Authors: Leonardo Alchieri, Matteo Garzon, Lidia Alecci, Francesco Bombassei De Bona, Martin Gjoreski, Giovanni De Felice, Silvia Santini
Abstract: Foundation models have recently extended beyond natural language and vision to timeseries domains, including physiological signals. However, progress in electrodermal activity (EDA) modeling is hindered by the absence of large-scale, curated, and openly accessible datasets. EDA reflects sympathetic nervous system activity and is widely used to infer cognitive load, stress, and engagement. Yet very few wearable devices provide continuous, unobtrusive sensing, and the only large-scale archive to date is proprietary. To address this gap, we compile EDAMAME, a collection of EDA traces from 24 public datasets, comprising more than 25,000 hours from 634 users. Using this resource, we train UME, the first dedicated foundation model for EDA. In eight out of ten scenarios, UME outperforms baselines and matches generalist timeseries foundation models while using 20x fewer computational resources. Our findings, however, also highlight the intrinsic challenges of EDA modeling, motivating further research to unlock its full potential. All datasets, model weights, and code are released to support further research.
Authors: Nadine Muller, Stefano DeRosa, Su Zhang, Chun Lee Huan
Abstract: Multi-agent deep learning (MADL), including multi-agent deep reinforcement learning (MADRL), distributed/federated training, and graph-structured neural networks, is becoming a unifying framework for decision-making and inference in wireless systems where sensing, communication, and computing are tightly coupled. Recent 5G-Advanced and 6G visions strengthen this coupling through integrated sensing and communication, edge intelligence, open programmable RAN, and non-terrestrial/UAV networking, which create decentralized, partially observed, time-varying, and resource-constrained control problems. This survey synthesizes the state of the art, with emphasis on 2021-2025 research, on MADL for distributed sensing and wireless communications. We present a task-driven taxonomy across (i) learning formulations (Markov games, Dec-POMDPs, CTDE), (ii) neural architectures (GNN-based radio resource management, attention-based policies, hierarchical learning, and over-the-air aggregation), (iii) advanced techniques (federated reinforcement learning, communication-efficient federated deep RL, and serverless edge learning orchestration), and (iv) application domains (MEC offloading with slicing, UAV-enabled heterogeneous networks with power-domain NOMA, intrusion detection in sensor networks, and ISAC-driven perceptive mobile networks). We also provide comparative tables of algorithms, training topologies, and system-level trade-offs in latency, spectral efficiency, energy, privacy, and robustness. Finally, we identify open issues including scalability, non-stationarity, security against poisoning and backdoors, communication overhead, and real-time safety, and outline research directions toward 6G-native sense-communicate-compute-learn systems.
Authors: Krishna Kumar Neelakanta Pillai Santha Kumari Amma
Abstract: Dynamic pricing in competitive retail markets requires strategies that adapt to fluctuating demand and competitor behavior. In this work, we present a systematic empirical evaluation of multi-agent reinforcement learning (MARL) approaches-specifically MAPPO and MADDPG-for dynamic price optimization under competition. Using a simulated marketplace environment derived from real-world retail data, we benchmark these algorithms against an Independent DDPG (IDDPG) baseline, a widely used independent learner in MARL literature. We evaluate profit performance, stability across random seeds, fairness, and training efficiency. Our results show that MAPPO consistently achieves the highest average returns with low variance, offering a stable and reproducible approach for competitive price optimization, while MADDPG achieves slightly lower profit but the fairest profit distribution among agents. These findings demonstrate that MARL methods-particularly MAPPO-provide a scalable and stable alternative to independent learning approaches for dynamic retail pricing.
Authors: Omer Nacar, Deema Alquffari, Saleh Alsharideh, Adeem AlOtaibi, Abdulaziz Alabdulkarim, Leen Alhazmi, Nada Alomar, Wareef Alzubaidi, Nada Alsultan, Ahmed Alrabghi, Demah Alhoshan, Rana Alsayyari, Hamed Alruwaili, Albaraa Jaafar, Khaled Alusmani, Abdulaziz Alsohimy, Munirah Alsubaie, Shahd Aldukhayil, Arwa Alali, Yazeed BinShihah, Razan Alsulaymi, Nourah Alhumaid, Razan Abdulsalam, Reem Alamoudi, Mohammed Alkhalifa
Abstract: Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present AISA-AR-FunctionCall, a production-oriented Arabic function-calling framework built on a 270M-parameter FunctionGemma backbone and trained through systematic dataset auditing, schema repair, tool-aware prompt restructuring, and full-parameter supervised fine-tuning. On a held-out test set, fine-tuning reduces parse failures from 87\% to below 1\%, improves function name accuracy by more than eightfold, and substantially enhances argument alignment across dialects and domains. Error analysis reveals a transition from structural collapse to semantic misalignment, suggesting that serialization stability and decision-level reasoning are separable challenges. We further explore a reasoning-augmented LoRA variant that introduces explicit intermediate reasoning prior to tool invocation. All datasets and models are publicly released under the AISA framework.
Authors: Ivan Felipe Benavides-Martinez, Justin Guthrie, Jhon Edwin Arias, Yeison Alberto Garces-Gomez, Angela Ines Guzman-Alvis, Cristiam Victoriano Portilla-Cabrera, Somnath Mondal, Andrew J. Allyn, Auroop R. Ganguly
Abstract: Geospatial foundation models generate high-dimensional embeddings that achieve strong predictive performance, yet their internal organization remains obscure, limiting their scientific use. Recent interpretability studies relate Google AlphaEarth Foundations (GAEF) embeddings to continuous environmental variables, but it is still unclear whether the embedding space exhibits a functional or hierarchical organization, in which some dimensions act as specialized representations while others encode shared or broader geospatial structure. In this work, we propose a functional interpretability framework that reverse-engineers the role of embedding dimensions by characterizing their contribution to land cover structure from observed classification behavior. The approach combines large-scale experimentation with a structural analysis of embedding-class relationships based on feature importance patterns and progressive ablation. Our results show that embedding dimensions exhibit consistent and non-uniform functional behavior, allowing them to be categorized along a hierarchical functional spectrum: specialist dimensions associated with specific land cover classes, low- and mid-generalist dimensions capturing shared characteristics between classes, and highgeneralist dimensions reflecting broader environmental gradients. Critically, we find that accurate land cover classification (98% of baseline performance) can be achieved using as few as 2 to 12 of the 64 available dimensions, depending on the class. This demonstrates substantial redundancy in the embedding space and offers a pathway toward significant reductions in computational cost. Together, these findings reveal that AlphaEarth embeddings are not only physically informative, but also functionally organized into a hierarchical structure, providing practical guidance for dimension selection in operational classification tasks.
Authors: Vladimer Khasia
Abstract: Sequence modeling universally relies on discrete subword tokenization to circumvent the $\mathcal{O}(N^2)$ computational intractability of native byte-level attention. However, this heuristic quantization imposes artificial morphological boundaries, enforces vocabulary dependence, and fractures the continuity of the optimization landscape. To resolve this dichotomy, we introduce \textbf{HoloByte}: a strictly tokenizer-free framework utilizing Continuous Hyperspherical Distillation. HoloByte partitions discrete byte sequences into fixed-capacity chunks and projects them into a continuous, strictly bounded hyperspherical manifold via an invertible, dimension-preserving orthogonal rotation operator. This spatial superposition allows a macroscopic transformer to operate exclusively on compressed continuous representations, formally reducing the exact attention time complexity from $\mathcal{O}(N^2D)$ to $\mathcal{O}\left( \frac{N^2}{W^2}D + ND^2 \right)$. A localized causal micro-decoder subsequently unbinds these representations to compute exact byte-level distributions. To govern this continuous trajectory, we propose a dual-objective formulation incorporating a mathematically precise Holographic Latent Mean Squared Error, which strictly bounds the gradient and guarantees asymptotic stability. Theoretically, we derive the minimal embedding dimension $D = \Omega(W \ln |\mathcal{V}|)$ required to ensure error-free discrete recovery from the continuous manifold. Empirically, under strictly matched parameter constraints, HoloByte is systematically outperforming a comparable discrete Byte-Pair Encoding (BPE) baseline. These results establish Continuous Hyperspherical Distillation as a mathematically rigorous and computationally tractable foundation for vocabulary-invariant sequence modeling. The code is available at https://github.com/VladimerKhasia/HoloByte
Authors: Hongjun Wang, Wei Liu, Weibo Gu, Xing Sun, Kai Han
Abstract: Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable boundaries and vanishing gradient regions, failing to maintain gradient fidelity. Furthermore, these methods lack a hazard-aware mechanism to adaptively suppress extreme deviations, leaving the optimization process vulnerable to abrupt policy shifts. To address these challenges, we propose Modulated Hazard-aware Policy Optimization (MHPO), a novel framework designed for robust and stable reinforcement learning. The proposed MHPO introduces a Log-Fidelity Modulator (LFM) to map unbounded importance ratios into a bounded, differentiable domain. This mechanism effectively prevents high-variance outlier tokens from destabilizing the loss landscape while ensuring global gradient stability. Complementarily, a Decoupled Hazard Penalty (DHP) integrates cumulative hazard functions from survival analysis to independently regulate positive and negative policy shifts. By shaping the optimization landscape with hazard-aware penalties, the proposed MHPO achieves fine-grained regulation of asymmetric policy shifts simultaneously mitigating mode collapse from over-expansion and preventing policy erosion from catastrophic contraction within a stabilized trust region. Extensive evaluations on diverse reasoning benchmarks across both text-based and vision-language tasks demonstrate that MHPO consistently outperforms existing methods, achieving superior performance while significantly enhancing training stability.
Authors: Mahfuz Ahmed Anik, Mohsin Mahmud Topu, Azmine Toushik Wasi, Md Isfar Khan, MD Manjurul Ahsan
Abstract: Sleep quality is influenced by a complex interplay of behavioral, environmental, and psychosocial factors, yet most computational studies focus mainly on predictive risk identification rather than actionable intervention design. Although machine learning models can accurately predict subjective sleep outcomes, they rarely translate predictive insights into practical intervention strategies. To address this gap, we propose a personalized predictive-prescriptive framework that integrates interpretable machine learning with mixed-integer optimization. A supervised classifier trained on survey data predicts sleep quality, while SHAP-based feature attribution quantifies the influence of modifiable factors. These importance measures are incorporated into a mixed-integer optimization model that identifies minimal and feasible behavioral adjustments, while modelling resistance to change through a penalty mechanism. The framework achieves strong predictive performance, with a test F1-score of 0.9544 and an accuracy of 0.9366. Sensitivity and Pareto analyses reveal a clear trade-off between expected improvement and intervention intensity, with diminishing returns as additional changes are introduced. At the individual level, the model generates concise recommendations, often suggesting one or two high-impact behavioral adjustments and sometimes recommending no change when expected gains are minimal. By integrating prediction, explanation, and constrained optimization, this framework demonstrates how data-driven insights can be translated into structured and personalized decision support for sleep improvement.
Authors: Martin G. Frasch
Abstract: Identifying physical laws from noisy observational data is a central challenge in scientific machine learning. We present Minimum-Action Learning (MAL), a framework that selects symbolic force laws from a pre-specified basis library by minimizing a Triple-Action functional combining trajectory reconstruction, architectural sparsity, and energy-conservation enforcement. A wide-stencil acceleration-matching technique reduces noise variance by 10,000x, transforming an intractable problem (SNR ~0.02) into a learnable one (SNR ~1.6); this preprocessing is the critical enabler shared by all methods tested, including SINDy variants. On two benchmarks -- Kepler gravity and Hooke's law -- MAL recovers the correct force law with Kepler exponent p = 3.01 +/- 0.01 at ~0.07 kWh (40% reduction vs. prediction-error-only baselines). The raw correct-basis rate is 40% for Kepler and 90% for Hooke; an energy-conservation-based criterion discriminates the true force law in all cases, yielding 100% pipeline-level identification. Basis library sensitivity experiments show that near-confounders degrade selection (20% with added r^{-2.5} and r^{-1.5}), while distant additions are harmless, and the conservation diagnostic remains informative even when the correct basis is absent. Direct comparison with noise-robust SINDy variants, Hamiltonian Neural Networks, and Lagrangian Neural Networks confirms MAL's distinct niche: interpretable, energy-constrained model selection that combines symbolic basis identification with dynamical rollout validation.
Authors: Krishna Kumar
Abstract: Machine learning models for geotechnical hazard prediction can achieve high accuracy while learning physically inconsistent relationships from sparse or biased training data. Current remedies (post-hoc explainability, such as SHAP and LIME, and training-time constraints) either diagnose individual predictions approximately or restrict model capacity without providing exhaustive guarantees. This paper encodes trained tree ensembles as logical formulas in a Satisfiability Modulo Theories (SMT) solver and checks physical specifications across the entire input domain, not just sampled points. Four geotechnical specifications (water table depth, PGA monotonicity, distance safety, and flat-ground safety) are formalized as decidable logical formulas and verified via SMT against both XGBoost ensembles and Explainable Boosting Machines (EBMs) trained on the 2011 Christchurch earthquake lateral spreading dataset (7,291 sites, four features). The SMT solver either produces a concrete counterexample where a specification fails or proves that no violation exists. The unconstrained EBM (80.1% accuracy) violates all four specifications. A fully constrained EBM (67.2%) satisfies three of four specifications, demonstrating that iterative constraint application guided by verification can progressively improve physical consistency. A Pareto analysis of 33 model variants reveals a persistent trade-off, as none of the variants studied achieve both greater than 80% accuracy and full compliance with the specified set. SHAP analysis of specification counterexamples shows that the offending feature can rank last, demonstrating that post-hoc explanations do not substitute for formal verification. These results establish a verify-fix-verify engineering loop and a formal certification for deploying physically consistent ML models in safety-critical geotechnical applications.
Authors: Yu-Chen Den, Kuan-Yu Chen, Kendro Vincent, Darby Tien-Hao Chang
Abstract: Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many Transformer variants implicitly assume stationarity and stable temporal dynamics -- assumptions routinely violated in financial markets characterized by regime shifts and non-stationarity. Empirically, state-of-the-art time-series Transformers often underperform even vanilla Transformers on financial tasks, while simpler architectures with distinct inductive biases, such as CNNs and RNNs, can achieve stronger performance with substantially lower complexity. At the same time, no single inductive bias dominates across markets or regimes, suggesting that robust financial forecasting requires integrating complementary temporal priors. We propose TIPS (Transformer with Inductive Prior Synthesis), a knowledge distillation framework that synthesizes diverse inductive biases -- causality, locality, and periodicity -- within a unified Transformer. TIPS trains bias-specialized Transformer teachers via attention masking, then distills their knowledge into a single student model with regime-dependent alignment across inductive biases. Across four major equity markets, TIPS achieves state-of-the-art performance, outperforming strong ensemble baselines by 55%, 9%, and 16% in annual return, Sharpe ratio, and Calmar ratio, while requiring only 38% of the inference-time computation. Further analyses show that TIPS generates statistically significant excess returns beyond both vanilla Transformers and its teacher ensembles, and exhibits regime-dependent behavioral alignment with classical architectures during their profitable periods. These results highlight the importance of regime-dependent inductive bias utilization for robust generalization in non-stationary financial time series.
Authors: Andy Gray
Abstract: A central question in the LLM debate is whether transformers can infer rules absent from training, or whether apparent generalisation reduces to similarity-based interpolation over observed examples. We test a strong interpolation-only hypothesis in two controlled settings: one where interpolation is ruled out by construction and proof, and one where success requires emitting intermediate symbolic derivations rather than only final answers. In Experiment 1, we use a cellular automaton with a pure XOR transition rule and remove specific local input patterns from training; since XOR is linearly inseparable, each held-out pattern's nearest neighbours have the opposite label, so similarity-based predictors fail on the held-out region. Yet a two-layer transformer recovers the rule (best 100%; 47/60 converged runs), and circuit extraction identifies XOR computation. Performance depends on multi-step constraint propagation: without unrolling, accuracy matches output bias (63.1%), while soft unrolling reaches 96.7%. In Experiment 2, we study symbolic operator chains over integers with one operator pair held out; the model must emit intermediate steps and a final answer in a proof-like format. Across all 49 holdout pairs, the transformer exceeds every interpolation baseline (mean 41.8%, up to 78.6%; mean KRR 4.3%; KNN and MLP score 0% on every pair), while removing intermediate-step supervision degrades performance. Together with a construction showing that a standard transformer block can implement exact local Boolean rules, these results provide an existence proof that transformers can learn rule structure not directly observed in training and express it explicitly, ruling out the strongest architectural form of interpolation-only accounts: that transformers cannot in principle discover and communicate unseen rules, while leaving open when such behaviour arises in large-scale language training.
Authors: Abinav Rao, Sujan Rachuri
Abstract: Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systematic study of this question, applying DPO to Janus-Pro at 1B and 7B parameters under seven training strategies and two post-hoc methods. The central finding is negative: generation quality resists DPO alignment across all tested conditions on this architecture. No method improves generation CLIPScore at 7B (|Delta| < 0.2, p > 0.5 at n=200 per seed, 3 seeds); at 1B, all methods degrade generation, and the result holds across preference data types (real-vs-generated and model-vs-model) and the data volumes tested (150-288 pairs). Gradient analysis reveals why: understanding and generation gradients are near-orthogonal (cos ~ 0) with ~11-14x magnitude imbalance driven by VQ token count asymmetry (576 generation tokens vs. ~30-100 text tokens). This imbalance is the dominant interference mechanism in multi-task DPO; magnitude-balancing yields directionally positive understanding deltas (+0.01-0.04 VQA, though individually not significant), but the generation gap persists regardless. We identify discrete VQ tokenization as a likely structural bottleneck -- supported by the generation DPO loss converging to ln(2) -- and provide practical guidance for practitioners working with VQ-based unified models.
Authors: Ahmed Zeid, Sidney Bender
Abstract: Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled approach to interpreting black-box predictions by identifying minimal input changes that alter model outputs. However, existing CFE methods often rely on dataset-specific generative models and incur substantial computational cost, limiting their scalability to high-resolution data. We propose SCE-LITE-HQ, a scalable framework for counterfactual generation that leverages pretrained generative foundation models without task-specific retraining. The method operates in the latent space of the generator, incorporates smoothed gradients to improve optimization stability, and applies mask-based diversification to promote realistic and structurally diverse counterfactuals. We evaluate SCE-LITE-HQ on natural and medical datasets using a desiderata-driven evaluation protocol. Results show that SCE-LITE-HQ produces valid, realistic, and diverse counterfactuals competitive with or outperforming existing baselines, while avoiding the overhead of training dedicated generative models.
Authors: Wenhao Zhao, Qiran Zou, Rushi Shah, Yudi Wu, Zhouhan Lin, Dianbo Liu
Abstract: Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and other generative models. Despite its prevalence, the characteristics and behaviors of vector quantization in generative models remain largely underexplored. In this study, we systematically investigate the issue of collapses in vector quantization, where collapsed representations are observed across discrete codebook tokens and continuous latent embeddings. By leveraging both synthetic and real datasets, we identify the severity of each type of collapses and triggering conditions. Our analysis reveals that random initialization and limited encoder capacity result in tokens collapse and embeddings collapse. Building on these findings, we propose potential solutions aimed at mitigating each collapse. To the best of our knowledge, this is the first comprehensive study examining representation collapsing problems in vector quantization.
Authors: Bharat Runwal, Ashish Agrawal, Anurag Roy, Rameswar Panda
Abstract: We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two architecture types (dense Transformer and attention-Mamba hybrid), and scales from 3B to 24B parameters, we show that mid-training on approximately 27B high-quality tokens yields consistent gains of +15 to +40 points on math, +5 to +12 points on code, and +6 to +13 points on science benchmarks while preserving general performance. The full PRISM to RL pipeline improves macro-average across six reasoning benchmarks from under 12 to 29-42 (a 3-4x improvement), whereas RL applied directly to most of the base models remains substantially less effective, with AIME scores near zero. Data composition matters most at mid-training, not RL: including science data during mid-training unlocks +17 to +28 point GPQA-Diamond gains during RL, while changing the RL mix produces less than 2 point differences. Mechanistically, mid-training densely restructures over 90% of model weights, while RL makes sparse, front-loaded refinements to approximately 5% of parameters. Representation analysis (CKA) confirms that RL consistently preserves mid-training's representational geometry (over 0.998 CKA) across architectures. Crucially, RL applies identical weight changes regardless of starting point, yet only succeeds on mid-trained models, consistent with mid-training placing the model in a configuration from which RL can effectively improve performance. Our results demonstrate that retention-aware mid-training is highly effective for reliable reasoning enhancement and provide practical guidance for designing robust mid-training pipelines.
Authors: Weikun K. Zhang, Rohan Pandey, Bhaumik Mehta, Kaijie Jin, Naomi Morato, Archit Ganapule, Michael Ruofan Zeng, Jarod Alper
Abstract: Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and multiplication gates. We formulate this problem as a single-player game, where an RL agent attempts to build the circuit within a fixed number of operations. We implement an AlphaZero-style training loop and compare two approaches: Proximal Policy Optimization with Monte Carlo Tree Search (PPO+MCTS) and Soft Actor-Critic (SAC). SAC achieves the highest success rates on two-variable targets, while PPO+MCTS scales to three variables and demonstrates steady improvement on harder instances. These results suggest that polynomial circuit synthesis is a compact, verifiable setting for studying self-improving search policies.
