity by a factor of $\varepsilon^{-0.5}$.
Authors: Dianyun Wang, Qingsen Ma, Yuhu Shang, Zhifeng Lu, Zhenbo Xu, Lechen Ning, Huijia Wu, Zhaofeng He
Abstract: Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures, suggesting parameter-efficient fine-tuning (PEFT) should be well-suited for alignment. However, Low-Rank Adaptation (LoRA) consistently underperforms full fine-tuning and reinforcement learning on safety benchmarks. We attribute this gap to semantic entanglement: safety-relevant directions are intertwined with unrelated concepts due to polysemanticity, impeding implicit subspace identification. To address this, we propose SAILS (Safety Alignment via Interpretable Low-rank Subspace), which leverages Sparse Autoencoders (SAEs) to disentangle representations into monosemantic features, constructs an interpretable safety subspace from SAE decoder directions, and uses it to initialize LoRA adapters. Theoretically, we prove that SAE-based identification achieves arbitrarily small recovery error under monosemanticity assumptions, while direct identification suffers an irreducible error floor. Empirically, SAILS achieves up to 99.6% safety rate on Gemma-2-9B -- exceeding full fine-tuning by 7.4 points and matching RLHF-based models -- while updating only 0.19% of parameters and providing interpretability.
Authors: Zhenda Xie, Yixuan Wei, Huanqi Cao, Chenggang Zhao, Chengqi Deng, Jiashi Li, Damai Dai, Huazuo Gao, Jiang Chang, Kuai Yu, Liang Zhao, Shangyan Zhou, Zhean Xu, Zhengyan Zhang, Wangding Zeng, Shengding Hu, Yuqing Wang, Jingyang Yuan, Lean Wang, Wenfeng Liang
Abstract: Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and diversifying connectivity patterns. While yielding substantial performance gains, this diversification fundamentally compromises the identity mapping property intrinsic to the residual connection, which causes severe training instability and restricted scalability, and additionally incurs notable memory access overhead. To address these challenges, we propose Manifold-Constrained Hyper-Connections (mHC), a general framework that projects the residual connection space of HC onto a specific manifold to restore the identity mapping property, while incorporating rigorous infrastructure optimization to ensure efficiency. Empirical experiments demonstrate that mHC is effective for training at scale, offering tangible performance improvements and superior scalability. We anticipate that mHC, as a flexible and practical extension of HC, will contribute to a deeper understanding of topological architecture design and suggest promising directions for the evolution of foundational models.
Authors: Nikhil Garg, Anxiong Song, Niklas Plessnig, Nathan Savoia, Laura B\'egon-Lours
Abstract: Electroencephalography (EEG)-based brain-computer interfaces (BCIs) are strongly affected by non-stationary neural signals that vary across sessions and individuals, limiting the generalization of subject-agnostic models and motivating adaptive and personalized learning on resource-constrained platforms. Programmable memristive hardware offers a promising substrate for such post-deployment adaptation; however, practical realization is challenged by limited weight resolution, device variability, nonlinear programming dynamics, and finite device endurance. In this work, we show that spiking neural networks (SNNs) can be deployed on ferroelectric memristive synaptic devices for adaptive EEG-based motor imagery decoding under realistic device constraints. We fabricate, characterize, and model ferroelectric synapses. We evaluate a convolutional-recurrent SNN architecture under two complementary deployment strategies: (i) device-aware training using a ferroelectric synapse model, and (ii) transfer of software-trained weights followed by low-overhead on-device re-tuning. To enable efficient adaptation, we introduce a device-aware weight-update strategy in which gradient-based updates are accumulated digitally and converted into discrete programming events only when a threshold is exceeded, emulating nonlinear, state-dependent programming dynamics while reducing programming frequency. Both deployment strategies achieve classification performance comparable to state-of-the-art software-based SNNs. Furthermore, subject-specific transfer learning achieved by retraining only the final network layers improves classification accuracy. These results demonstrate that programmable ferroelectric hardware can support robust, low-overhead adaptation in spiking neural networks, opening a practical path toward personalized neuromorphic processing of neural signals.