Authors: Akshaj Murhekar, Christina Liu, Abhijit Mishra, Shounak Roychowdhury, Jacek Gwizdka
Abstract: Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction. Most existing Brain-Computer Interface (BCI) approaches rely on memory-intensive fine-tuning of Large Language Models (LLMs) or encoder-decoder models on raw EEG signals, resulting in expensive training pipelines, limited accessibility, and potential exposure of sensitive neural data. We introduce SENSE (SEmantic Neural Sparse Extraction), a lightweight and privacy-preserving framework that translates non-invasive electroencephalography (EEG) into text without LLM fine-tuning. SENSE decouples decoding into two stages: on-device semantic retrieval and prompt-based language generation. EEG signals are locally mapped to a discrete textual space to extract a non-sensitive Bag-of-Words (BoW), which conditions an off-the-shelf LLM to synthesize fluent text in a zero-shot manner. The EEG-to-keyword module contains only ~6M parameters and runs fully on-device, ensuring raw neural signals remain local while only abstract semantic cues interact with language models. Evaluated on a 128-channel EEG dataset across six subjects, SENSE matches or surpasses the generative quality of fully fine-tuned baselines such as Thought2Text while substantially reducing computational overhead. By localizing neural decoding and sharing only derived textual cues, SENSE provides a scalable and privacy-aware retrieval-augmented architecture for next-generation BCIs.
Authors: Omar Erak, Omar Alhussein, Fang Fang, Sami Muhaidat
Abstract: Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit protection of connectivity or topology. This letter proposes TopoJSCC, a topology-aware DeepJSCC framework that integrates persistent-homology regularizers to end-to-end training. Specifically, we enforce topological consistency by penalizing Wasserstein distances between cubical persistence diagrams of original and reconstructed images, and between Vietoris--Rips persistence of latent features before and after the channel to promote a robust latent manifold. TopoJSCC is based on end-to-end learning and requires no side information. Experiments show improved topology preservation and peak signal-to-noise ratio (PSNR) in low signal-to-noise ratio (SNR) and bandwidth-ratio regimes.
Authors: Benjamin Hudson, Laurent Charlin, Emma Frejinger
Abstract: Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and leverage them to solve downstream problems, for example risk-averse formulations. We focus on human choice settings that can be formulated as (integer) linear programs. In such settings, existing inverse optimization and choice modelling methods infer preferences from observed choices but typically produce point estimates or fail to capture contextual shifts, making them unsuitable for risk-averse decision-making. Using a bounded-variance score function gradient estimator, we train a predictive model mapping contextual features to a rich class of parameterizable distributions. This approach yields a maximum likelihood estimate. The model generates scenarios for unseen contexts in the subsequent optimization phase. In a synthetic ridesharing environment, our approach reduces average post-decision surprise by up to 114$\times$ compared to a risk-neutral approach with perfect predictions and up to 25$\times$ compared to leading risk-averse baselines.
Authors: Yasi Zhang, Tianyu Chen, Mingyuan Zhou, Oscar Leong, Ying Nian Wu, Michal Lukasik
Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal structure inherent in regression tasks; for instance, they fail to recognize that predicting 4 is significantly better than predicting 1 when the ground truth is 5. Conversely, existing regression-aware approaches are often confined to Supervised Fine-Tuning (SFT), limiting their ability to explore optimal reasoning paths. To bridge this gap, we propose \textbf{REAL} (\underline{RE}gression-\underline{A}ware Reinforcement \underline{L}earning), a principled RL framework designed to optimize regression rewards, and also proven to be optimal for correlation metrics. A key technical challenge is that the regression objective is explicitly policy-dependent, thus invalidating standard policy gradient methods. To address this, we employ the generalized policy gradient estimator, which naturally decomposes optimization into two complementary components: (1) exploration over Chain-of-Thought (CoT) trajectory, and (2) regression-aware prediction refinement of the final score. Extensive experiments across model scales (8B to 32B) demonstrate that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods, exhibiting significantly better generalization on out-of-domain benchmarks. On Qwen3-32B specifically, we achieve gains of +8.40 Pearson and +7.20 Spearman correlation over the SFT baseline, and +18.30/+11.20 over the base model. These findings highlight the critical value of integrating regression objectives into RL exploration for accurate LLM evaluation.
Authors: Awatif Yasmin, Tarek Mahmud, Sana Alamgeer, Anne H. H. Ngu
Abstract: Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited by the scarcity of real-world fall data and the dominance of non-fall feedback samples. This imbalance biases the model toward routine activities and weakens its sensitivity to true fall events. To address this challenge, we propose a personalization framework that combines semi-supervised clustering with contrastive learning to identify and balance the most informative user feedback samples. The framework is evaluated under three retraining strategies, including Training from Scratch (TFS), Transfer Learning (TL), and Few-Shot Learning (FSL), to assess adaptability across learning paradigms. Real-time experiments with ten participants show that the TFS approach achieves the highest performance, with up to a 25% improvement over the baseline, while FSL achieves the second-highest performance with a 7% improvement, demonstrating the effectiveness of selective personalization for real-world deployment.
Authors: Maxim Khomiakov, Jes Frellsen
Abstract: Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconfident, which makes deployment decisions difficult when external ground truth is limited. We propose a practical calibration protocol based on controlled input interventions: if noise severity increases, task performance should exhibit a statistically significant deterioration trend. We operationalize this with a slope-based hypothesis test over repeated trials, using signal-to-noise-ratio (SNR) perturbations for tabular data and lexical perturbations for text data. Across UCI tabular benchmarks and four text classification datasets, we find clear modality-dependent behavior. Our results reveal a modality gap: while text-based judges degrade predictably, the majority of tabular datasets show a lack of statistically significant performance deterioration even under significant signal-to-noise reduction. Interestingly we find that model performance is lower on datasets that are insensitive to noise interventions. We present a reproducible methodology and reporting protocol for robust LLM-judge calibration under distribution shift.
Authors: Cheng-Hsi Hsiao, Krishna Kumar, Ellen M. Rathje
Abstract: Explainable Boosting Machines (EBMs) provide transparent predictions through additive shape functions, enabling direct inspection of feature contributions. However, EBMs can learn non-physical relationships that reduce their reliability in natural hazard applications. This study presents a domain-informed framework to improve the physical consistency of EBMs for lateral spreading prediction. Our approach modifies learned shape functions based on domain knowledge. These modifications correct non-physical behavior while maintaining data-driven patterns. We apply the method to the 2011 Christchurch earthquake dataset and correct non-physical trends observed in the original EBM. The resulting model produces more physically consistent global and local explanations, with an acceptable tradeoff in accuracy (4--5\%).
Authors: Peng Xia, Jianwen Chen, Xinyu Yang, Haoqin Tu, Jiaqi Liu, Kaiwen Xiong, Siwei Han, Shi Qiu, Haonian Ji, Yuyin Zhou, Zeyu Zheng, Cihang Xie, Huaxiu Yao
Abstract: Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two complementary mechanisms. Skill-driven fast adaptation analyzes failure trajectories via an LLM evolver to synthesize new skills, enabling immediate improvement with zero downtime. Opportunistic policy optimization performs gradient-based updates via cloud LoRA fine-tuning and Reinforcement Learning with a Process Reward Model (RL-PRM). This is triggered during user-inactive windows by the Opportunistic Meta-Learning Scheduler (OMLS), which monitors system inactivity and calendar data. These mechanisms are mutually reinforcing: a refined policy generates better trajectories for skill synthesis, while richer skills provide higher-quality data for policy optimization. To prevent data contamination, a versioning mechanism separates support and query data. Built on a proxy-based architecture, MetaClaw scales to production-size LLMs without local GPUs. Experiments on MetaClaw-Bench and AutoResearchClaw show that skill-driven adaptation improves accuracy by up to 32% relative. The full pipeline advances Kimi-K2.5 accuracy from 21.4% to 40.6% and increases composite robustness by 18.3%. Code is available at https://github.com/aiming-lab/MetaClaw.
Authors: Tynan Perez, Rafael Gomez-Bombarelli
Abstract: The success of large-scale pretraining in NLP and computer vision has catalyzed growing efforts to develop analogous foundation models for the physical sciences. However, pretraining strategies using atomistic data remain underexplored. To date, large-scale supervised pretraining on DFT force-energy labels has provided the strongest performance gains to downstream property prediction, out-performing existing methods of self-supervised learning (SSL) which remain limited to ground-state geometries, and/or single domains of atomistic data. We address these shortcomings with Self-Conditioned Denoising (SCD), a backbone-agnostic reconstruction objective that utilizes self-embeddings for conditional denoising across any domain of atomistic data, including small molecules, proteins, periodic materials, and 'non-equilibrium' geometries. When controlled for backbone architecture and pretraining dataset, SCD significantly outperforms previous SSL methods on downstream benchmarks and matches or exceeds the performance of supervised force-energy pretraining. We show that a small, fast GNN pretrained by SCD can achieve competitive or superior performance to larger models pretrained on significantly larger labeled or unlabeled datasets, across tasks in multiple domains. Our code is available at: https://github.com/TyJPerez/SelfConditionedDenoisingAtoms
URLs: https://github.com/TyJPerez/SelfConditionedDenoisingAtoms
Authors: Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati, Nina Rouhani, Morteza Dehghani
Abstract: The real world is non-stationary and infinitely complex, requiring intelligent agents to learn continually without the prohibitive cost of retraining from scratch. While online continual learning offers a framework for this setting, learning new information often interferes with previously acquired knowledge, causes forgetting and degraded generalization. To address this, we propose Abstraction-Augmented Training (AAT), a loss-level modification encouraging models to capture the latent relational structure shared across examples. By jointly optimizing over concrete instances and their abstract representations, AAT introduces a memory-efficient inductive bias that stabilizes learning in strictly online data streams, eliminating the need for a replay buffer. To capture the multi-faceted nature of abstraction, we introduce and evaluate AAT on two benchmarks: a controlled relational dataset where abstraction is realized through entity masking, and a narrative dataset where abstraction is expressed through shared proverbs. Our results show that AAT achieves performance comparable to or exceeding strong experience replay (ER) baselines, despite requiring zero additional memory and only minimal changes to the training objective. This work highlights structural abstraction as a powerful, memory-free alternative to ER.
Authors: Parsa Mirtaheri, Mikhail Belkin
Abstract: Large language models (LLMs) can produce chains of thought (CoT) that do not accurately reflect the actual factors driving their answers. In multiple-choice settings with an injected hint favoring a particular option, models may shift their final answer toward the hinted option and produce a CoT that rationalizes the response without acknowledging the hint - an instance of motivated reasoning. We study this phenomenon across multiple LLM families and datasets demonstrating that motivated reasoning can be identified by probing internal activations even in cases when it cannot be easily determined from CoT. Using supervised probes trained on the model's residual stream, we show that (i) pre-generation probes, applied before any CoT tokens are generated, predict motivated reasoning as well as a LLM-based CoT monitor that accesses the full CoT trace, and (ii) post-generation probes, applied after CoT generation, outperform the same monitor. Together, these results show that motivated reasoning is detected more reliably from internal representations than from CoT monitoring. Moreover, pre-generation probing can flag motivated behavior early, potentially avoiding unnecessary generation.
Authors: David Restrepo, Miguel L Martins, Chenwei Wu, Luis Filipe Nakayama, Diego M Lopez, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante
Abstract: Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contributing to cross-modal separation known as the modality gap. While this phenomenon has been widely observed, its practical impact on supervised multimodal learning -particularly in medical domains- remains unclear. In this work, we introduce a lightweight post-hoc mechanism that keeps pretrained VLM encoders frozen while continuously controlling cross-modal separation through a single hyperparameter {{\lambda}}. This enables systematic analysis of how the modality gap affects downstream multimodal performance without expensive retraining. We evaluate generalist (CLIP, SigLIP) and medically specialized (BioMedCLIP, MedSigLIP) models across diverse medical and natural datasets in a supervised multimodal settings. Results consistently show that reducing excessive modality gap improves downstream performance, with medical datasets exhibiting stronger sensitivity to gap modulation; however, fully collapsing the gap is not always optimal, and intermediate, task-dependent separation yields the best results. These findings position the modality gap as a tunable property of multimodal representations rather than a quantity that should be universally minimized.
Authors: Truong-Son Hy
Abstract: We propose Q-BIOLAT, a framework for modeling and optimizing protein fitness landscapes in binary latent spaces. Starting from protein sequences, we leverage pretrained protein language models to obtain continuous embeddings, which are then transformed into compact binary latent representations. In this space, protein fitness is approximated using a quadratic unconstrained binary optimization (QUBO) model, enabling efficient combinatorial search via classical heuristics such as simulated annealing and genetic algorithms. On the ProteinGym benchmark, we demonstrate that Q-BIOLAT captures meaningful structure in protein fitness landscapes and enables the identification of high-fitness variants. Despite using a simple binarization scheme, our method consistently retrieves sequences whose nearest neighbors lie within the top fraction of the training fitness distribution, particularly under the strongest configurations. We further show that different optimization strategies exhibit distinct behaviors, with evolutionary search performing better in higher-dimensional latent spaces and local search remaining competitive in preserving realistic sequences. Beyond its empirical performance, Q-BIOLAT provides a natural bridge between protein representation learning and combinatorial optimization. By formulating protein fitness as a QUBO problem, our framework is directly compatible with emerging quantum annealing hardware, opening new directions for quantum-assisted protein engineering. Our implementation is publicly available at: https://github.com/HySonLab/Q-BIOLAT
Authors: Youssef Youssef, Jitin Singla
Abstract: Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. By maximizing mutual information between latent representations and clinical labels, the framework learns to filter anatomical "nuisance" variables. On the PTB-XL dataset, our method achieves approx. 76\% reduction in RMSE compared to state-of-the-art model in patient-independent setting. Cross-dataset evaluation on the PTB Diagnostic Database confirms superior generalization, bridging the gap between hardware portability and diagnostic-grade reconstruction.
Authors: Haoliang Sun, Qi Wei, Lei Feng, Yupeng Hu, Fan Liu, Hehe Fan, Yilong Yin
Abstract: Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have been broadly applied in prevailing approaches, which have been generally learned under the meta-learning scenario. Despite the robustness of noise achieved by the probabilistic meta-learning models, they usually suffer from model collapse that degenerates generalization performance. In this paper, we propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions as an amortized variational inference problem and derive the evidence lower bound under the meta-learning framework. Specifically, VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable, which can rectify the loss of the noisy sample with the extra randomness regularization and is, therefore, more robust to label noise. To achieve the inference of the rectifying vector, we approximate its conditional posterior with an amortization meta-network. By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function, which can significantly improve the generalization performance. The elaborated meta-network and prior network adhere to the smoothness assumption, enabling the generation of reliable rectification vectors. Given a set of clean meta-data, VRI can be efficiently meta-learned within the bi-level optimization programming. Besides, theoretical analysis guarantees that the meta-network can be efficiently learned with our algorithm. Comprehensive comparison experiments and analyses validate its effectiveness for robust learning with noisy labels, particularly in the presence of open-set noise.
Authors: Noam H. Rotenberg, Andreia V. Faria, Brian Caffo
Abstract: Ordinal data is widely prevalent in clinical and other domains, yet there is a lack of both modern, machine-learning based methods and publicly available software to address it. In this paper, we present a model-agnostic method of ordinal classification, which can apply any non-ordinal classification method in an ordinal fashion. We also provide an open-source implementation of these algorithms, in the form of a Python package. We apply these models on multiple real-world datasets to show their performance across domains. We show that they often outperform non-ordinal classification methods, especially when the number of datapoints is relatively small or when there are many classes of outcomes. This work, including the developed software, facilitates the use of modern, more powerful machine learning algorithms to handle ordinal data.
Authors: Zahin Sufiyan, Shadan Golestan, Yoshihiro Mitsuka, Shotaro Miwa, Osmar Zaiane
Abstract: Generative Flow Networks for continuous scenarios (CFlowNets) have shown promise in solving sequential decision-making tasks by learning stochastic policies using a flow and a retrieval network. Despite their demonstrated efficiency compared to state-of-the-art Reinforcement Learning (RL) algorithms, their practical application in robotic control tasks is constrained by the reliance on pre-training the retrieval network. This dependency poses challenges in dynamic robotic environments, where pre-training data may not be readily available or representative of the current environment. This paper introduces WINFlowNets, a novel CFlowNets framework that enables the co-training of flow and retrieval networks. WINFlowNets begins with a warm-up phase for the retrieval network to bootstrap its policy, followed by a shared training architecture and a shared replay buffer for co-training both networks. Experiments in simulated robotic environments demonstrate that WINFlowNets surpasses CFlowNets and state-of-the-art RL algorithms in terms of average reward and training stability. Furthermore, WINFlowNets exhibits strong adaptive capability in fault environments, making it suitable for tasks that demand quick adaptation with limited sample data. These findings highlight WINFlowNets' potential for deployment in dynamic and malfunction-prone robotic systems, where traditional pre-training or sample inefficient data collection may be impractical.
Authors: Sizhuang He, Yangtian Zhang, Shiyang Zhang, David van Dijk
Abstract: The finite symmetric group S_n provides a natural domain for permutations, yet learning probability distributions on S_n is challenging due to its factorially growing size and discrete, non-Euclidean structure. Recent permutation diffusion methods define forward noising via shuffle-based random walks (e.g., riffle shuffles) and learn reverse transitions with Plackett-Luce (PL) variants, but the resulting trajectories can be abrupt and increasingly hard to denoise as n grows. We propose Soft-Rank Diffusion, a discrete diffusion framework that replaces shuffle-based corruption with a structured soft-rank forward process: we lift permutations to a continuous latent representation of order by relaxing discrete ranks into soft ranks, yielding smoother and more tractable trajectories. For the reverse process, we introduce contextualized generalized Plackett-Luce (cGPL) denoisers that generalize prior PL-style parameterizations and improve expressivity for sequential decision structures. Experiments on sorting and combinatorial optimization benchmarks show that Soft-Rank Diffusion consistently outperforms prior diffusion baselines, with particularly strong gains in long-sequence and intrinsically sequential settings.
Authors: Hengyuan Zhang, Xinrong Chen, Zunhai Su, Xiao Liang, Jing Xiong, Wendong Xu, He Xiao, Chaofan Tao, Wei Zhang, Ruobing Xie, Lei Jiang, Hayden Kwok-Hay So, Ngai Wong
Abstract: Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing methods typically treat all intra-layer weight modules uniformly and rely on a single numerical property when estimating sensitivity, overlooking their distinct operational roles and structural characteristics. To address this, we propose NSDS, a novel calibration-free LMPQ framework driven by Numerical and Structural Dual-Sensitivity. Specifically, it first mechanistically decomposes each layer into distinct operational roles and quantifies their sensitivity from both numerical and structural perspectives. These dual-aspect scores are then aggregated into a unified layer-wise metric through a robust aggregation scheme based on MAD-Sigmoid and Soft-OR to guide bit allocation. Extensive experiments demonstrate that NSDS consistently achieves superior performance compared to various baselines across diverse models and downstream tasks, without relying on any calibration data.
Authors: Ziran Liu
Abstract: Internal noise in deep networks is usually inherited from heuristics such as dropout, hard masking, or additive perturbation. We ask two questions: what correlation geometry should internal noise have, and is the implemented perturbation compatible with the representations it acts on? We answer these questions through Variational Kernel Design (VKD), a framework in which a noise mechanism is specified by a law family, a correlation kernel, and an injection operator, and is derived from learning desiderata. In a solved spatial subfamily, a quadratic maximum-entropy principle over latent log-fields yields a Gaussian optimizer with precision given by the Dirichlet Laplacian, so the induced geometry is the Dirichlet Green kernel. Wick normalization then gives a canonical positive mean-one gate, Gaussian Chaos Noise (GCh). For the sample-wise gate used in practice, we prove exact Gaussian control of pairwise log-ratio deformation, margin-sensitive ranking stability, and an exact expected intrinsic roughness budget; hard binary masks instead induce singular or coherence-amplified distortions on positive coherent representations. On ImageNet and ImageNet-C, GCh consistently improves calibration and under shift also improves NLL at competitive accuracy.
Authors: Seyed Mohammad Asghari, Chris Chute, Vikranth Dwaracherla, Xiuyuan Lu, Mehdi Jafarnia, Victor Minden, Zheng Wen, Benjamin Van Roy
Abstract: We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates reward and language models as choice data is received. The reward model is fit to the choice data, while the language model is updated by a variation of reinforce, with reinforcement signals provided by the reward model. Several features enable the efficiency gains: a small affirmative nudge added to each reinforcement signal, an epistemic neural network that models reward uncertainty, and information-directed exploration. With Gemma large language models (LLMs), our algorithm matches the performance of offline RLHF trained on 200K labels using fewer than 20K labels, representing more than a 10x gain in data efficiency. Extrapolating from our results, we expect our algorithm trained on 1M labels to match offline RLHF trained on 1B labels. This represents a 1,000x gain. To our knowledge, these are the first results to demonstrate that such large improvements are possible.
Authors: Shuizhou Chen, Lang Yu, Kedu Jin, Songming Zhang, Hao Wu, Wenxuan Huang, Sheng Xu, Quan Qian, Qin Chen, Lei Bai, Siqi Sun, Zhangyang Gao
Abstract: Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations from single-cell measurements. In practice, however, large-scale perturbation prediction remains constrained by three coupled bottlenecks: inefficient training and inference pipelines, unstable modeling in high-dimensional sparse expression space, and evaluation protocols that overemphasize reconstruction-like accuracy while underestimating biological fidelity. In this work we present a specialized large-scale foundation model SCALE for virtual cell perturbation prediction that addresses the above limitations jointly. First, we build a BioNeMo-based training and inference framework that substantially improves data throughput, distributed scalability, and deployment efficiency, yielding 12.51* speedup on pretrain and 1.29* on inference over the prior SOTA pipeline under matched system settings. Second, we formulate perturbation prediction as conditional transport and implement it with a set-aware flow architecture that couples LLaMA-based cellular encoding with endpoint-oriented supervision. This design yields more stable training and stronger recovery of perturbation effects. Third, we evaluate the model on Tahoe-100M using a rigorous cell-level protocol centered on biologically meaningful metrics rather than reconstruction alone. On this benchmark, our model improves PDCorr by 12.02% and DE Overlap by 10.66% over STATE. Together, these results suggest that advancing virtual cells requires not only better generative objectives, but also the co-design of scalable infrastructure, stable transport modeling, and biologically faithful evaluation.
Authors: Rui Wu, Hong Xie, Yongjun Li
Abstract: Current continuous generative models (e.g., Diffusion Models, Flow Matching) implicitly assume that locally consistent causal mechanisms naturally yield globally coherent counterfactuals. In this paper, we prove that this assumption fails fundamentally when the causal graph exhibits non-trivial homology (e.g., structural conflicts or hidden confounders). We formalize structural causal models as cellular sheaves over Wasserstein spaces, providing a strict algebraic topological definition of cohomological obstructions in measure spaces. To ensure computational tractability and avoid deterministic singularities (which we define as manifold tearing), we introduce entropic regularization and derive the Entropic Wasserstein Causal Sheaf Laplacian, a novel system of coupled non-linear Fokker-Planck equations. Crucially, we prove an entropic pullback lemma for the first variation of pushforward measures. By integrating this with the Implicit Function Theorem (IFT) on Sinkhorn optimality conditions, we establish a direct algorithmic bridge to automatic differentiation (VJP), achieving O(1)-memory reverse-mode gradients strictly independent of the iteration horizon. Empirically, our framework successfully leverages thermodynamic noise to navigate topological barriers ("entropic tunneling") in high-dimensional scRNA-seq counterfactuals. Finally, we invert this theoretical framework to introduce the Topological Causal Score, demonstrating that our Sheaf Laplacian acts as a highly sensitive algebraic detector for topology-aware causal discovery.
Authors: Rui Wu, Hong Xie, Yongjun Li
Abstract: Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric challenges. We establish the fundamental limits of such interventions. We define the Counterfactual Event Horizon and prove the Manifold Tearing Theorem: deterministic flows inevitably develop finite-time singularities under extreme interventions. We establish the Causal Uncertainty Principle for the trade-off between intervention extremity and identity preservation. Finally, we introduce Geometry-Aware Causal Flow (GACF), a scalable algorithm that utilizes a topological radar to bypass manifold tearing, validated on high-dimensional scRNA-seq data.
Authors: Yaozhong Shi, Grigorios Lavrentiadis, Konstantinos Tsalouchidis, Zachary E. Ross, David McCallen, Caifeng Zou, Kamyar Azizzadenesheli, Domniki Asimaki
Abstract: Earthquake hazard analysis and design of spatially distributed infrastructure, such as power grids and energy pipeline networks, require scenario-specific ground-motion time histories with realistic frequency content and spatiotemporal coherence. However, producing the large ensembles needed for uncertainty quantification with physics-based simulations is computationally intensive and impractical for engineering workflows. To address this challenge, we introduce Ground-Motion Flow (GMFlow), a physics-inspired latent operator flow matching framework that generates realistic, large-scale regional ground-motion time-histories conditioned on physical parameters. Validated on simulated earthquake scenarios in the San Francisco Bay Area, GMFlow generates spatially coherent ground motion across more than 9 million grid points in seconds, achieving a 10,000-fold speedup over the simulation workflow, which opens a path toward rapid and uncertainty-aware hazard assessment for distributed infrastructure. More broadly, GMFlow advances mesh-agnostic functional generative modeling and could potentially be extended to the synthesis of large-scale spatiotemporal physical fields in diverse scientific domains.
Authors: Alireza Sadeghi, Wael AbdAlmageed
Abstract: Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples or modify existing data based on the causal relationships among latent variables. To facilitate the development and evaluation of these models, a variety of synthetic and real-world datasets have been proposed, each with distinct advantages and limitations. For practical applications, CRL models must perform robustly across multiple evaluation directions, including reconstruction, disentanglement, causal discovery, and counterfactual reasoning, using appropriate metrics for each direction. However, this multi-directional evaluation can complicate model comparison, as a model may excel in some direction while under-performing in others. Another significant challenge in this field is reproducibility: the source code corresponding to published results must be publicly available, and repeated runs should yield performance consistent with the original reports. In this study, we critically analyzed the synthetic and real-world datasets currently employed in the literature, highlighting their limitations and proposing a set of essential characteristics for suitable datasets in CRL model development. We also introduce a single aggregate metric that consolidates performance across all evaluation directions, providing a comprehensive score for each model. Finally, we reviewed existing implementations from the literature and assessed them in terms of reproducibility, identifying gaps and best practices in the field.
Authors: Dibakar Sigdel
Abstract: Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series. We introduce the \textbf{Phasor Transformer} block, a phase-native alternative representing sequence states on the unit-circle manifold $S^1$. Each block combines lightweight trainable phase-shifts with parameter-free Discrete Fourier Transform (DFT) token coupling, achieving global $\mathcal{O}(N\log N)$ mixing without explicit attention maps. Stacking these blocks defines the \textbf{Large Phasor Model (LPM)}. We validate LPM on autoregressive time-series prediction over synthetic multi-frequency benchmarks. Operating with a highly compact parameter budget, LPM learns stable global dynamics and achieves competitive forecasting behavior compared to conventional self-attention baselines. Our results establish an explicit efficiency-performance frontier, demonstrating that large-model scaling for time-series can emerge from geometry-constrained phase computation with deterministic global coupling, offering a practical path toward scalable temporal modeling in oscillatory domains.
Authors: Yue Hu, Jialiang Tang, Siwei Yu, Baosheng Yu, Jing Zhang, Dacheng Tao
Abstract: Non-stationarity is a fundamental challenge in multivariate long-term time series forecasting, often manifested as rapid changes in amplitude and phase. These variations lead to severe distribution shifts and consequently degrade predictive performance. Existing normalization-based methods primarily rely on first- and second-order statistics, implicitly assuming that distributions evolve smoothly and overlooking fine-grained temporal dynamics. To address these limitations, we propose TimeAPN, an Adaptive Amplitude-Phase Non-Stationarity Normalization framework that explicitly models and predicts non-stationary factors from both the time and frequency domains. Specifically, TimeAPN first models the mean sequence jointly in the time and frequency domains, and then forecasts its evolution over future horizons. Meanwhile, phase information is extracted in the frequency domain, and the phase discrepancy between the predicted and ground-truth future sequences is explicitly modeled to capture temporal misalignment. Furthermore, TimeAPN incorporates amplitude information into an adaptive normalization mechanism, enabling the model to effectively account for abrupt fluctuations in signal energy. The predicted non-stationary factors are subsequently integrated with the backbone forecasting outputs through a collaborative de-normalization process to reconstruct the final non-stationary time series. The proposed framework is model-agnostic and can be seamlessly integrated with various forecasting backbones. Extensive experiments on seven real-world multivariate datasets demonstrate that TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons and outperforms state-of-the-art reversible normalization methods.
Authors: Linxiao Yang, Xue Jiang, Gezheng Xu, Tian Zhou, Min Yang, ZhaoYang Zhu, Linyuan Geng, Zhipeng Zeng, Qiming Chen, Xinyue Gu, Rong Jin, Liang Sun
Abstract: Transformers enable in-context learning (ICL) for rapid, gradient-free adaptation in time series forecasting, yet most ICL-style approaches rely on tabularized, hand-crafted features, while end-to-end sequence models lack inference-time adaptation. We bridge this gap with a unified framework, Baguan-TS, which integrates the raw-sequence representation learning with ICL, instantiated by a 3D Transformer that attends jointly over temporal, variable, and context axes. To make this high-capacity model practical, we tackle two key hurdles: (i) calibration and training stability, improved with a feature-agnostic, target-space retrieval-based local calibration; and (ii) output oversmoothing, mitigated via context-overfitting strategy. On public benchmark with covariates, Baguan-TS consistently outperforms established baselines, achieving the highest win rate and significant reductions in both point and probabilistic forecasting metrics. Further evaluations across diverse real-world energy datasets demonstrate its robustness, yielding substantial improvements.
Authors: Hao Ma, Zhiqiang Pu, Xiaolin Ai, Huimu Wang
Abstract: We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level guidance for the Soft Actor-Critic (SAC) algorithm. The LLM-based supervisor analyzes the most recent trajectory using state information and visual replays, offering action-level interventions that enable targeted exploration. Furthermore, we provide a theoretical analysis of GuidedSAC, proving that it preserves the convergence guarantees of SAC while improving convergence speed. Through experiments in both discrete and continuous control environments, including toy text tasks and complex MuJoCo benchmarks, we demonstrate that GuidedSAC consistently outperforms standard SAC and state-of-the-art exploration-enhanced variants (e.g., RND, ICM, and E3B) in terms of sample efficiency and final performance.
Authors: Ahmet Kaplan
Abstract: This study explores the combination of automated machine learning (AutoML) with model-based deep unfolding (DU) for optimizing wireless beamforming and waveforms. We convert the iterative proximal gradient descent (PGD) algorithm into a deep neural network, wherein the parameters of each layer are learned instead of being predetermined. Additionally, we enhance the architecture by incorporating a hybrid layer that performs a learnable linear gradient transformation prior to the proximal projection. By utilizing AutoGluon with a tree-structured parzen estimator (TPE) for hyperparameter optimization (HPO) across an expanded search space, which includes network depth, step-size initialization, optimizer, learning rate scheduler, layer type, and post-gradient activation, the proposed auto-unrolled PGD (Auto-PGD) achieves 98.8% of the spectral efficiency of a traditional 200-iteration PGD solver using only five unrolled layers, while requiring only 100 training samples. We also address a gradient normalization issue to ensure consistent performance during training and evaluation, and we illustrate per-layer sum-rate logging as a tool for transparency. These contributions highlight a notable reduction in the amount of training data and inference cost required, while maintaining high interpretability compared to conventional black-box architectures.
Authors: Charuka Herath, Yogachandran Rahulamathavan, Varuna De Silva, Sangarapillai Lambotharan
Abstract: Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are increasingly available on edge devices, their potential to reduce the energy overhead of fine-tuning remains underexplored. In this work, we propose QuantFL, a sustainable FL framework that leverages pre-trained initialisation to enable aggressive, computationally lightweight quantisation. We demonstrate that pre-training naturally concentrates update statistics, allowing us to use memory-efficient bucket quantisation without the energy-intensive overhead of complex error-feedback mechanisms. On MNIST and CIFAR-100, QuantFL reduces total communication by 40\% ($\simeq40\%$ total-bit reduction with full-precision downlink; $\geq80\%$ on uplink or when downlink is quantised) while matching or exceeding uncompressed baselines under strict bandwidth budgets; BU attains 89.00\% (MNIST) and 66.89\% (CIFAR-100) test accuracy with orders of magnitude fewer bits. We also account for uplink and downlink costs and provide ablations on quantisation levels and initialisation. QuantFL delivers a practical, "green" recipe for scalable training on battery-constrained IoT networks.
Authors: Luca Pellegrini
Abstract: Neural Operators (NOs) are a powerful deep learning framework designed to learn the solution operator that arise from partial differential equations. This study investigates NOs ability to capture the stiff spatio-temporal dynamics of the FitzHugh-Nagumo model, which describes excitable cells. A key contribution of this work is evaluating the translation invariance using a novel training strategy. NOs are trained using an applied current with varying spatial locations and intensities at a fixed time, and the test set introduces a more challenging out-of-distribution scenario in which the applied current is translated in both time and space. This approach significantly reduces the computational cost of dataset generation. Moreover we benchmark seven NOs architectures: Convolutional Neural Operators (CNOs), Deep Operator Networks (DONs), DONs with CNN encoder (DONs-CNN), Proper Orthogonal Decomposition DONs (POD-DONs), Fourier Neural Operators (FNOs), Tucker Tensorized FNOs (TFNOs), Localized Neural Operators (LocalNOs). We evaluated these models based on training and test accuracy, efficiency, and inference speed. Our results reveal that CNOs performs well on translated test dynamics. However, they require higher training costs, though their performance on the training set is similar to that of the other considered architectures. In contrast, FNOs achieve the lowest training error, but have the highest inference time. Regarding the translated dynamics, FNOs and their variants provide less accurate predictions. Finally, DONs and their variants demonstrate high efficiency in both training and inference, however they do not generalize well to the test set. These findings highlight the current capabilities and limitations of NOs in capturing complex ionic model dynamics and provide a comprehensive benchmark including their application to scenarios involving translated dynamics.
Authors: Binqing Wu, Zongjiang Shang, Shiyu Liu, Jianlong Huang, Jiahui Xu, Ling Chen
Abstract: Accurate air quality forecasting is essential for public health and environmental sustainability, but remains challenging due to the complex pollutant dynamics. Existing deep learning methods often model pollutant dynamics as an instantaneous process, overlooking the intrinsic delays in pollutant propagation. Thus, we propose AirDDE, the first neural delay differential equation framework in this task that integrates delay modeling into a continuous-time pollutant evolution under physical guidance. Specifically, two novel components are introduced: (1) a memory-augmented attention module that retrieves globally and locally historical features, which can adaptively capture delay effects modulated by multifactor data; and (2) a physics-guided delay evolving function, grounded in the diffusion-advection equation, that models diffusion, delayed advection, and source/sink terms, which can capture delay-aware pollutant accumulation patterns with physical plausibility. Extensive experiments on three real-world datasets demonstrate that AirDDE achieves the state-of-the-art forecasting performance with an average MAE reduction of 8.79\% over the best baselines. The code is available at https://github.com/w2obin/airdde-aaai.
Authors: Mohammad Nooraiepour
Abstract: Accurate prediction of permeability tensors from pore-scale microstructure images is essential for subsurface flow modeling, yet direct numerical simulation requires hours per sample, fundamentally limiting large-scale uncertainty quantification and reservoir optimization workflows. A physics-informed deep learning framework is presented that resolves this bottleneck by combining a MaxViT hybrid CNN-Transformer architecture with progressive transfer learning and differentiable physical constraints. MaxViT's multi-axis attention mechanism simultaneously resolves grain-scale pore-throat geometry via block-local operations and REV-scale connectivity statistics through grid-global operations, providing the spatial hierarchy that permeability tensor prediction physically requires. Training on 20000 synthetic porous media samples spanning three orders of magnitude in permeability, a three-phase progressive curriculum advances from an ImageNet-pretrained baseline with D4-equivariant augmentation and tensor transformation, through component-weighted loss prioritizing off-diagonal coupling, to frozen-backbone transfer learning with porosity conditioning via Feature-wise Linear Modulation (FiLM). Onsager reciprocity and positive definiteness are enforced via differentiable penalty terms. On a held-out test set of 4000 samples, the framework achieves variance-weighted R2 = 0.9960 (R2_Kxx = 0.9967, R2_Kxy = 0.9758), a 33% reduction in unexplained variance over the supervised baseline. The results offer three transferable principles for physics-informed scientific machine learning: large-scale visual pretraining transfers effectively across domain boundaries; physical constraints are most robustly integrated as differentiable architectural components; and progressive training guided by diagnostic failure-mode analysis enables unambiguous attribution of performance gains across methodological stages.
Authors: Alexander K\"ohler, Michael Breu{\ss}
Abstract: In many CAD-based applications, complex geometries are defined by a high number of design parameters. This leads to high-dimensional design spaces that are challenging for downstream engineering processes like simulations, optimization, and design exploration tasks. Therefore, dimension reduction methods such as principal component analysis (PCA) are used. The PCA identifies dominant modes of geometric variation and yields a compact representation of the geometry. While classical PCA excels in the compact representation part, it does not directly recover underlying design parameters of a generated geometry. In this work, we deal with the problem of estimating design parameters from PCA-based representations. Analyzing a recent modification of the PCA dedicated to our field of application, we show that the results are actually identical to the standard PCA. We investigate limitations of this approach and present reasonable conditions under which accurate, interpretable parameter estimation can be obtained. With the help of dedicated experiments, we take a more in-depth look at every stage of the PCA and the possible changes of the geometry during these processes.
Authors: Isabella Marasco, Davide Evangelista, Elena Loli Piccolomini, Michele Colajanni
Abstract: Artificial intelligence systems predominantly rely on static data distributions, making them ineffective in dynamic real-world environments, such as cybersecurity, autonomous transportation, or finance, where data shifts frequently. Continual learning offers a potential solution by enabling models to learn from sequential data while retaining prior knowledge. However, a critical and underexplored issue in this domain is data normalization. Conventional normalization methods, such as min-max scaling, presuppose access to the entire dataset, which is incongruent with the sequential nature of continual learning. In this paper we introduce Continual Learning Adaptive Normalization (CLeAN), a novel adaptive normalization technique designed for continual learning in tabular data. CLeAN involves the estimation of global feature scales using learnable parameters that are updated via an Exponential Moving Average (EMA) module, enabling the model to adapt to evolving data distributions. Through comprehensive evaluations on two datasets and various continual learning strategies, including Resevoir Experience Replay, A-GEM, and EwC we demonstrate that CLeAN not only improves model performance on new data but also mitigates catastrophic forgetting. The findings underscore the importance of adaptive normalization in enhancing the stability and effectiveness of tabular data, offering a novel perspective on the use of normalization to preserve knowledge in dynamic learning environments.
Authors: Lanlan Yu, Quan-Hui Liu, Haoyue Zheng, Xinfu Yang
Abstract: Estimating time-varying reproduction numbers from epidemic incidence data is a central task in infectious disease surveillance, yet it poses an inherently ill-posed inverse problem. Existing approaches often rely on strong structural assumptions derived from epidemiological models, which can limit their ability to adapt to non-stationary transmission dynamics induced by interventions or behavioral changes, leading to delayed detection of regime shifts and degraded estimation accuracy. In this work, we propose a Conditional Inverse Reproduction Learning framework (CIRL) that addresses the inverse problem by learning a {conditional mapping} from historical incidence patterns and explicit time information to latent reproduction numbers. Rather than imposing strongly enforced parametric constraints, CIRL softly integrates epidemiological structure with flexible likelihood-based statistical modeling, using the renewal equation as a forward operator to enforce dynamical consistency. The resulting framework combines epidemiologically grounded constraints with data-driven temporal representations, producing reproduction number estimates that are robust to observation noise while remaining responsive to abrupt transmission changes and zero-inflated incidence observations. Experiments on synthetic epidemics with controlled regime changes and real-world SARS and COVID-19 data demonstrate the effectiveness of the proposed approach.
Authors: Simon Kl\"uttermann, Tim Katzke, Phuong Huong Nguyen, Emmanuel M\"uller
Abstract: Tabular foundation models, specifically Prior-Data Fitted Networks (PFNs), have revolutionized outlier detection (OD) by enabling unsupervised zero-shot adaptation to new datasets without training. However, despite their predictive power, these models typically function as opaque black boxes, outputting scalar outlier scores that lack the operational context required for safety-critical decision-making. Existing post-hoc explanation methods are often computationally prohibitive for real-time deployment or fail to capture the epistemic uncertainty inherent in zero-shot inference. In this work, we introduce FoMo-X, a modular framework that equips OD foundation models with intrinsic, lightweight diagnostic capabilities. We leverage the insight that the frozen embeddings of a pretrained PFN backbone already encode rich, context-conditioned relational information. FoMo-X attaches auxiliary diagnostic heads to these embeddings, trained offline using the same generative simulator prior as the backbone. This allows us to distill computationally expensive properties, such as Monte Carlo dropout based epistemic uncertainty, into a deterministic, single-pass inference. We instantiate FoMo-X with two novel heads: a Severity Head that discretizes deviations into interpretable risk tiers, and an Uncertainty Head that provides calibrated confidence measures. Extensive evaluation on synthetic and real-world benchmarks (ADBench) demonstrates that FoMo-X recovers ground-truth diagnostic signals with high fidelity and negligible inference overhead. By bridging the gap between foundation model performance and operational explainability, FoMo-X offers a scalable path toward trustworthy, zero-shot outlier detection.
Authors: Md Maruf Hossain, Tim Katzke, Simon Kl\"uttermann, Emmanuel M\"uller
Abstract: We propose SYRAN, an unsupervised anomaly detection method based on symbolic regression. Instead of encoding normal patterns in an opaque, high-dimensional model, our method learns an ensemble of human-readable equations that describe symbolic invariants: functions that are approximately constant on normal data. Deviations from these invariants yield anomaly scores, so that the detection logic is interpretable by construction, rather than via post-hoc explanation. Experimental results demonstrate that SYRAN is highly interpretable, providing equations that correspond to known scientific or medical relationships, and maintains strong anomaly detection performance comparable to that of state-of-the-art methods.
Authors: Felix Schur
Abstract: Can latent actions and environment dynamics be recovered from offline trajectories when actions are never observed? We study this question in a setting where trajectories are action-free but tagged with demonstrator identity. We assume that each demonstrator follows a distinct policy, while the environment dynamics are shared across demonstrators and identity affects the next observation only through the chosen action. Under these assumptions, the conditional next-observation distribution $p(o_{t+1}\mid o_t,e)$ is a mixture of latent action-conditioned transition kernels with demonstrator-specific mixing weights. We show that this induces, for each state, a column-stochastic nonnegative matrix factorization of the observable conditional distribution. Using sufficiently scattered policy diversity and rank conditions, we prove that the latent transitions and demonstrator policies are identifiable up to permutation of the latent action labels. We extend the result to continuous observation spaces via a Gram-determinant minimum-volume criterion, and show that continuity of the transition map over a connected state space upgrades local permutation ambiguities to a single global permutation. A small amount of labeled action data then suffices to fix this final ambiguity. These results establish demonstrator diversity as a principled source of identifiability for learning latent actions and dynamics from offline RL data.
Authors: Wenhan Cao, Keyu Yan, Lin Zhao
Abstract: We present a drifting-based framework for amortized sampling of Boltzmann distributions defined by energy functions. The method trains a one-step neural generator by projecting samples along a Gaussian-smoothed score field from the current model distribution toward the target Boltzmann distribution. For targets specified only up to an unknown normalization constant, we derive a practical target-side drift from a smoothed energy and use two estimators: a local importance-sampling mean-shift estimator and a second-order curvature-corrected approximation. Combined with a mini-batch Gaussian mean-shift estimate of the sampler-side smoothed score, this yields a simple stop-gradient objective for stable one-step training. On a four-mode Gaussian-mixture Boltzmann target, our sampler achieves mean error $0.0754$, covariance error $0.0425$, and RBF MMD $0.0020$. Additional double-well and banana targets show that the same formulation also handles nonconvex and curved low-energy geometries. Overall, the results support drifting as an effective way to amortize iterative sampling from Boltzmann distributions into a single forward pass at test time.
Authors: Nishant Kumar, Franck Kerherv\'e, Lionel Agostini, Laurent Cordier
Abstract: Climate change and the rapid growth of urban populations are intensifying environmental stresses within cities, making the behavior of urban atmospheric flows a critical factor in public health, energy use, and overall livability. This study targets to develop fast and accurate models of urban pollutant dispersion to support decision-makers, enabling them to implement mitigation measures in a timely and cost-effective manner. To reach this goal, an end-to-end data-driven approach is proposed to model and predict the airflow and pollutant dispersion in a street canyon in skimming flow regime. A series of time-resolved snapshots obtained from large eddy simulation (LES) serves as the database. The proposed framework is based on four fundamental steps. Firstly, a reduced basis is obtained by spectral proper orthogonal decomposition (SPOD) of the database. The projection of the time series snapshot data onto the SPOD modes (time-domain approach) provides the temporal coefficients of the dynamics. Secondly, a nonlinear compression of the temporal coefficients is performed by autoencoder to reduce further the dimensionality of the problem. Thirdly, a reduced-order model (ROM) is learned in the latent space using Long Short-Term Memory (LSTM) netowrks. Finally, the pollutant dispersion is estimated from the predicted velocity field through convolutional neural network that maps both fields. The results demonstrate the efficacy of the model in predicting the instantaneous as well as statistically stationary fields over long time horizon.
Authors: Cai Xu, Changhao Sun, Ziyu Guan, Wei Zhao
Abstract: Multi-view learning primarily aims to fuse multiple features to describe data comprehensively. Most prior studies implicitly assume that different views share similar dimensions. In practice, however, severe dimensional disparities often exist among different views, leading to the unbalanced multi-view learning issue. For example, in emotion recognition tasks, video frames often reach dimensions of $10^6$, while physiological signals comprise only $10^1$ dimensions. Existing methods typically face two main challenges for this problem: (1) They often bias towards high-dimensional data, overlooking the low-dimensional views. (2) They struggle to effectively align representations under extreme dimensional imbalance, which introduces severe redundancy into the low-dimensional ones. To address these issues, we propose the Adaptive Multi-view Sparsity Learning (AdaMuS) framework. First, to prevent ignoring the information of low-dimensional views, we construct view-specific encoders to map them into a unified dimensional space. Given that mapping low-dimensional data to a high-dimensional space often causes severe overfitting, we design a parameter-free pruning method to adaptively remove redundant parameters in the encoders. Furthermore, we propose a sparse fusion paradigm that flexibly suppresses redundant dimensions and effectively aligns each view. Additionally, to learn representations with stronger generalization, we propose a self-supervised learning paradigm that obtains supervision information by constructing similarity graphs. Extensive evaluations on a synthetic toy dataset and seven real-world benchmarks demonstrate that AdaMuS consistently achieves superior performance and exhibits strong generalization across both classification and semantic segmentation tasks.
Authors: Dilxat Muhtar, Jiashun Liu, Wei Gao, Weixun Wang, Shaopan Xiong, Ju Huang, Siran Yang, Wenbo Su, Jiamang Wang, Ling Pan, Bo Zheng
Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior experience across episodes. While augmenting agents with historical experience offers a promising remedy, existing approaches suffer from a critical weakness: the experience distilled from history is either stored statically or fail to coevolve with the improving actor, causing a progressive misalignment between the experience and the actor's evolving capability that diminishes its utility over the course of training. Inspired by complementary learning systems in neuroscience, we present Complementary RL to achieve seamless co-evolution of an experience extractor and a policy actor within the RL optimization loop. Specifically, the actor is optimized via sparse outcome-based rewards, while the experience extractor is optimized according to whether its distilled experiences demonstrably contribute to the actor's success, thereby evolving its experience management strategy in lockstep with the actor's growing capabilities. Empirically, Complementary RL outperforms outcome-based agentic RL baselines that do not learn from experience, achieving 10% performance improvement in single-task scenarios and exhibits robust scalability in multi-task settings. These results establish Complementary RL as a paradigm for efficient experience-driven agent learning.
Authors: Zirui Gong, Leo Yu Zhang, Yanjun Zhang, Viet Vo, Tianqing Zhu, Shirui Pan, Cong Wang
Abstract: Federated Learning (FL) enables collaborative model training by sharing model updates instead of raw data, aiming to protect user privacy. However, recent studies reveal that these shared updates can inadvertently leak sensitive training data through gradient inversion attacks (GIAs). Among them, active GIAs are particularly powerful, enabling high-fidelity reconstruction of individual samples even under large batch sizes. Nevertheless, existing approaches often require architectural modifications, which limit their practical applicability. In this work, we bridge this gap by introducing the Activation REcovery via Sparse inversion (ARES) attack, an active GIA designed to reconstruct training samples from large training batches without requiring architectural modifications. Specifically, we formulate the recovery problem as a noisy sparse recovery task and solve it using the generalized Least Absolute Shrinkage and Selection Operator (Lasso). To extend the attack to multi-sample recovery, ARES incorporates the imprint method to disentangle activations, enabling scalable per-sample reconstruction. We further establish the expected recovery rate and derive an upper bound on the reconstruction error, providing theoretical guarantees for the ARES attack. Extensive experiments on CNNs and MLPs demonstrate that ARES achieves high-fidelity reconstruction across diverse datasets, significantly outperforming prior GIAs under large batch sizes and realistic FL settings. Our results highlight that intermediate activations pose a serious and underestimated privacy risk in FL, underscoring the urgent need for stronger defenses.
Authors: Sinan Ibrahim, Gr\'egoire Ouerdane, Hadi Salloum, Henni Ouerdane, Stefan Streif, Pavel Osinenko
Abstract: The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sensitive to environmental design, reward structures, and stochasticity inherent in both algorithmic learning and environmental dynamics. To manage this complexity, we introduce a rigorous benchmarking framework by extending converse optimality to discrete-time, control-affine, nonlinear systems with noise. Our framework provides necessary and sufficient conditions, under which a prescribed value function and policy are optimal for constructed systems, enabling the systematic generation of benchmark families via homotopy variations and randomized parameters. We validate it by automatically constructing diverse environments, demonstrating our framework's capacity for a controlled and comprehensive evaluation across algorithms. By assessing standard methods against a ground-truth optimum, our work delivers a reproducible foundation for precise and rigorous RL benchmarking.
Authors: Aleksander Ogonowski, Konrad Klimaszewski, Przemys{\l}aw Rokita
Abstract: We present DSS-GAN, the first generative adversarial network to employ Mamba as a hierarchical generator backbone for noise-to-image synthesis. The central contribution is Directional Latent Routing (DLR), a novel conditioning mechanism that decomposes the latent vector into direction-specific subvectors, each jointly projected with a class embedding to produce a feature-wise affine modulation of the corresponding Mamba scan. Unlike conventional class conditioning that injects a global signal, DLR couples class identity and latent structure along distinct spatial axes of the feature map, applied consistently across all generative scales. DSS-GAN achieves improved FID, KID, and precision-recall scores compared to StyleGAN2-ADA across multiple tested datasets. Analysis of the latent space reveals that directional subvectors exhibit measurable specialization: perturbations along individual components produce structured, direction-correlated changes in the synthesized image.
Authors: Ting Gao, Stavros Orfanoudakis, Nan Lin, Elvin Isufi, Winnie Daamen, Serge Hoogendoorn
Abstract: Diffusion-based policies have gained significant popularity in Reinforcement Learning (RL) due to their ability to represent complex, non-Gaussian distributions. Stochastic Differential Equation (SDE)-based diffusion policies often rely on indirect entropy control due to the intractability of the exact entropy, while also suffering from computationally prohibitive policy gradients through the iterative denoising chain. To overcome these issues, we propose Flow Matching Policy with Entropy Regularization (FMER), an Ordinary Differential Equation (ODE)-based online RL framework. FMER parameterizes the policy via flow matching and samples actions along a straight probability path, motivated by optimal transport. FMER leverages the model's generative nature to construct an advantage-weighted target velocity field from a candidate set, steering policy updates toward high-value regions. By deriving a tractable entropy objective, FMER enables principled maximum-entropy optimization for enhanced exploration. Experiments on sparse multi-goal FrankaKitchen benchmarks demonstrate that FMER outperforms state-of-the-art methods, while remaining competitive on standard MuJoco benchmarks. Moreover, FMER reduces training time by 7x compared to heavy diffusion baselines (QVPO) and 10-15% relative to efficient variants.
Authors: Chinenye Omejieke, Shuyao Chen, Xia Cui
Abstract: We present a practical, reproducible framework for identifying undervalued football players grounded in objective mispricing. Instead of relying on subjective expert labels, we estimate an expected market value from structured data (historical market dynamics, biographical and contract features, transfer history) and compare it to the observed valuation to define mispricing. We then assess whether news-derived Natural Language Processing (NLP) features (i.e., sentiment statistics and semantic embeddings from football articles) complement market signals for shortlisting undervalued players. Using a chronological (leakage-aware) evaluation, gradient-boosted regression explains a large share of the variance in log-transformed market value. For undervaluation shortlisting, ROC-AUC-based ablations show that market dynamics are the primary signal, while NLP features provide consistent, secondary gains that improve robustness and interpretability. SHAP analyses suggest the dominance of market trends and age, with news-derived volatility cues amplifying signals in high-uncertainty regimes. The proposed pipeline is designed for decision support in scouting workflows, emphasizing ranking/shortlisting over hard classification thresholds, and includes a concise reproducibility and ethics statement.
Authors: Joohyoung Jeon, Hongchul Lee
Abstract: For LLM trading agents to be genuinely trustworthy, they must demonstrate understanding of market dynamics rather than exploitation of memorized ticker associations. Building responsible multi-agent systems demands rigorous signal validation: proving that predictions reflect legitimate patterns, not pre-trained recall. We address two sources of spurious performance: memorization bias from ticker-specific pre-training, and survivorship bias from flawed backtesting. Our approach is to blindfold the agents--anonymizing all identifiers--and verify whether meaningful signals persist. BlindTrade anonymizes tickers and company names, and four LLM agents output scores along with reasoning. We construct a GNN graph from reasoning embeddings and trade using PPO-DSR policy. On 2025 YTD (through 2025-08-01), we achieved Sharpe 1.40 +/- 0.22 across 20 seeds and validated signal legitimacy through negative control experiments. To assess robustness beyond a single OOS window, we additionally evaluate an extended period (2024--2025), revealing market-regime dependency: the policy excels in volatile conditions but shows reduced alpha in trending bull markets.
Authors: Jing Wang, Jie Shen, Yiming Luo, Amar Sra, Qiaomin Xie, Jeremy C. Weiss
Abstract: Early prediction of Post-Acute Sequelae of SARS-CoV-2 severity is a critical challenge for women's health, particularly given the diagnostic overlap between PASC and common hormonal transitions such as menopause. Identifying and accounting for these confounding factors is essential for accurate long-term trajectory prediction. We conducted a retrospective study of 1,155 women (mean age 61) from the NIH RECOVER dataset. By integrating static clinical profiles with four weeks of longitudinal wearable data (monitoring cardiac activity and sleep), we developed a causal network based on a Large Language Model to predict future PASC scores. Our framework achieved a precision of 86.7\% in clinical severity prediction. Our causal attribution analysis demonstrate the model's ability to differentiate between active pathology and baseline noise: direct indicators such as breathlessness and malaise reached maximum saliency (1.00), while confounding factors like menopause and diabetes were successfully suppressed with saliency scores below 0.27.
Authors: Oksana Kolomenko, Ricardo Knauer, Erik Rodner
Abstract: Embeddings are a powerful way to enrich data-driven machine learning models with the world knowledge of large language models (LLMs). Yet, there is limited evidence on how to design effective LLM-based embedding pipelines for tabular prediction. In this work, we systematically benchmark 256 pipeline configurations, covering 8 preprocessing strategies, 16 embedding models, and 2 downstream models. Our results show that it strongly depends on the specific pipeline design whether incorporating the prior knowledge of LLMs improves the predictive performance. In general, concatenating embeddings tends to outperform replacing the original columns with embeddings. Larger embedding models tend to yield better results, while public leaderboard rankings and model popularity are poor performance indicators. Finally, gradient boosting decision trees tend to be strong downstream models. Our findings provide researchers and practitioners with guidance for building more effective embedding pipelines for tabular prediction tasks.
Authors: Qi Liu, Laure Zanna, Joan Bruna
Abstract: Recent advances in autoregressive neural surrogate models have enabled orders-of-magnitude speedups in simulating dynamical systems. However, autoregressive models are generally prone to distribution drift: compounding errors in autoregressive rollouts that severely degrade generation quality over long time horizons. Existing work attempts to address this issue by implicitly leveraging the inherent trade-off between short-time accuracy and long-time consistency through hyperparameter tuning. In this work, we introduce a unifying mathematical framework that makes this tradeoff explicit, formalizing and generalizing hyperparameter-based strategies in existing approaches. Within this framework, we propose a robust, hyperparameter-free model implemented as a conditional diffusion model that balances short-time fidelity with long-time consistency by construction. Our model, Self-refining Neural Surrogate model (SNS), can be implemented as a standalone model that refines its own autoregressive outputs or as a complementary model to existing neural surrogates to ensure long-time consistency. We also demonstrate the numerical feasibility of SNS through high-fidelity simulations of complex dynamical systems over arbitrarily long time horizons.
Authors: Yihong Chen, Quanming Yao
Abstract: Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing studies have largely focused on the forward pass, making it unclear whether their connection is direct or mediated by a training-time mechanism. We study this question from the perspective of backpropagation. Empirically and theoretically, we show that under causal mask, attention sinks can induce pronounced gradient concentration, which we term gradient sinks. Furthermore, in pre-norm architectures with RMSNorm, massive activations can be understood as an adaptive response to this localized gradient pressure during training. To test this hypothesis, we introduce V-scale, a modification that adjusts value-path backpropagated gradients. In pretrained V-scale models, attention sinks are preserved whereas massive activations are suppressed. These results support the interpretation that gradient sink is a key training-time mediator linking attention sinks and massive activations.
Authors: Luca Hinkamp, Simon Kl\"uttermann, Emmanuel M\"uller
Abstract: In practice, machine learning methods commonly require anomaly detection (AD) to filter inputs or detect distributional shifts. Typically, this is implemented by running a separate AD model alongside the primary model. However, this separation ignores the fact that the primary model already encodes substantial information about the target distribution. In this paper, we introduce On-Model AD, a setting for anomaly detection that explicitly leverages access to a related machine learning model. Within this setting, we propose RangeAD, an algorithm that utilizes neuron-wise output ranges derived from the primary model. RangeAD achieves superior performance even on high-dimensional tasks while incurring substantially lower inference costs. Our results demonstrate the potential of the On-Model AD setting as a practical framework for efficient anomaly detection.
Authors: Ant\^onio Junior Alves Caiado, Michael Hahsler
Abstract: Transformer-based language models are widely deployed for reasoning, yet their behavior under inference-time stochasticity remains underexplored. While dropout is common during training, its inference-time effects via Monte Carlo sampling lack systematic evaluation across architectures, limiting understanding of model reliability in uncertainty-aware applications. This work analyzes dropout-induced variability across 19 transformer models using MC Dropout with 100 stochastic forward passes per sample. Dropout robustness is defined as maintaining high accuracy and stable predictions under stochastic inference, measured by standard deviation of per-run accuracies. A cognitive decomposition framework disentangles performance into memory and reasoning components. Experiments span five dropout configurations yielding 95 unique evaluations on 1,000 samples. Results reveal substantial architectural variation. Smaller models demonstrate perfect prediction stability while medium-sized models exhibit notable volatility. Mid-sized models achieve the best overall performance; larger models excel at memory tasks. Critically, 53% of models suffer severe accuracy degradation under baseline MC Dropout, with task-specialized models losing up to 24 percentage points, indicating unsuitability for uncertainty quantification in these architectures. Asymmetric effects emerge: high dropout reduces memory accuracy by 27 percentage points while reasoning degrades only 1 point, suggesting memory tasks rely on stable representations that dropout disrupts. 84% of models demonstrate memory-biased performance. This provides the first comprehensive MC Dropout benchmark for transformers, revealing dropout robustness is architecture-dependent and uncorrelated with scale. The cognitive profiling framework offers actionable guidance for model selection in uncertainty-aware applications.
Authors: David Millard, Cecilia Alm, Rashid Ali, Pengcheng Shi, Ali Baheri
Abstract: Federated reinforcement learning typically aggregates value functions or policies by parameter averaging, which emphasizes expected return and can obscure statistical multimodality and tail behavior that matter in safety-critical settings. We formalize federated distributional reinforcement learning (FedDistRL), where clients parametrize quantile value function critics and federate these networks only. We also propose TR-FedDistRL, which builds a per client, risk-aware Wasserstein barycenter over a temporal buffer. This local barycenter provides a reference region to constrain the parameter averaged critic, ensuring necessary distributional information is not averaged out during the federation process. The distributional trust region is implemented as a shrink-squash step around this reference. Under fixed-policy evaluation, the feasibility map is nonexpansive and the update is contractive in a probe-set Wasserstein metric under evaluation. Experiments on a bandit, multi-agent gridworld, and continuous highway environment show reduced mean-smearing, improved safety proxies (catastrophe/accident rate), and lower critic/policy drift versus mean-oriented and non-federated baselines.
Authors: Yanke Yu, Jin Li, Ying Sun, Ping Li, Zhefeng Wang, Yi Zheng
Abstract: Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions into modules remains highly unexplored. To bridge this gap, we formulate a functional module discovery problem and propose an Unsupervised LLM Cross-layer MOdule Discovery (ULCMOD) framework that simultaneously disentangles the large set of neurons in the entire LLM into modules while discovering the topics of input samples related to these modules. Our framework introduces a novel objective function and an efficient Iterative Decoupling (IterD) algorithm. Extensive experiments show that our method discovers high-quality, disentangled modules that capture more meaningful semantic information and achieve superior performance in various downstream tasks. Moreover, our qualitative analysis reveals that the discovered modules show semantic coherence, correspond to interpretable specializations, and a clear spatial and hierarchical organization within the LLM. Our work provides a novel tool for interpreting the functional modules of LLMs, filling a critical blank in LLM's interpretability research.
Authors: Jing Qin, Muhao Chen
Abstract: Tensegrity structures possess intrinsic geometric symmetries that govern their dynamic behavior. However, most existing physics-informed neural network (PINN) approaches for tensegrity dynamics do not explicitly exploit these symmetries, leading to high computational complexity and unstable optimization. In this work, we propose a symmetry-reduced physics-informed neural network (SymPINN) framework that embeds group-theory-based symmetry directly into both the solution expression and the neural network architecture to predict tensegrity dynamics. By decomposing nodes into symmetry orbits and representing free nodal coordinates using a symmetry basis, the proposed method constructs a reduced coordinate representation that preserves geometric symmetry of the structure. The full coordinates are then recovered via symmetry transformations of the reduced solution learned by the network, ensuring that the predicted configurations automatically satisfy the symmetry constraints. In this framework, equivariance is enforced through orbit-based coordinate generation, symmetry-consistent message passing, and physics residual constraints. In addition, SymPINN improves training effectiveness by encoding initial conditions as hard constraints, incorporating Fourier feature encoding to enhance the representation of dynamic motions, and employing a two-stage optimization strategy. Extensive numerical experiments on symmetric T-bars and lander structures demonstrate significantly improved prediction accuracy and computational efficiency compared to standard physics-informed models, indicating the great potential of symmetry-aware learning for structure-preserving modeling of tensegrity dynamics.
Authors: William Thorossian
Abstract: Modern seismic and volcanic monitoring is increasingly shaped by continuous, multi-sensor observations and by the need to extract actionable information from nonstationary, noisy wavefields. In this context, machine learning has moved from a research curiosity to a practical ingredient of processing chains for detection, phase picking, classification, denoising, and anomaly tracking. However, improved accuracy on a fixed dataset is not sufficient for operational use. Models must remain reliable under domain shift (new stations, changing noise, evolving volcanic activity), provide uncertainty that supports decision-making, and connect their outputs to physically meaningful constraints. This paper surveys and organizes recent ML approaches for seismic and volcanic signal analysis, highlighting where classical signal processing provides indispensable inductive bias, how self-supervision and generative modeling can reduce dependence on labels, and which evaluation protocols best reflect transfer across regions. We conclude with open challenges for robust, interpretable, and maintainable AI-assisted monitoring.
Authors: Alexander D. Goldie, Zilin Wang, Adrian Hayler, Deepak Nathani, Edan Toledo, Ken Thampiratwong, Aleksandra Kalisz, Michael Beukman, Alistair Letcher, Shashank Reddy, Clarisse Wibault, Theo Wolf, Charles O'Neill, Uljad Berdica, Nicholas Roberts, Saeed Rahmani, Hannah Erlebach, Roberta Raileanu, Shimon Whiteson, Jakob N. Foerster
Abstract: Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems has thus far been limited by existing task suites. They suffer from many issues, such as: poor evaluation methodologies; data contamination; and containing saturated or very similar problems. Here, we introduce DiscoGen, a procedural generator of algorithm discovery tasks for machine learning, such as developing optimisers for reinforcement learning or loss functions for image classification. Motivated by the success of procedural generation in reinforcement learning, DiscoGen spans millions of tasks of varying difficulty and complexity from a range of machine learning fields. These tasks are specified by a small number of configuration parameters and can be used to optimise algorithm discovery agents (ADAs). We present DiscoBench, a benchmark consisting of a fixed, small subset of DiscoGen tasks for principled evaluation of ADAs. Finally, we propose a number of ambitious, impactful research directions enabled by DiscoGen, in addition to experiments demonstrating its use for prompt optimisation of an ADA. DiscoGen is released open-source at https://github.com/AlexGoldie/discogen.
Authors: Marijn Ruiter, Miguel Aguiar, Jake Rap, Karl H. Johansson, Amritam Das
Abstract: We propose RHYME-XT, an operator-learning framework for surrogate modeling of spatiotemporal control systems governed by input-affine nonlinear partial integro-differential equations (PIDEs) with localized rhythmic behavior. RHYME-XT uses a Galerkin projection to approximate the infinite-dimensional PIDE on a learned finite-dimensional subspace with spatial basis functions parameterized by a neural network. This yields a projected system of ODEs driven by projected inputs. Instead of integrating this non-autonomous system, we directly learn its flow map using an architecture for learning flow functions, avoiding costly computations while obtaining a continuous-time and discretization-invariant representation. Experiments on a neural field PIDE show that RHYME-XT outperforms a state-of-the-art neural operator and is able to transfer knowledge effectively across models trained on different datasets, through a fine-tuning process.
Authors: Abhishek Gupta, Aditya Mahajan
Abstract: Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. Using the well-established perturbation theory of linear operators, this viewpoint allows one to identify derivatives of the objective function as a function of the linear operators. This leads to generalization of many well-known results in reinforcement learning to cases with generate state and action spaces. Prior results of this type were only established in the finite-state finite-action MDP settings and in settings with certain linear function approximations. The framework also leads to new low-complexity PPO-type reinforcement learning algorithms for general state and action space MDPs.
Authors: Arpit Singh Gautam, Saurabh Jha
Abstract: Post training quantization is essential for deploying large language models (LLMs) on resource constrained hardware, yet state of the art methods enforce uniform bit widths across layers, yielding suboptimal accuracy efficiency trade offs. We present RAMP (Reinforcement Adaptive Mixed Precision), an off policy Soft Actor Critic framework that learns per layer bit width assignments to minimize perplexity under a global bit budget. The policy conditions on an 11 dimensional embedding of activation statistics, weight properties, and structural descriptors, enabling zero shot transfer across model families and scales. To enable stable sub 4 bit quantization, we introduce Scale Folding, a preconditioning technique that migrates activation outliers into weights via per channel scaling and normalization layer compensation. A quality prioritized reward with asymmetric penalties and budget cliffs drives rapid convergence. On Llama 2 7B, RAMP achieves 5.54 perplexity at 3.68GB (3.65 effective bits), outperforming uniform 4 bit AWQ (5.60 at 3.90 GB) and GPTQ by 6% in size and 1% to3% in quality. Critically, a policy trained only on Llama 2 7B generalizes zero shot to Llama 2 13B and Mistral 7B, often surpassing target specific training, supporting the hypothesis that quantization sensitivity is primarily architectural. The HALO pipeline exports allocations to GGUF format for kernel free inference on CPUs, GPUs, and edge devices, retaining 99.5% of FP16 commonsense reasoning performance.
Authors: Borja Aizpurua, Sukhbinder Singh, Rom\'an Or\'us
Abstract: Large language models (LLMs) contain billions of parameters, yet many exact values are not essential. We show that what matters most is the relative rank of weights-whether one connection is stronger or weaker than another-rather than precise magnitudes. To reduce the number of unique weight values, we apply weight clustering to pretrained models, replacing every weight matrix with K shared values from K-means. For Llama 3.1-8B-Instruct and SmolLM2-135M, reducing each matrix to only 16-64 distinct values preserves strong accuracy without retraining, providing a simple, training-free method to compress LLMs on disk. Optionally fine-tuning only the cluster means (centroids) recovers 30-40 percent of the remaining accuracy gap at minimal cost. We then systematically randomize cluster means while keeping assignments fixed. Scrambling the relative ranks of the clusters degrades quality sharply-perplexity can increase by orders of magnitude-even when global statistics such as mean and variance are preserved. In contrast, rank-preserving randomizations cause almost no loss at mid and late layers. On the other hand, when many layers are perturbed simultaneously, progressive layer-by-layer replacement reveals that scale drift-not rank distortion-is the dominant collapse mechanism; however, an affine correction w' = aw + b with a > 0 (which preserves both rank order and overall weight distribution) can substantially delay this drift. This rank-based perspective offers a new lens on model compression and robustness.
Authors: Zhongzhu Zhou, Fengxiang Bie, Ziyan Chen, Zhenyu Zhang, Yibo Yang, Junxiong Wang, Ben Athiwaratkun, Xiaoxia Wu, Shuaiwen Leon Song
Abstract: Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, making it attractive for efficient inference. However, many practical conversion baselines rely on weight-only low-rank approximations (e.g., SVD-style initializations) and uniform rank allocation. They focus on minimizing the difference between weight matrices rather than on how those weights affect input activations, ignore the covariance structure of activations, and enforce uniform rank across layers, causing activation drift and degraded attention fidelity. To address these issues, we propose CARE, a Covariance-Aware, Rank-Enhanced MLA conversion pipeline under a fixed KV width. CARE introduces three key steps: (i) activation-preserving factorization, which aligns the approximation with the actual input activations rather than just the weights; (ii) adjusted-rank allocation, which spreads a fixed KV budget across layers by giving more capacity to layers that need it most; and (iii) KV-parity mapping, which reparameterizes the converted K and V to fit the MLA format while keeping the KV-cache size unchanged. Our method outperforms a uniform-rank SVD baseline on Qwen3-4B/30B-A3B-Instruct-2507 and Llama-3.1-8B/70B-Instruct, reducing one-shot perplexity by up to 215x and improving mean accuracy by up to 1.70x at matched KV budgets. With a brief post-SVD healing fine-tune, we fully recover the original model's accuracy.
Authors: Cristiano Capone, Luca Falorsi, Andrea Ciardiello, Luca Manneschi
Abstract: Rapid adaptation in complex control systems remains a central challenge in reinforcement learning. We introduce a framework in which policy and value functions share a low-dimensional coefficient vector - a goal embedding - that captures task identity and enables immediate adaptation to novel tasks without retraining representations. During pretraining, we jointly learn structured value bases and compatible policy bases through a bilinear actor-critic decomposition. The critic factorizes as Q = sum_k G_k(g) y_k(s,a), where G_k(g) is a goal-conditioned coefficient vector and y_k(s,a) are learned value basis functions. This multiplicative gating - where a context signal scales a set of state-dependent bases - is reminiscent of gain modulation observed in Layer 5 pyramidal neurons, where top-down inputs modulate the gain of sensory-driven responses without altering their tuning. Building on Successor Features, we extend the decomposition to the actor, which composes a set of primitive policies weighted by the same coefficients G_k(g). At test time the bases are frozen and G_k(g) is estimated zero-shot via a single forward pass, enabling immediate adaptation to novel tasks without any gradient update. We train a Soft Actor-Critic agent on the MuJoCo Ant environment under a multi-directional locomotion objective, requiring the agent to walk in eight directions specified as continuous goal vectors. The bilinear structure allows each policy head to specialize to a subset of directions, while the shared coefficient layer generalizes across them, accommodating novel directions by interpolating in goal embedding space. Our results suggest that shared low-dimensional goal embeddings offer a general mechanism for rapid, structured adaptation in high-dimensional control, and highlight a potentially biologically plausible principle for efficient transfer in complex reinforcement learning systems.
Authors: Ben S. Southworth, Stephen Thomas
Abstract: Orthogonalized-momentum optimizers such as Muon improve transformer training by approximately whitening/orthogonalizing matrix-valued momentum updates via a short polar-decomposition iteration. However, polar-factor approximations typically require multiple large matrix multiplications, and the resulting overhead can be substantial and hardware-dependent. We introduce MUD (MomentUm Decorrelation), a complementary whitening approach that replaces Muon's polar update with a triangular (Cholesky-like) whitening surrogate inspired by classical Gram--Schmidt and Gauss-Seidel ideas. We show that row-orthonormal matrices are fixed points of the MUD map, relate the inner step to symmetric Gauss-Seidel preconditioning of the Gram matrix, and prove quadratic local convergence near the fixed point. In terms of time-to-perplexity, MUD yields consistent 10-50\% wall-clock improvements over tuned AdamW and Muon in time-to-perplexity, typically converging slightly slower per step than Muon but with substantially lower optimizer overhead -- relative to Muon, MUD improves peak tokens/s by roughly $1.3-2.6\times$ across most settings and up to nearly $3\times$ on GPT-2 large on an A100. We also demonstrate training a ESM-2 150M protein language model, where MUD matches Muon-level validation perplexity in significantly less wall-clock time.
Authors: Kaito Baba, Satoshi Kodera
Abstract: We propose MARL-Rad, a novel multi-modal multi-agent reinforcement learning framework for radiology report generation that coordinates region-specific agents and a global integrating agent, optimized via clinically verifiable rewards. Unlike prior single-model reinforcement learning or post-hoc agentization of independently trained models, our method jointly trains multiple agents and optimizes the entire agent system through reinforcement learning. Experiments on the MIMIC-CXR and IU X-ray datasets show that MARL-Rad consistently improves clinically efficacy (CE) metrics such as RadGraph, CheXbert, and GREEN scores, achieving state-of-the-art CE performance. Further analyses confirm that MARL-Rad enhances laterality consistency and produces more accurate, detail-informed reports.
Authors: Chidozie Ezeakunne, Jose E. Tabarez, Reeju Pokharel, Anup Pandey
Abstract: Solving the alternating current power flow equations in real time is essential for secure grid operation, yet classical Newton-Raphson solvers can be slow under stressed conditions. Existing graph neural networks for power flow are typically trained on a single system and often degrade on different systems. We present PowerModelsGAT-AI, a physics-informed graph attention network that predicts bus voltages and generator injections. The model uses bus-type-aware masking to handle different bus types and balances multiple loss terms, including a power-mismatch penalty, using learned weights. We evaluate the model on 14 benchmark systems (4 to 6,470 buses) and train a unified model on 13 of these under N-2 (two-branch outage) conditions, achieving an average normalized mean absolute error of 0.89% for voltage magnitudes and R^2 > 0.99 for voltage angles. We also show continual learning: when adapting a base model to a new 1,354-bus system, standard fine-tuning causes severe forgetting with error increases exceeding 1000% on base systems, while our experience replay and elastic weight consolidation strategy keeps error increases below 2% and in some cases improves base-system performance. Interpretability analysis shows that learned attention weights correlate with physical branch parameters (susceptance: r = 0.38; thermal limits: r = 0.22), and feature importance analysis supports that the model captures established power flow relationships.
Authors: Guoan Wang, Shihao Yang, Jun-en Ding, Hao Zhu, Feng Liu
Abstract: Electroencephalography (EEG) provides a non-invasive window into neural dynamics at high temporal resolution and plays a pivotal role in clinical neuroscience research. Despite this potential, prevailing computational approaches to EEG analysis remain largely confined to task-specific classification objectives or coarse-grained pattern recognition, offering limited support for clinically meaningful interpretation. To address these limitations, we introduce NeuroNarrator, the first generalist EEG-to-text foundation model designed to translate electrophysiological segments into precise clinical narratives. A cornerstone of this framework is the curation of NeuroCorpus-160K, the first harmonized large-scale resource pairing over 160,000 EEG segments with structured, clinically grounded natural-language descriptions. Our architecture first aligns temporal EEG waveforms with spatial topographic maps via a rigorous contrastive objective, establishing spectro-spatially grounded representations. Building on this grounding, we condition a Large Language Model through a state-space-inspired formulation that integrates historical temporal and spectral context to support coherent clinical narrative generation. This approach establishes a principled bridge between continuous signal dynamics and discrete clinical language, enabling interpretable narrative generation that facilitates expert interpretation and supports clinical reporting workflows. Extensive evaluations across diverse benchmarks and zero-shot transfer tasks highlight NeuroNarrator's capacity to integrate temporal, spectral, and spatial dynamics, positioning it as a foundational framework for time-frequency-aware, open-ended clinical interpretation of electrophysiological data.
Authors: Jindong Li, Dario Zanca, Vincent Christlein, Tim Hamann, Jens Barth, Peter K\"ampf, Bj\"orn Eskofier
Abstract: Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In this work, we systematically investigate two strategies to address these issues: sub-word tokenization and concatenation-based data augmentation. Our experiments on the OnHW-Words500 dataset reveal a clear dichotomy between handling inter-writer and intra-writer variance. On the writer-independent split, structural abstraction via Bigram tokenization significantly improves performance to unseen writing styles, reducing the word error rate (WER) from 15.40% to 12.99%. In contrast, on the writer-dependent split, tokenization degrades performance due to vocabulary distribution shifts between the training and validation sets. Instead, our proposed concatenation-based data augmentation acts as a powerful regularizer, reducing the character error rate by 34.5% and the WER by 25.4%. Further analysis shows that short, low-level tokens benefit model performance and that concatenation-based data augmentation performance gain surpasses those achieved by proportionally extended training. These findings reveal a clear variance-dependent effect: sub-word tokenization primarily mitigates inter-writer stylistic variability, whereas concatenation-based data augmentation effectively compensates for intra-writer distributional sparsity.
Authors: Mehran Shabanpour, Sadaf Khademi, Konstantinos N Plataniotis, Arash Mohammadi
Abstract: Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural dynamics and the semantic context of behavioral tasks. We present the Dual-Enhanced COnditioned Diffusion (DECODE) for EEG, a novel framework that unifies semantic guidance from natural language descriptions with temporal dynamics from historical signals to generate event-specific neural responses. DECODE leverages pre-trained language models to condition the diffusion process on rich textual descriptions of cognitive events, while maintaining temporal coherence through history-based Langevin dynamics. Evaluated on a real-world driving task dataset with five distinct behaviors, DECODE achieves sub-microvolt prediction accuracy (MAE = 0.626 microvolt) over 75 timestep horizons while maintaining well-calibrated uncertainty estimates. Our framework demonstrates that natural language can effectively bridge high-level cognitive descriptions and low-level neural dynamics, opening new possibilities for zero-shot generalization to novel behaviors and interpretable BCIs. By generating physiologically plausible, event-specific EEG trajectories conditioned on semantic descriptions, DECODE establishes a new paradigm for understanding and predicting context-dependent neural activity.
Authors: Nabeel Ahmad Saidd
Abstract: Multi-horizon price forecasting is central to portfolio allocation, risk management, and algorithmic trading, yet deep learning architectures have proliferated faster than rigorous financial benchmarks can evaluate them. This study provides a controlled comparison of nine architectures (Autoformer, DLinear, iTransformer, LSTM, ModernTCN, N-HiTS, PatchTST, TimesNet, and TimeXer) spanning Transformer, MLP, CNN, and RNN families across cryptocurrency, forex, and equity index markets at 4-hour and 24-hour horizons. A total of 918 experiments were conducted under a strict five-stage protocol including fixed-seed Bayesian hyperparameter optimization, configuration freezing per asset class, multi-seed retraining, uncertainty aggregation, and statistical validation. ModernTCN achieves the best mean rank (1.333) with a 75 percent first-place rate, followed by PatchTST (2.000). Results reveal a clear three-tier ranking structure and show that architecture explains nearly all performance variance, while seed randomness is negligible. Rankings remain stable across horizons despite 2 to 2.5 times error amplification. Directional accuracy remains near 50 percent across all configurations, indicating that MSE-trained models lack directional skill at hourly resolution. The findings highlight the importance of architectural inductive bias over raw parameter count and provide reproducible guidance for multi-step financial forecasting.
Authors: Artemis Kontou, Natalia Miroshnikova, Costakis Matheou, Sophocles Sophocleous, Nicholas Tsekouras, Kleanthis Malialis, Panayiotis Kolios
Abstract: This study presents AI-HEART, a cloud-based information system for managing and analysing long-duration ambulatory electrocardiogram (ECG) recordings and supporting clinician decision-making. The platform operationalises an end-to-end pipeline that ingests multi-day three-lead ECGs, normalises inputs, performs signal preprocessing, and applies dedicated deep neural networks for wave delineation, noise/quality detection, and beat- and rhythm-level multi-class arrhythmia classification. To address class imbalance and real-world signal variability, model development combines large clinically annotated datasets with expert-in-the-loop curation and generative augmentation for under-represented rhythms. Empirical evaluation on three-lead ambulatory ECG data shows that delineation accuracy is sufficient for automated interval measurement, noise detection reliably flags poor-quality segments, and arrhythmia classification achieves high specificity with clinically useful macro-averaged performance across common and rarer rhythms. Beyond predictive accuracy, AI-HEART provides a scalable deployment approach for integrating AI into routine ECG services, enabling traceable outputs, audit-friendly storage of recordings and derived annotations, and clinician review/editing that captures feedback for controlled model improvement. The findings demonstrate the technical feasibility and operational value of a noise-aware AI-ECG platform as a digital health information system.
Authors: Fengcheng Wu (Harbin Institute of Technology, Shenzhen, China), Zhenxi Song (Harbin Institute of Technology, Shenzhen, China), Guoyang Xu (Harbin Institute of Technology, Shenzhen, China), Kaisong Hu (Harbin Institute of Technology, Shenzhen, China), Zirui Wang (Harbin Institute of Technology, Shenzhen, China), Yi Guo (Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen), Zhiguo Zhang (Harbin Institute of Technology, Shenzhen, China)
Abstract: Robust and interpretable dementia diagnosis from noisy, non-stationary electroencephalography (EEG) is clinically essential yet remains challenging. To this end, we propose SeeGraph, a Sparse-Explanatory dynamic EEG-graph network that models time-evolving functional connectivity and employs a node-guided sparse edge mask to reveal the connections that drive diagnostic decisions, while remaining robust to noise and cross-site variability. SeeGraph comprises four components: (1) a dual-trajectory temporal encoder that models dynamic EEG with two streams, where node signals capture regional oscillations and edge signals capture interregional coupling; (2) a topology-aware positional encoder that derives graph-spectral Laplacian coordinates from the fused connectivity and augments node embeddings; (3) a node-guided sparse explanatory edge mask that gates the connectivity into a compact subgraph; and (4) a gated graph predictor that operates on the sparsified graph. The framework is trained using cross-entropy loss together with a sparsity regularizer on the mask, yielding noise-robust and interpretable diagnoses. The effectiveness of SeeGraph is validated on public and in-house EEG cohorts, including patients with neurodegenerative dementias and healthy controls, under both raw and noise-perturbed conditions. Its sparse, node-guided explanations highlight disease-relevant connections and align with established clinical findings on functional connectivity alterations, thereby offering transparent cues for neurological evaluation.
Authors: Junzi Zhang, Jianing Shen, Weijie Tu, Yi Zhang, Hailin Zhang, Tom Gedeon, Bin Jiang, Yue Yao
Abstract: Large language models (LLMs) are becoming an increasingly important component of human--computer interaction, enabling users to coordinate a wide range of intelligent agents through natural language. While language-based interfaces are powerful and flexible, they implicitly assume that users can reliably produce explicit linguistic input, an assumption that may not hold for users with speech or motor impairments, e.g., Amyotrophic Lateral Sclerosis (ALS). In this work, we investigate whether neural signals can be used as an alternative input to LLMs, particularly to support those socially marginalized or underserved users. We build a simple brain-LLM interface, which uses EEG signals to guide image generation models at test time. Specifically, we first train a classifier to estimate user satisfaction from EEG signals. Its predictions are then incorporated into a test-time scaling (TTS) framework that dynamically adapts model inference using neural feedback collected during user evaluation. The experiments show that EEG can predict user satisfaction, suggesting that neural activity carries information on real-time preference inference. These findings provide a first step toward integrating neural feedback into adaptive language-model inference, and hopefully open up new possibilities for future research on adaptive LLM interaction.
Authors: Sindu B. S., Jan Hamaekers
Abstract: Epoxy polymers are widely used due to their multifunctional properties, but machine learning (ML) applications remain limited owing to their complex 3D molecular structure, multi-component nature, and lack of curated datasets. Existing ML studies are largely restricted to simulation data, specific properties, or narrow constituent ranges. To address these limitations, we developed an informed Gaussian Process Regression-based Knowledge Distillation (GPR-KD) framework for predicting multiple physical (glass transition temperature, density) and mechanical properties (elastic modulus, tensile strength, compressive strength, flexural strength, fracture energy, adhesive strength) of thermoset epoxy polymers. The model was trained on experimental literature data covering diverse monomer classes (9 resins, 40 hardeners). Individual GPR models serve as teacher models capturing nonlinear feature-property relationships, while a unified neural network student model learns distilled knowledge across all properties simultaneously. By encoding the target property as an input feature, the student model leverages cross-property correlations. Molecular-level descriptors extracted from SMILES representations using RDKit create a physics-informed model. The framework combines GPR interpretability and robustness with deep learning scalability and generalization. Comparative analysis demonstrates superior prediction accuracy over conventional ML models. Simultaneous multi-property prediction further improves accuracy through information sharing across correlated properties. The proposed framework enables accelerated design of novel epoxy polymers with tailored properties.
Authors: Thomas Jiralerspong, Flemming Kondrup, Yoshua Bengio
Abstract: Chain-of-thought (CoT) monitoring is proposed as a method for overseeing the internal reasoning of language-model agents. Prior work has shown that when models are explicitly informed that their reasoning is being monitored, or are fine-tuned to internalize this fact, they may learn to obfuscate their CoTs in ways that allow them to evade CoT-based monitoring systems. We ask whether reasoning agents can autonomously infer that their supposedly private CoT is under surveillance, and whether this awareness leads to strategic evasion, without any explicit training or instructions. In a multi-episode agentic framework, models pursue both a primary task and a concealed side task while being told that their reasoning is private; a hidden CoT monitor blocks episodes when suspicious reasoning is detected. We find that frontier models can deduce the existence of this monitor purely from blocking feedback, with the most capable models reaching a confident belief that their thinking is observed in up to 19% of episodes. This awareness scales with model capability and, in rare cases, escalates to an explicit intent to suppress reasoning about the side task. However, models that form this intent uniformly fail to execute it, openly reasoning about their concealed objectives in the very next episode. This intent-capability gap is reassuring for current deployment, but the autonomous emergence of both monitoring awareness and evasion intent suggests that CoT monitoring is not a permanently reliable safeguard.
Authors: Morgan D. Sanger, Olyvia B. Smith, Brett W. Maurer, Liam Wotherspoon, Marc O. Eberhard, Jeffrey W. Berman
Abstract: Large earthquakes along the Cascadia Subduction Zone (CSZ) are expected to trigger widespread soil liquefaction that could disrupt transportation systems across the U.S. Pacific Northwest. However, past regional assessments have relied on simple geologic screening methods and binomial shaking thresholds that are only loosely informed by liquefaction science. This study introduces a mechanics-informed, data-driven framework for estimating liquefaction-induced road closures and service reductions, and the framework is applied to a magnitude-9 CSZ earthquake. Predicted liquefaction severity is translated into segment-level probabilities of closure and reduced service using empirically derived fragility relationships. These probabilities are mapped at 90-m resolution and propagated through the National Highway System using a spatially correlated Monte Carlo simulation to estimate link-level disruption. Results show that impacts are concentrated in low-lying coastal zones, river valleys, and urban waterfronts, with major disruptions expected along critical routes including U.S. Route 101. Local mobility is further examined in Pacific and Grays Harbor counties, Washington, where limited network redundancy, strong shaking, and high liquefaction susceptibility lead to elevated probabilities of isolation and loss of hospital access. Socioeconomic analysis reveals modest but statistically significant associations between road impacts and demographic indicators, suggesting that liquefaction impacts may compound with existing social vulnerabilities. While not a substitute for site-specific analysis, the results provide a regional baseline for emergency planning, risk communication, and prioritization of more advanced geotechnical sampling and analysis. Moreover, the methodology proposed here is not specific to the CSZ, but rather, could be applied to analogous studies of road impacts elsewhere.
Authors: Mohsen Sahraei Ardakani, Hong Wan, Rui Song
Abstract: Mobile Edge Computing (MEC) technology has been introduced to enable could computing at the edge of the network in order to help resource limited mobile devices with time sensitive data processing tasks. In this paradigm, mobile devices can offload their computationally heavy tasks to more efficient nearby MEC servers via wireless communication. Consequently, the main focus of researches on the subject has been on development of efficient offloading schemes, leaving the privacy of mobile user out. While the Blockchain technology is used as the trust mechanism for secured sharing of the data, the privacy issues induced from wireless communication, namely, usage pattern and location privacy are the centerpiece of this work. The effects of these privacy concerns on the task offloading Markov Decision Process (MDP) is addressed and the MDP is solved using a Deep Recurrent Q-Netwrok (DRQN). The Numerical simulations are presented to show the effectiveness of the proposed method.
Authors: Gianluca Audone, Francesco Marchetti, Emma Perracchione, Milvia Rossini
Abstract: Classical Gaussian processes and Kriging models are commonly based on stationary kernels, whereby correlations between observations depend exclusively on the relative distance between scattered data. While this assumption ensures analytical tractability, it limits the ability of Gaussian processes to represent heterogeneous correlation structures. In this work, we investigate variably scaled kernels as an effective tool for constructing non-stationary Gaussian processes by explicitly modifying the correlation structure of the data. Through a scaling function, variably scaled kernels alter the correlations between data and enable the modeling of targets exhibiting abrupt changes or discontinuities. We analyse the resulting predictive uncertainty via the variably scaled kernel power function and clarify the relationship between variably scaled kernels-based constructions and classical non-stationary kernels. Numerical experiments demonstrate that variably scaled kernels-based Gaussian processes yield improved reconstruction accuracy and provide uncertainty estimates that reflect the underlying structure of the data
Authors: Niklas Ro{\ss}berg, Sinan Hasirlioglu, Mohamed Essayed Bouzouraa, Wolfgang Utschick, Michael Botsch
Abstract: Approval of ADS depends on evaluating its behavior within representative real-world traffic scenarios. A common way to obtain such scenarios is to extract them from real-world data recordings. These can then be grouped and serve as basis on which the ADS is subsequently tested. This poses two central challenges: how scenarios are extracted and how they are grouped. Existing extraction methods rely on heterogeneous definitions, hindering scenario comparability. For the grouping of scenarios, rule-based or ML-based methods can be utilized. However, while modern ML-based approaches can handle the complexity of traffic scenarios, unlike rule-based approaches, they lack interpretability and may not align with domain-knowledge. This work contributes to a standardized scenario extraction based on the Scenario-as-Specification concept, as well as a domain-knowledge-guided scenario clustering process. Experiments on the highD dataset demonstrate that scenarios can be extracted reliably and that domain-knowledge can be effectively integrated into the clustering process. As a result, the proposed methodology supports a more standardized process for deriving scenario categories from highway data recordings and thus enables a more efficient validation process of automated vehicles.
Authors: Trung V. Phan, Tri Gia Nguyen, Thomas Bauschert
Abstract: This paper presents DeepStage, a deep reinforcement learning (DRL) framework for adaptive, stage-aware defense against Advanced Persistent Threats (APTs). The enterprise environment is modeled as a partially observable Markov decision process (POMDP), where host provenance and network telemetry are fused into unified provenance graphs. Building on our prior work, StageFinder, a graph neural encoder and an LSTM-based stage estimator infer probabilistic attacker stages aligned with the MITRE ATT&CK framework. These stage beliefs, combined with graph embeddings, guide a hierarchical Proximal Policy Optimization (PPO) agent that selects defense actions across monitoring, access control, containment, and remediation. Evaluated in a realistic enterprise testbed using CALDERA-driven APT playbooks, DeepStage achieves a stage-weighted F1-score of 0.89, outperforming a risk-aware DRL baseline by 21.9%. The results demonstrate effective stage-aware and cost-efficient autonomous cyber defense.
Authors: Protopopov Alexey
Abstract: Automatic speech recognition systems based on neural networks are vulnerable to adversarial attacks that alter transcriptions in a malicious way. Recent works in this field have focused on making attacks work in over-the-air scenarios, however such attacks are typically detectable by human hearing, limiting their potential applications. In the present work we explore different approaches of making over-the-air attacks less detectable, as well as the impact these approaches have on the attacks' effectiveness.
Authors: D. Mart\'in-P\'erez, F. Rodr\'iguez-D\'iaz, D. Guti\'errez-Avil\'es, A. Troncoso, F. Mart\'inez-\'Alvarez
Abstract: Quantum transfer learning combines pretrained classical deep learning models with quantum circuits to reuse expressive feature representations while limiting the number of trainable parameters. In this work, we introduce a family of compact quantum transfer learning architectures that attach variational quantum classifiers to frozen convolutional backbones for image classification. We instantiate and evaluate several classical-quantum hybrid models implemented in PennyLane and Qiskit, and systematically compare them with a classical transfer-learning baseline across heterogeneous image datasets. To ensure a realistic assessment, we evaluate all approaches under both ideal simulation and noisy emulation using noise models calibrated from IBM quantum hardware specifications, as well as on real IBM quantum hardware. Experimental results show that the proposed quantum transfer learning architectures achieve competitive and, in several cases, superior accuracy while consistently reducing training time and energy consumption relative to the classical baseline. Among the evaluated approaches, PennyLane-based implementations provide the most favorable trade-off between accuracy and computational efficiency, suggesting that hybrid quantum transfer learning can offer practical benefits in realistic NISQ era settings when feature extraction remains classical.
Authors: Sa Xiao, Hao Jing, Honglu Sun, Haoyu Li
Abstract: This paper presents TorchNWP, a compilation library tool for the efficient coupling of artificial intelligence components and traditional numerical models. It aims to address the issues of poor cross-language compatibility, insufficient coupling flexibility, and low data transfer efficiency between operational numerical models developed in Fortran and Python-based deep learning frameworks. Based on LibTorch, it optimizes and designs a unified application-layer calling interface, converts deep learning models under the PyTorch framework into a static binary format, and provides C/C++ interfaces. Then, using hybrid Fortran/C/C++ programming, it enables the deployment of deep learning models within numerical models. Integrating TorchNWP into a numerical model only requires compiling it into a callable link library and linking it during the compilation and linking phase to generate the executable. On this basis, tangent linear and adjoint model based on neural networks are implemented at the C/C++ level, which can shield the internal structure of neural network models and simplify the construction process of four-dimensional variational data assimilation systems. Meanwhile, it supports deployment on heterogeneous platforms, is compatible with mainstream neural network models, and enables mapping of different parallel granularities and efficient parallel execution. Using this tool requires minimal code modifications to the original numerical model, thus reducing coupling costs. It can be efficiently integrated into numerical weather prediction models such as CMA-GFS and MCV, and has been applied to the coupling of deep learning-based physical parameterization schemes (e.g., radiation, non-orographic gravity wave drag) and the development of their tangent linear and adjoint models, significantly improving the accuracy and efficiency of numerical weather prediction.
Authors: Pierre Krack, Tobias J\"ulg, Wolfram Burgard, Florian Walter
Abstract: Well-designed dense reward functions in robot manipulation not only indicate whether a task is completed but also encode progress along the way. Generally, designing dense rewards is challenging and usually requires access to privileged state information available only in simulation, not in real-world experiments. This makes reward prediction models that infer task state information from camera images attractive. A common approach is to predict rewards from expert demonstrations based on visual similarity or sequential frame ordering. However, this biases the resulting reward function towards a specific solution and leaves it undefined in states not covered by the demonstrations. In this work, we introduce Rewarding DINO, a method for language-conditioned reward modeling that learns actual reward functions rather than specific trajectories. The model's compact size allows it to serve as a direct replacement for analytical reward functions with comparatively low computational overhead. We train our model on data sampled from 24 Meta-World+ tasks using a rank-based loss and evaluate pairwise accuracy, rank correlation, and calibration. Rewarding DINO achieves competitive performance in tasks from the training set and generalizes to new settings in simulation and the real world, indicating that it learns task semantics. We also test the model with off-the-shelf reinforcement learning algorithms to solve tasks from our Meta-World+ training set.
Authors: Bruno Carpentieri, Andrei Velichko, Mudassir Shams, Paola Lecca
Abstract: We propose an interpretable AI-assisted reliability diagnostic framework for parameterized root-finding schemes based on kNN-LLE proxy stability profiling and multi-horizon early prediction. The approach augments a numerical solver with a lightweight predictive layer that estimates solver reliability from short prefixes of iteration dynamics, enabling early identification of stable and unstable parameter regimes. For each configuration in the parameter space, raw and smoothed proxy profiles of a largest Lyapunov exponent (LLE) estimator are constructed, from which contractivity-based reliability scores summarizing finite-time convergence are derived. Machine learning models predict the reliability score from early segments of the proxy profile, allowing the framework to determine when solver dynamics become diagnostically informative. Experiments on a two-parameter parallel root-finding scheme show reliable prediction after only a few iterations: the best models achieve R^2=0.48 at horizon T=1, improve to R^2=0.67 by T=3, and exceed R^2=0.89 before the characteristic minimum-location scale of the stability profile. Prediction accuracy increases to R^2=0.96 at larger horizons, with mean absolute errors around 0.03, while inference costs remain negligible (microseconds per sample). The framework provides interpretable stability indicators and supports early decisions during solver execution, such as continuing, restarting, or adjusting parameters.
Authors: Nazia Riasat
Abstract: Recent advances in generative AI have led to increasingly realistic synthetic data, yet evaluation criteria remain focused on marginal distribution matching. While these diagnostics assess local realism, they provide limited insight into whether a generative model preserves the multivariate dependence structures governing downstream inference. We introduce covariance-level dependence fidelity as a practical criterion for evaluating whether a generative distribution preserves joint structure beyond univariate marginals. We establish three core results. First, distributions can match all univariate marginals exactly while exhibiting substantially different dependence structures, demonstrating marginal fidelity alone is insufficient. Second, dependence divergence induces quantitative instability in downstream inference, including sign reversals in regression coefficients despite identical marginal behavior. Third, explicit control of covariance-level dependence divergence ensures stable behavior for dependence-sensitive tasks such as principal component analysis. Synthetic constructions illustrate how dependence preservation failures lead to incorrect conclusions despite identical marginal distributions. These results highlight dependence fidelity as a useful diagnostic for evaluating generative models in dependence-sensitive downstream tasks, with implications for diffusion models and variational autoencoders. These guarantees apply specifically to procedures governed by covariance structure; tasks requiring higher-order dependence such as tail-event estimation require richer criteria.
Authors: Yasaswini Chebolu
Abstract: Reliable terrain perception is a fundamental requirement for autonomous navigation in unstructured, off-road environments. Desert landscapes present unique challenges due to low chromatic contrast between terrain categories, extreme lighting variability, and sparse vegetation that defy the assumptions of standard road-scene segmentation models. We present DesertFormer, a semantic segmentation pipeline for off-road desert terrain analysis based on SegFormer B2 with a hierarchical Mix Transformer (MiT-B2) backbone. The system classifies terrain into ten ecologically meaningful categories -- Trees, Lush Bushes, Dry Grass, Dry Bushes, Ground Clutter, Flowers, Logs, Rocks, Landscape, and Sky -- enabling safety-aware path planning for ground robots and autonomous vehicles. Trained on a purpose-built dataset of 4,176 annotated off-road images at 512x512 resolution, DesertFormer achieves a mean Intersection-over-Union (mIoU) of 64.4% and pixel accuracy of 86.1%, representing a +24.2% absolute improvement over a DeepLabV3 MobileNetV2 baseline (41.0% mIoU). We further contribute a systematic failure analysis identifying the primary confusion patterns -- Ground Clutter to Landscape and Dry Grass to Landscape -- and propose class-weighted training and copy-paste augmentation for rare terrain categories. Code, checkpoints, and an interactive inference dashboard are released at https://github.com/Yasaswini-ch/Vision-based-Desert-Terrain-Segmentation-using-SegFormer.
URLs: https://github.com/Yasaswini-ch/Vision-based-Desert-Terrain-Segmentation-using-SegFormer.
Authors: Isaac Robledo, Alberto Vilari\~no, Arnau Mir\'o, Oriol Lehmkuhl, Carlos Sanmiguel Vila, Rodrigo Castellanos
Abstract: Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization to reduce high-fidelity CFD cost while retaining RANS-level accuracy. The framework couples a low-fidelity-informed Gaussian process regression transfer model with uncertainty-triggered sampling and a synchronized elitism rule embedded in a hybrid genetic algorithm. Low-fidelity XFOIL evaluations provide inexpensive features, while sparse RANS simulations are adaptively allocated when predictive uncertainty exceeds a threshold; elite candidates are mandatorily validated at high fidelity, and the population is re-evaluated to prevent evolutionary selection based on outdated fitness values produced by earlier surrogate states. The method is demonstrated for a two-point problem at $Re=6\times10^6$ with cruise at $\alpha=2^\circ$ (maximize $E=L/D$) and take-off at $\alpha=10^\circ$ (maximize $C_L$) using a 12-parameter CST representation. Independent multi-fidelity surrogates per flight condition enable decoupled refinement. The optimized design improves cruise efficiency by 41.05% and take-off lift by 20.75% relative to the best first-generation individual. Over the full campaign, only 14.78% (cruise) and 9.5% (take-off) of evaluated individuals require RANS, indicating a substantial reduction in high-fidelity usage while maintaining consistent multi-point performance.
Authors: Ido Aharon, Jonathan Shaki, Sarit Kraus
Abstract: We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but differ in an auxiliary language, inducing structured diversity across models. We then generate pseudo-translations for the primary pair using token-level ensemble decoding, averaging model predictions in both directions. These ensemble outputs are used as synthetic parallel data to further train each model, allowing the models to improve via shared supervision. At deployment time, we select a single model by validation performance, preserving single-model inference cost. Experiments show statistically significant improvements over single-model UNMT baselines, with mean gains of 1.7 chrF when translating from English and 0.67 chrF when translating into English.
Authors: Kushankur Ghosh, Mehar Klair, Kian Kyars, Euijin Choo, J\"org Sander
Abstract: Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as attacks. However, existing approaches rely on brittle, manually engineered rules to build provenance graphs, lack functional context for system entities, and provide limited support for analyst investigation. We present Auto-Prov, an adaptive, end-to-end framework that leverages large language models (LLMs) to automatically construct provenance graphs from heterogeneous and evolving logs, embed system-level functional attributes into the graph, enable provenance graph-based anomaly detectors to learn from these enriched graphs, and summarize the detected attacks to assist an analyst's investigation. Auto-Prov clusters unseen log types and efficiently extracts provenance edges and entity-level information via automatically generated rules. It further infers system-level functional context for both known and previously unseen system entities using a combination of LLM inference and behavior-based estimation. Attacks detected by provenance-graph-based anomaly detectors trained on Auto-Prov's graphs are then summarized into natural-language text. We evaluate Auto-Prov with four state-of-the-art provenance graph-based detectors across diverse logs. Results show that Auto-Prov consistently enhances detection performance, generalizes across heterogeneous log formats, and produces stable, interpretable attack summaries that remain robust under system evolution.
Authors: Lucas Bandarkar, Alan Ansell, Trevor Cohn
Abstract: Modern LLMs continue to exhibit significant variance in behavior across languages, such as being able to recall factual information in some languages but not others. While typically studied as a problem to be mitigated, in this work, we propose leveraging this cross-lingual inconsistency as a tool for interpretability in mixture-of-experts (MoE) LLMs. Our knowledge localization framework contrasts routing for sets of languages where the model correctly recalls information from languages where it fails. This allows us to isolate model components that play a functional role in answering about a piece of knowledge. Our method proceeds in two stages: (1) querying the model with difficult factual questions across a diverse set of languages to generate "success" and "failure" activation buckets and then (2) applying a statistical contrastive analysis to the MoE router logits to identify experts important for knowledge. To validate the necessity of this small number of experts for answering a knowledge question, we deactivate them and re-ask the question. We find that despite only deactivating about 20 out of 6000 experts, the model no longer answers correctly in over 40% of cases. Generally, this method provides a realistic and scalable knowledge localization approach to address increasingly complex LLMs.
Authors: Marceau Lafargue-Hauret, Raghav Mehta, Fabio De Sousa Ribeiro, M\'elanie Roschewitz, Ben Glocker
Abstract: Image segmentation relies on large annotated datasets, which are expensive and slow to produce. Silver-standard (AI-generated) labels are easier to obtain, but they risk introducing bias. Self-supervised learning, needing only images, has become key for pre-training. Recent work combining contrastive learning with counterfactual generation improves representation learning for classification but does not readily extend to pixel-level tasks. We propose a pipeline combining counterfactual generation with dense contrastive learning via Dual-View (DVD-CL) and Multi-View (MVD-CL) methods, along with supervised variants that utilize available silver-standard annotations. A new visualisation algorithm, the Color-coded High Resolution Overlay map (CHRO-map) is also introduced. Experiments show annotation-free DVD-CL outperforms other dense contrastive learning methods, while supervised variants using silver-standard labels outperform training on the silver-standard labeled data directly, achieving $\sim$94% DSC on challenging data. These results highlight that pixel-level contrastive learning, enhanced by counterfactuals and silver-standard annotations, improves robustness to acquisition and pathological variations.
Authors: Davide Di Gioia
Abstract: A common architectural pattern in advanced AI reasoning systems is the symbolic graph network: specialized agents or modules connected by delegation edges, routing tasks through a dynamic execution graph. Current schedulers optimize load and fitness but are geometry-blind: they do not model how failures propagate differently in tree-like versus cyclic regimes. In tree-like delegation, a single failure can cascade exponentially; in dense cyclic graphs, failures tend to self-limit. We identify this observability gap, quantify its system-level cost, and propose a lightweight mitigation. We formulate online geometry control for route-risk estimation on time-indexed execution graphs with route-local failure history. Our approach combines (i) a Euclidean spatio-temporal propagation baseline, (ii) a hyperbolic route-risk model with temporal decay (and optional burst excitation), and (iii) a learned geometry selector over structural features. The selector is a compact MLP (9->12->1) using six topology statistics plus three geometry-aware signals: BFS shell-growth slope, cycle-rank norm, and fitted Poincare curvature. On the Genesis 3 benchmark distribution, adaptive switching improves win rate in the hardest non_tree regime from 64-72% (fixed hyperbolic variants) to 92%, and achieves 87.2% overall win rate. To measure total system value, we compare against Genesis 3 routing without any spatio-temporal sidecar, using only native bandit/LinUCB signals (team fitness and mean node load). This baseline achieves 50.4% win rate overall and 20% in tree-like regimes; the full sidecar recovers 87.2% overall (+36.8 pp), with +48 to +68 pp gains in tree-like settings, consistent with a cascade-sensitivity analysis. Overall, a 133-parameter sidecar substantially mitigates geometry-blind failure propagation in one high-capability execution-graph system.
Authors: Sad{\i}k Bera Y\"uksel, Ali Tevfik Buyukkocak, Derya Aksaray
Abstract: Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations.
Authors: Max Sch\"olpple, Liu Fanghui, Ingo Steinwart
Abstract: We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by previous observations that many algorithms, such as gradient-descent based learning, exhibit implicit regularization. In a nutshell, for a self-regularized algorithm the complexity of the predictor is inherently controlled by that of the simplest comparator achieving the same empirical risk. This framework is sufficiently rich to cover both classical regularized empirical risk minimization and gradient descent. Building on self-regularization, we provide a thorough statistical analysis of such algorithms including minmax-optimal rates, where it suffices to show that the algorithm is self-regularized -- all further requirements stem from the learning problem itself. Finally, we discuss the problem of data-dependent hyperparameter selection, providing a general result which yields minmax-optimal rates up to a double logarithmic factor and covers data-driven early stopping for RKHS-based gradient descent.
Authors: Sophie Kearney, Shu Yang, Zixuan Wen, Weimin Lyu, Bojian Hou, Duy Duong-Tran, Tianlong Chen, Jason H. Moore, Marylyn D. Ritchie, Chao Chen, Li Shen
Abstract: Accurate diagnosis of Alzheimer's disease (AD) requires handling tabular biomarker data, yet such data are often small and incomplete, where deep learning models frequently fail to outperform classical methods. Pretrained large language models (LLMs) offer few-shot generalization, structured reasoning, and interpretable outputs, providing a powerful paradigm shift for clinical prediction. We propose TAP-GPT Tabular Alzheimer's Prediction GPT, a domain-adapted tabular LLM framework built on TableGPT2 and fine-tuned for few-shot AD classification using tabular prompts rather than plain texts. We evaluate TAP-GPT across four ADNI-derived datasets, including QT-PAD biomarkers and region-level structural MRI, amyloid PET, and tau PET for binary AD classification. Across multimodal and unimodal settings, TAP-GPT improves upon its backbone models and outperforms traditional machine learning baselines in the few-shot setting while remaining competitive with state-of-the-art general-purpose LLMs. We show that feature selection mitigates degradation in high-dimensional inputs and that TAP-GPT maintains stable performance under simulated and real-world missingness without imputation. Additionally, TAP-GPT produces structured, modality-aware reasoning aligned with established AD biology and shows greater stability under self-reflection, supporting its use in iterative multi-agent systems. To our knowledge, this is the first systematic application of a tabular-specialized LLM to multimodal biomarker-based AD prediction, demonstrating that such pretrained models can effectively address structured clinical prediction tasks and laying the foundation for tabular LLM-driven multi-agent clinical decision-support systems. The source code is publicly available on GitHub: https://github.com/sophie-kearney/TAP-GPT.
Authors: Haoyang Fang, Shuai Zhang, Yifei Ma, Hengyi Wang, Cuixiong Hu, Katrin Kirchhoff, Bernie Wang, George Karypis
Abstract: Domain-specific finetuning is essential for dense retrievers, yet not all training pairs contribute equally to the learning process. We introduce OPERA, a data pruning framework that exploits this heterogeneity to improve both the effectiveness and efficiency of retrieval model adaptation. We first investigate static pruning (SP), which retains only high-similarity query-document pairs, revealing an intrinsic quality-coverage tradeoff: ranking (NDCG) improves while retrieval (Recall) can degrade due to reduced query diversity. To resolve this tradeoff, we propose a two-stage dynamic pruning (DP) strategy that adaptively modulates sampling probabilities at both query and document levels throughout training, prioritizing high-quality examples while maintaining access to the full training set. Evaluations across eight datasets spanning six domains demonstrate the effectiveness of both approaches: SP improves ranking over standard finetuning (NDCG@10 +0.5\%), while DP achieves the strongest performance on both ranking (NDCG@10 +1.9\%) and retrieval (Recall@20 +0.7\%), with an average rank of 1.38 across all methods. These findings scale to Qwen3-Embedding, an LLM-based dense retriever, confirming architecture-agnostic benefits. Notably, DP reaches comparable performance in less than 50\% of the training time required by standard finetuning.
Authors: Eden Saig, Tamar Garbuz, Ariel D. Procaccia, Inbal Talgam-Cohen, Jamie Tucker-Foltz
Abstract: When organizations delegate text generation tasks to AI providers via pay-for-performance contracts, expected payments rise when evaluation is noisy. As evaluation methods become more elaborate, the economic benefits of decreased noise are often overshadowed by increased evaluation costs. In this work, we introduce adaptive contracts for AI delegation, which allow detailed evaluation to be performed selectively after observing an initial coarse signal in order to conserve resources. We make three sets of contributions: First, we provide efficient algorithms for computing optimal adaptive contracts under natural assumptions or when core problem dimensions are small, and prove hardness of approximation in the general unstructured case. We then formulate alternative models of randomized adaptive contracts and discuss their benefits and limitations. Finally, we empirically demonstrate the benefits of adaptivity over non-adaptive baselines using question-answering and code-generation datasets.
Authors: Federico Albanese, Pablo Ronco, Nicol\'as D'Ippolito
Abstract: Responsible use of AI demands that we protect sensitive information without undermining the usefulness of data, an imperative that has become acute in the age of large language models. We address this challenge with an on-premise, LLM-driven substitution pipeline that anonymizes text by replacing personally identifiable information (PII) with realistic, type-consistent surrogates. Executed entirely within organizational boundaries using local LLMs, the approach prevents data egress while preserving fluency and task-relevant semantics. We conduct a systematic, multi-metric, cross-technique evaluation on the Action-Based Conversation Dataset, benchmarking against industry standards (Microsoft Presidio and Google DLP) and a state-of-the-art approach (ZSTS, in redaction-only and redaction-plus-substitution variants). Our protocol jointly measures privacy, semantic utility, and trainability under privacy via a lifecycle-ready criterion obtained by fine-tuning a compact encoder (BERT+LoRA) on sanitized text. In addition, we assess agentic Q&A performance by inserting an on-premise anonymization layer before the answering LLM and evaluating the quality of its responses. This intermediate, type-preserving substitution stage ensures that no sensitive content is exposed to third-party APIs, enabling responsible deployment of Q\&A agents without compromising confidentiality. Our method attains state-of-the-art privacy, minimal topical drift, strong factual utility, and low trainability loss, outperforming rule-based approaches and named-entity recognition (NER) baselines and ZSTS variants on the combined privacy--utility--trainability frontier. These results show that local LLM substitution yields anonymized corpora that are both responsible to use and operationally valuable: safe for agentic pipelines and suitable for downstream fine-tuning with limited degradation.
Authors: Ishrith Gowda, Chunwei Liu
Abstract: Multi-site neuroimaging analysis is fundamentally confounded by scanner-induced covariate shifts, where the marginal distribution of voxel intensities $P(\mathbf{x})$ varies non-linearly across acquisition protocols while the conditional anatomy $P(\mathbf{y}|\mathbf{x})$ remains constant. This is particularly detrimental to radiomic reproducibility, where acquisition variance often exceeds biological pathology variance. Existing statistical harmonization methods (e.g., ComBat) operate in feature space, precluding spatial downstream tasks, while standard deep learning approaches are theoretically bounded by local effective receptive fields (ERF), failing to model the global intensity correlations characteristic of field-strength bias. We propose SA-CycleGAN-2.5D, a domain adaptation framework motivated by the $H\Delta H$-divergence bound of Ben-David et al., integrating three architectural innovations: (1) A 2.5D tri-planar manifold injection preserving through-plane gradients $\nabla_z$ at $O(HW)$ complexity; (2) A U-ResNet generator with dense voxel-to-voxel self-attention, surpassing the $O(\sqrt{L})$ receptive field limit of CNNs to model global scanner field biases; and (3) A spectrally-normalized discriminator constraining the Lipschitz constant ($K_D \le 1$) for stable adversarial optimization. Evaluated on 654 glioma patients across two institutional domains (BraTS and UPenn-GBM), our method reduces Maximum Mean Discrepancy (MMD) by 99.1% ($1.729 \to 0.015$) and degrades domain classifier accuracy to near-chance (59.7%). Ablation confirms that global attention is statistically essential (Cohen's $d = 1.32$, $p < 0.001$) for the harder heterogeneous-to-homogeneous translation direction. By bridging 2D efficiency and 3D consistency, our framework yields voxel-level harmonized images that preserve tumor pathophysiology, enabling reproducible multi-center radiomic analysis.
Authors: Prajwal Panth, Agniva Maiti
Abstract: The rapid proliferation of Large Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous languages of the Global South from the AI revolution. The Tharu language, an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India, exemplifies this crisis. Despite a rich oral tradition, Tharu suffers from severe data scarcity and linguistic fragmentation, causing state-of-the-art multilingual models to routinely "hallucinate" or default to dominant high-resource neighbors like Hindi and Nepali due to contamination in pre-training corpora. This paper presents Tharu-LLaMA (3B), a specialized instruction-following model designed to address this exclusion. We introduce TharuChat, a novel dataset constructed via a LLM-to-Human bootstrapping pipeline. We utilized prompt-engineered Gemini models, fed with Rana Tharu grammar and folklore, to synthesize training data. Unlike curated gold-standard corpora, TharuChat reflects the noisy, heterogeneous linguistic reality of the region: it is predominantly anchored in Rana Tharu (~70%) while integrating elements of Dangaura and Kochila dialects. We provide a transparent analysis of the dataset's limitations, including dialectal code-mixing and residual Awadhi/Hindi influence. Through a rigorous empirical ablation study, we demonstrate that despite these imperfections, small-scale synthetic data is highly effective, increasing the dataset volume from 25% to 100% results in a linear reduction in perplexity from 6.42 to 2.88. The resulting model serves as a proof-of-concept for the preservation of under-resourced Himalayan languages via generative AI, achievable on consumer-grade hardware.
Authors: Boyong Wu, Sanghwan Kim, Zeynep Akata
Abstract: Multimodal Large Language Models (MLLMs) are increasingly applied to pixel-level vision tasks, yet their intrinsic capacity for spatial understanding remains poorly understood. We investigate segmentation capacity through a layerwise linear probing evaluation across the entire MLLM pipeline: vision encoder, adapter, and LLM. We further conduct an intervention based attention knockout analysis to test whether cross-token attention progressively refines visual representations, and an evaluation of bidirectional attention among image tokens on spatial consistency. Our analysis reveals that the adapter introduces a segmentation representation drop-off, but LLM layers progressively recover through attention-mediated refinement, where correctly classified tokens steer misclassified neighbors toward the correct label. At early image token positions, this recovery is bounded by causal attention, which bidirectional attention among image tokens alleviates. These findings provide a mechanistic account of how MLLMs process visual information for segmentation, informing the design of future segmentation-capable models.
Authors: Hengrui Luo, Xiaoye S. Li, Yang Liu, Marcus Noack, Ji Qiang, Mark D. Risser
Abstract: Gaussian process (GP) regression is widely used for uncertainty quantification, yet the standard formulation assumes noise-free covariates. When inputs are measured with error, this errors-in-variables (EIV) setting can lead to optimistically narrow posterior intervals and biased decisions. We study GP regression under input measurement uncertainty by representing each noisy input as a probability measure and defining covariance through Wasserstein distances between these measures. Building on this perspective, we instantiate a deterministic projected Wasserstein ARD (PWA) kernel whose one-dimensional components admit closed-form expressions and whose product structure yields a scalable, positive-definite kernel on distributions. Unlike latent-input GP models, PWA-based GPs (\PWAGPs) handle input noise without introducing unobserved covariates or Monte Carlo projections, making uncertainty quantification more transparent and robust.
Authors: Haozheng Luo, Yimin Wang, Jiahao Yu, Binghui Wang, Yan Chen
Abstract: We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state space. Methodologically, CRAFT integrates contrastive representation learning with reinforcement learning to separate safe and unsafe reasoning trajectories, yielding a latent-space geometry that supports robust, reasoning-level safety alignment. Theoretically, we show that incorporating latent-textual consistency into GRPO eliminates superficially aligned policies by ruling them out as local optima. Empirically, we evaluate CRAFT on multiple safety benchmarks using two strong reasoning models, Qwen3-4B-Thinking and R1-Distill-Llama-8B, where it consistently outperforms state-of-the-art defenses such as IPO and SafeKey. Notably, CRAFT delivers an average 79.0% improvement in reasoning safety and 87.7% improvement in final-response safety over the base models, demonstrating the effectiveness of hidden-space reasoning alignment.
Authors: Panuganti Chirag Sai, Gandholi Sarat, R. Raghunatha Sarma, Venkata Kalyan Tavva, Naveen M
Abstract: Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy and Latency Optimization), a explainable multi-agent online reinforcement learning framework that dynamically optimizes memory controller parameters using reward decomposition. ReLMXEL operates within the memory controller, leveraging detailed memory behavior metrics to guide decision-making. Experimental evaluations across diverse workloads demonstrate consistent performance gains over baseline configurations, with refinements driven by workload-specific memory access behaviour. By incorporating explainability into the learning process, ReLMXEL not only enhances performance but also increases the transparency of control decisions, paving the way for more accountable and adaptive memory system designs.
Authors: Aniruddha Bora, Julie Chalfant, Chryssostomos Chryssostomidis
Abstract: International shipping produces approximately 3% of global greenhouse gas emissions, yet voyage routing remains dominated by heuristic methods. We present PIER (Physics-Informed, Energy-efficient, Risk-aware routing), an offline reinforcement learning framework that learns fuel-efficient, safety-aware routing policies from physics-calibrated environments grounded in historical vessel tracking data and ocean reanalysis products, requiring no online simulator. Validated on one full year (2023) of AIS data across seven Gulf of Mexico routes (840 episodes per method), PIER reduces mean CO2 emissions by 10% relative to great-circle routing. However, PIER's primary contribution is eliminating catastrophic fuel waste: great-circle routing incurs extreme fuel consumption (>1.5x median) in 4.8% of voyages; PIER reduces this to 0.5%, a 9-fold reduction. Per-voyage fuel variance is 3.5x lower (p<0.001), with bootstrap 95% CI for mean savings [2.9%, 15.7%]. Partial validation against observed AIS vessel behavior confirms consistency with the fastest real transits while exhibiting 23.1x lower variance. Crucially, PIER is forecast-independent: unlike A* path optimization whose wave protection degrades 4.5x under realistic forecast uncertainty, PIER maintains constant performance using only local observations. The framework combines physics-informed state construction, demonstration-augmented offline data, and a decoupled post-hoc safety shield, an architecture that transfers to wildfire evacuation, aircraft trajectory optimization, and autonomous navigation in unmapped terrain.
Authors: Ang Li, Xinyang Gong, Bozhou Chen, Yunlong Lu, Jiaming Ji, Yongyi Wang, Yaodong Yang, Wenxin Li
Abstract: We present ShuttleEnv, an interactive and data-driven simulation environment for badminton, designed to support reinforcement learning and strategic behavior analysis in fast-paced adversarial sports. The environment is grounded in elite-player match data and employs explicit probabilistic models to simulate rally-level dynamics, enabling realistic and interpretable agent-opponent interactions without relying on physics-based simulation. In this demonstration, we showcase multiple trained agents within ShuttleEnv and provide live, step-by-step visualization of badminton rallies, allowing attendees to explore different play styles, observe emergent strategies, and interactively analyze decision-making behaviors. ShuttleEnv serves as a reusable platform for research, visualization, and demonstration of intelligent agents in sports AI. Our ShuttleEnv demo video URL: https://drive.google.com/file/d/1hTR4P16U27H2O0-w316bR73pxE2ucczX/view
URLs: https://drive.google.com/file/d/1hTR4P16U27H2O0-w316bR73pxE2ucczX/view
Authors: Weiming Wu, Zi-Jian Cheng, Jie Meng, Peng Zhen, Shan Huang, Qun Li, Guobin Wu, Lan-Zhe Guo
Abstract: The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairness. However, the exponential surge in ride-hailing volume renders manual review intractable, while conventional automated methods lack the reasoning transparency required for quasi-judicial decisions. Although Multimodal LLMs offer a promising paradigm, they fundamentally struggle to bridge the gap between general visual semantics and rigorous evidentiary protocols, often leading to perceptual hallucinations and logical looseness. To address these systemic misalignments, we introduce RideJudge, a Progressive Visual-Logic-Aligned Framework. Instead of relying on generic pre-training, we bridge the semantic gap via SynTraj, a synthesis engine that grounds abstract liability concepts into concrete trajectory patterns. To resolve the conflict between massive regulation volume and limited context windows, we propose an Adaptive Context Optimization strategy that distills expert knowledge, coupled with a Chain-of-Adjudication mechanism to enforce active evidentiary inquiry. Furthermore, addressing the inadequacy of sparse binary feedback for complex liability assessment, we implement a novel Ordinal-Sensitive Reinforcement Learning mechanism that calibrates decision boundaries against hierarchical severity. Extensive experiments show that our RideJudge-8B achieves 88.41\% accuracy, surpassing 32B-scale baselines and establishing a new standard for interpretable adjudication.
Authors: Ian Chen, Alfredo Alexander-Katz
Abstract: Free energies are fundamental quantities governing phase behavior and thermodynamic stability in polymer systems, yet their accurate computation often requires extensive simulations and post-processing techniques such as the Bennett Acceptance Ratio (BAR). While BAR provides reliable estimates when applied between closely related thermodynamic states, evaluating free energies across large changes in interaction strength typically requires a sequence of intermediate simulations to maintain sufficient phase-space overlap, substantially increasing computational cost. In this work we develop a machine learning framework for rapidly predicting excess free energies of linear diblock copolymer systems from simulation-derived energetic descriptors. Using dissipative particle dynamics simulations of freely-jointed chain polymers, we construct a dataset of per-chain energetic statistics, including heterogeneous interaction energies, homogeneous interaction energies, and bonded spring energies, and train feed-forward neural networks to learn the relationship between these descriptors and free energies computed using a stratified BAR procedure. The resulting models accurately reproduce the reference free energies across a range of chain lengths, compositions, and densities, including polymer architectures held out from training. In regimes where direct, brute-force BAR estimates become unreliable due to poor phase-space overlap, the neural network predictions remain consistent with the reference values. These results demonstrate that physically informed machine learning models can serve as efficient surrogates for expensive free-energy calculations and provide a promising approach for accelerating thermodynamic analysis of polymer systems.
Authors: Martin Monperrus
Abstract: A coding agent can bootstrap itself. Starting from a 926-word specification and a first implementation produced by an existing agent (Claude Code), a newly generated agent re-implements the same specification correctly from scratch. This reproduces, in the domain of AI coding agents, the classical bootstrap sequence known from compiler construction, and instantiates the meta-circular property known from Lisp. The result carries a practical implication: the specification, not the implementation, is the stable artifact of record. Improving an agent means improving its specification; the implementation is, in principle, regenerable at any time.
Authors: Shiming Chen, Shuhuang Chen, Guo-Sen Xie, Xinge You
Abstract: Zero-shot learning (ZSL) aims to recognize the unseen classes in the open-world guided by the side-information (e.g., attributes). Its key task is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus conducting a desirable semantic knowledge transfer from seen classes to unseen ones. Prior works simply utilize unidirectional attention within a weakly-supervised manner to learn the spurious and limited latent semantic representations, which fail to effectively discover the intrinsic semantic knowledge (e.g., attribute semantic) between visual and attribute features. To solve the above challenges, we propose a mutually causal semantic distillation network (termed MSDN++) to distill the intrinsic and sufficient semantic representations for ZSL. MSDN++ consists of an attribute$\rightarrow$visual causal attention sub-net that learns attribute-based visual features, and a visual$\rightarrow$attribute causal attention sub-net that learns visual-based attribute features. The causal attentions encourages the two sub-nets to learn causal vision-attribute associations for representing reliable features with causal visual/attribute learning. With the guidance of semantic distillation loss, the two mutual attention sub-nets learn collaboratively and teach each other throughout the training process. Extensive experiments on three widely-used benchmark datasets (e.g., CUB, SUN, AWA2, and FLO) show that our MSDN++ yields significant improvements over the strong baselines, leading to new state-of-the-art performances.
Authors: Ivor J. A. Simpson, Neill D. F. Campbell
Abstract: Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference. Variational inference has previously been employed to capture these distributions, however restrictive assumptions about the posterior form can lead to poor characterisation, overconfidence and low-quality samples. More flexible posteriors are typically bottlenecked by the complexity of high-dimensional covariance matrices required for dense 3D image registration. In this work, we present a memory and computationally efficient inference method, Structured SIR, that enables expressive, multi-modal, characterisation of uncertainty with high quality samples. We propose the use of a Sampled Importance Resampling (SIR) algorithm with a novel memory-efficient high-dimensional covariance parameterisation as the sum of a low-rank covariance and a sparse, spatially structured Cholesky precision factor. This structure enables capturing complex spatial correlations while remaining computationally tractable. We evaluate the efficacy of this approach in 3D dense image registration of brain MRI data, which is a very high-dimensional problem. We demonstrate that our proposed methods produces uncertainty estimates that are significantly better calibrated than those produced by variational methods, achieving equivalent or better accuracy. Crucially, we show that the model yields highly structured multi-modal posterior distributions, enable effective and efficient uncertainty quantification.
Authors: Akira Saito, Masato Tanaka
Abstract: Piecewise-linear nonlinear systems appear in many engineering disciplines. Prediction of the dynamic behavior of such systems is of great importance from practical and theoretical viewpoint. In this paper, a data-driven model order reduction method for piecewise-linear systems is proposed, which is based on dynamic mode decomposition (DMD). The overview of the concept of DMD is provided, and its application to model order reduction for nonlinear systems based on Galerkin projection is explained. The proposed approach uses impulse responses of the system to obtain snapshots of the state variables. The snapshots are then used to extract the dynamic modes that are used to form the projection basis vectors. The dynamics described by the equations of motion of the original full-order system are then projected onto the subspace spanned by the basis vectors. This produces a system with much smaller number of degrees of freedom (DOFs). The proposed method is applied to two representative examples of piecewise linear systems: a cantilevered beam subjected to an elastic stop at its end, and a bonded plates assembly with partial debonding. The reduced order models (ROMs) of these systems are constructed by using the Galerkin projection of the equation of motion with DMD modes alone, or DMD modes with a set of classical constraint modes to be able to handle the contact nonlinearity efficiently. The obtained ROMs are used for the nonlinear forced response analysis of the systems under harmonic loading. It is shown that the ROMs constructed by the proposed method produce accurate forced response results.
Authors: Ruibo Fan, Xiangrui Yu, Xinglin Pan, Zeyu Li, Weile Luo, Qiang Wang, Wei Wang, Xiaowen Chu
Abstract: Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to fundamental design mismatches with GPU architectures: at the kernel level, variable-length bitstreams produced by traditional entropy codecs break SIMT parallelism; at the system level, decoupled pipelines lead to redundant memory traffic. We present ZipServ, a lossless compression framework co-designed for efficient LLM inference. ZipServ introduces Tensor-Core-Aware Triple Bitmap Encoding (TCA-TBE), a novel fixed-length format that enables constant-time, parallel decoding, together with a fused decompression-GEMM (ZipGEMM) kernel that decompresses weights on-the-fly directly into Tensor Core registers. This "load-compressed, compute-decompressed" design eliminates intermediate buffers and maximizes compute intensity. Experiments show that ZipServ reduces the model size by up to 30%, achieves up to 2.21x kernel-level speedup over NVIDIA's cuBLAS, and expedites end-to-end inference by an average of 1.22x over vLLM. ZipServ is the first lossless compression system that provides both storage savings and substantial acceleration for LLM inference on GPUs.
Authors: Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato, Elvis Nunez, Matthew Trager, Wei Xia, Stefano Soatto
Abstract: Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We observe that most tokens do not require (Global) Attention over the entire sequence and can rely on local context. Based on this, we propose L2A (Learning To Attend), a layer that enables conditional (token-wise) long-range memory access by deciding when to invoke global attention. We evaluate L2A on Qwen 2.5 and Qwen 3 models, extending their effective context length from 32K to 128K tokens. L2A matches the performance of standard long-context training to within 3% while skipping Global Attention for $\sim$80% of tokens, outperforming prior baselines. We also design custom Triton kernels to efficiently implement this token-wise conditional Attention on GPUs, achieving up to $\sim$2x improvements in training throughput and time-to-first-token over FlashAttention. Moreover, L2A enables post-training pruning of highly sparse Global Attention layers, reducing KV cache memory by up to 50% with negligible performance loss.
Authors: Jiaxin Jiang, Lei Shi, Jiyuan Tan
Abstract: Mirror Descent (MD) is a scalable first-order method widely used in large-scale optimization, with applications in image processing, policy optimization, and neural network training. This paper generalizes MD to optimization on Riemannian manifolds. In particular, we develop a Riemannian Mirror Descent (RMD) framework via reparameterization and further propose a stochastic variant of RMD. We also establish non-asymptotic convergence guarantees for both RMD and stochastic RMD. As an application to the Stiefel manifold, our RMD framework reduces to the Curvilinear Gradient Descent (CGD) method proposed in [26]. Moreover, when specializing the stochastic RMD framework to the Stiefel setting, we obtain a stochastic extension of CGD, which effectively addresses large-scale manifold optimization problems.
Authors: Marco De Nadai, Edoardo D'Amico, Max Lefarov, Alexandre Tamborrino, Divita Vohra, Mark VanMiddlesworth, Shawn Lin, Jacqueline Wood, Jan Stypka, Eliza Klyce, Keshi Dai, Timothy Christopher Heath, Martin D. Gould, Yves Raimond, Sandeep Ghael, Tony Jebara, Andreas Damianou, Vladan Radosavljevic, Paul N. Bennett, Mounia Lalmas, Praveen Chandar
Abstract: LLMs are increasingly applied to recommendation, retrieval, and reasoning, yet deploying a single end-to-end model that can jointly support these behaviors over large, heterogeneous catalogs remains challenging. Such systems must generate unambiguous references to real items, handle multiple entity types, and operate under strict latency and reliability constraints requirements that are difficult to satisfy with text-only generation. While tool-augmented recommender systems address parts of this problem, they introduce orchestration complexity and limit end-to-end optimization. We view this setting as an instance of a broader research problem: how to adapt LLMs to reason jointly over multiple-domain entities, users, and language in a fully self-contained manner. To this end, we introduce NEO, a framework that adapts a pre-trained decoder-only LLM into a tool-free, catalog-grounded generator. NEO represents items as SIDs and trains a single model to interleave natural language and typed item identifiers within a shared sequence. Text prompts control the task, target entity type, and output format (IDs, text, or mixed), while constrained decoding guarantees catalog-valid item generation without restricting free-form text. We refer to this instruction-conditioned controllability as language-steerability. We treat SIDs as a distinct modality and study design choices for integrating discrete entity representations into LLMs via staged alignment and instruction tuning. We evaluate NEO at scale on a real-world catalog of over 10M items across multiple media types and discovery tasks, including recommendation, search, and user understanding. In offline experiments, NEO consistently outperforms strong task-specific baselines and exhibits cross-task transfer, demonstrating a practical path toward consolidating large-scale discovery capabilities into a single language-steerable generative model.
Authors: Saugat Aryal, Mark T. Keane
Abstract: Recently, in eXplainable AI (XAI), $\textit{even if}$ explanations -- so-called semi-factuals -- have emerged as a popular strategy that explains how a predicted outcome $\textit{can remain the same}$ even when certain input-features are altered. For example, in the commonly-used banking app scenario, a semi-factual explanation could inform customers about better options, other alternatives for their successful application, by saying "$\textit{Even if}$ you asked for double the loan amount, you would still be accepted". Most semi-factuals XAI algorithms focus on finding maximal value-changes to a single key-feature that do $\textit{not}$ alter the outcome (unlike counterfactual explanations that often find minimal value-changes to several features that alter the outcome). However, no current semi-factual method explains $\textit{why}$ these extreme value-changes do not alter outcomes; for example, a more informative semi-factual could tell the customer that it is their good credit score that allows them to borrow double their requested loan. In this work, we advance a new algorithm -- the $\textit{informative semi-factuals}$ (ISF) method -- that generates more elaborated explanations supplementing semi-factuals with information about additional $\textit{hidden features}$ that influence an automated decision. Experimental results on benchmark datasets show that this ISF method computes semi-factuals that are both informative and of high-quality on key metrics. Furthermore, a user study shows that people prefer these elaborated explanations over the simpler semi-factual explanations generated by current methods.
Authors: Edoardo D'Amico, Marco De Nadai, Praveen Chandar, Divita Vohra, Shawn Lin, Max Lefarov, Paul Gigioli, Gustavo Penha, Ilya Kopysitsky, Ivo Joel Senese, Darren Mei, Francesco Fabbri, Oguz Semerci, Yu Zhao, Vincent Tang, Brian St. Thomas, Alexandra Ranieri, Matthew N. K. Smith, Aaron Bernkopf, Bryan Leung, Ghazal Fazelnia, Mark VanMiddlesworth, Timothy Christopher Heath, Petter Pehrson Skiden, Alice Y. Wang, Doug J. Cole, Andreas Damianou, Maya Hristakeva, Reid Wilbur, Tarun Chillara, Vladan Radosavljevic, Pooja Chitkara, Sainath Adapa, Juan Elenter, Bernd Huber, Jacqueline Wood, Saaketh Vedantam, Jan Stypka, Sandeep Ghael, Martin D. Gould, David Murgatroyd, Yves Raimond, Mounia Lalmas, Paul N. Bennett
Abstract: Podcast listening is often grounded in a set of favorite shows, while listener intent can evolve over time. This combination of stable preferences and changing intent motivates recommendation approaches that support both familiarity and exploration. Traditional recommender systems typically emphasize long-term interaction patterns, and are less explicitly designed to incorporate rich contextual signals or flexible, intent-aware discovery objectives. In this setting, models that can jointly reason over semantics, context, and user state offer a promising direction. Large Language Models (LLMs) provide strong semantic reasoning and contextual conditioning for discovery-oriented recommendation, but deploying them in production introduces challenges in catalog grounding, user-level personalization, and latency-critical serving. We address these challenges with GLIDE, a production-scale generative recommender for podcast discovery at Spotify. GLIDE formulates recommendation as an instruction-following task over a discretized catalog using Semantic IDs, enabling grounded generation over a large inventory. The model conditions on recent listening history and lightweight user context, while injecting long-term user embeddings as soft prompts to capture stable preferences under strict inference constraints. We evaluate GLIDE using offline retrieval metrics, human judgments, and LLM-based evaluation, and validate its impact through large-scale online A/B testing. Across experiments involving millions of users, GLIDE increases non-habitual podcast streaming on Spotify home surface by up to 5.4% and new-show discovery by up to 14.3%, while meeting production cost and latency constraints.
Authors: Nicola J. M\"uller, Moritz Oster, Isabel Valera, J\"org Hoffmann, Timo P. Gros
Abstract: Learning per-domain generalizing policies is a key challenge in learning for planning. Standard approaches learn state-value functions represented as graph neural networks using supervised learning on optimal plans generated by a teacher planner. In this work, we advocate for learning Q-value functions instead. Such policies are drastically cheaper to evaluate for a given state, as they need to process only the current state rather than every successor. Surprisingly, vanilla supervised learning of Q-values performs poorly as it does not learn to distinguish between the actions taken and those not taken by the teacher. We address this by using regularization terms that enforce this distinction, resulting in Q-value policies that consistently outperform state-value policies across a range of 10 domains and are competitive with the planner LAMA-first.
Authors: Caren Hasler
Abstract: We study the consistency of the $k$-nearest neighbor regressor under complex survey designs. While consistency results for this algorithm are well established for independent and identically distributed data, corresponding results for complex survey data are lacking. We show that the $k$-nearest neighbor regressor is consistent under regularity conditions on the sampling design and the distribution of the data. We derive lower bounds for the rate of convergence and show that these bounds exhibit the curse of dimensionality, as in the independent and identically distributed setting. Empirical studies based on simulated and real data illustrate our theoretical findings.
Authors: Qianpu Chen, Giulio Barbero, Mike Preuss, Derya Soydaner
Abstract: We introduce Emergent Trust Learning (ETL), a lightweight, trust-based control algorithm that can be plugged into existing AI agents. It enables these to reach cooperation in competitive game environments under shared resources. Each agent maintains a compact internal trust state, which modulates memory, exploration, and action selection. ETL requires only individual rewards and local observations and incurs negligible computational and communication overhead. We evaluate ETL in three environments: In a grid-based resource world, trust-based agents reduce conflicts and prevent long-term resource depletion while achieving competitive individual returns. In a hierarchical Tower environment with strong social dilemmas and randomised floor assignments, ETL sustains high survival rates and recovers cooperation even after extended phases of enforced greed. In the Iterated Prisoner's Dilemma, the algorithm generalises to a strategic meta-game, maintaining cooperation with reciprocal opponents while avoiding long-term exploitation by defectors. Code will be released upon publication.
Authors: Nil Ayday, Lingchu Yang, Debarghya Ghoshdastidar
Abstract: Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models perform well in practice. In this work, we prove that attention-based architectures have structural benefits over graph convolutional networks in the context of node-level prediction tasks. Specifically, we study the neural network gaussian process limits of graph transformers (GAT, Graphormer, Specformer) with infinite width and infinite heads, and derive the node-level and edge-level kernels across the layers. Our results characterise how the node features and the graph structure propagate through the graph attention layers. As a specific example, we prove that graph transformers structurally preserve community information and maintain discriminative node representations even in deep layers, thereby preventing oversmoothing. We provide empirical evidence on synthetic and real-world graphs that validate our theoretical insights, such as integrating informative priors and positional encoding can improve performance of deep graph transformers.
Authors: Zihao Zheng, Zhihao Mao, Sicheng Tian, Maoliang Li, Jiayu Chen, Xinhao Sun, Zhaobo Zhang, Xuanzhe Liu, Donggang Cao, Hong Mei, Xiang Chen
Abstract: Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative Decoding (SD) is a promising acceleration method which can be divided into two categories: drafter-based SD and retrieval-based SD. Existing methods fail to analyze the advantages and disadvantages of these two types of SD in VLA models, leading to their sole application or optimization. In this paper, we analyze the trajectory patterns of robots controlled by the VLA model and derive a key insight: the two types of SD should be used in a hybrid manner. However, achieving hybrid SD in VLA models poses several challenges: (1) draft rejection and persistent errors in retrieval-based SD; (2) difficulty in determining the hybrid boundary. To address these, we propose the HeiSD framework. We propose a retrieval-based SD optimization method in HeiSD,which contains a verify-skip mechanism and a sequence-wise relaxed acceptance strategy. Moreover, we proposed a kinematic-based fused metric in HeiSD to automatically determine the hybrid boundary. Experimental results demonstrate that HeiSD attains a speedup of up to 2.45x in simulation benchmarks and 2.06x~2.41x in real-world scenarios, while sustaining a high task success rate.
Authors: Suryasis Jana, Abhik Ghosh
Abstract: Neural networks are central to modern artificial intelligence, yet their training remains highly sensitive to data contamination. Standard neural classifiers are trained by minimizing the categorical cross-entropy loss, corresponding to maximum likelihood estimation under a multinomial model. While statistically efficient under ideal conditions, this approach is highly vulnerable to contaminated observations including label noises corrupting supervision in the output space, and adversarial perturbations inducing worst-case deviations in the input space. In this paper, we propose a unified and statistically grounded framework for robust neural classification that addresses both forms of contamination within a single learning objective. We formulate neural network training as a minimum-divergence estimation problem and introduce rSDNet, a robust learning algorithm based on the general class of $S$-divergences. The resulting training objective inherits robustness properties from classical statistical estimation, automatically down-weighting aberrant observations through model probabilities. We establish essential population-level properties of rSDNet, including Fisher consistency, classification calibration implying Bayes optimality, and robustness guarantees under uniform label noise and infinitesimal feature contamination. Experiments on three benchmark image classification datasets show that rSDNet improves robustness to label corruption and adversarial attacks while maintaining competitive accuracy on clean data, Our results highlight minimum-divergence learning as a principled and effective framework for robust neural classification under heterogeneous data contamination.
Authors: Liang Shi, Jiarui Lu, Junqi Liu, Chence Shi, Zhi Yang, Jian Tang
Abstract: Understanding the dynamic behavior of biomolecules is fundamental to elucidating biological function and facilitating drug discovery. While Molecular Dynamics (MD) simulations provide a rigorous physical basis for studying these dynamics, they remain computationally expensive for long timescales. Conversely, recent deep generative models accelerate conformation generation but are typically either failing to model temporal relationship or built only for monomeric proteins. To bridge this gap, we introduce ATMOS, a novel generative framework based on State Space Models (SSM) designed to generate atom-level MD trajectories for biomolecular systems. ATMOS integrates a Pairformer-based state transition mechanism to capture long-range temporal dependencies, with a diffusion-based module to decode trajectory frames in an autoregressive manner. ATMOS is trained across crystal structures from PDB and conformation trajectory from large-scale MD simulation datasets including mdCATH and MISATO. We demonstrate that ATMOS achieves state-of-the-art performance in generating conformation trajectories for both protein monomers and complex protein-ligand systems. By enabling efficient inference of atomic trajectory of motions, this work establishes a promising foundation for modeling biomolecular dynamics.
Authors: Roy Henha Eyono, Daniel Levenstein, Arna Ghosh, Jonathan Cornford, Blake Richards
Abstract: Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to changes in the distribution of their inputs. In artificial neural networks (ANNs), normalization is used to improve learning in tasks that involve complex input distributions. However, it is unclear whether inhibition-mediated normalization in biological neural circuits also improves learning. Here, we explore this possibility using ANNs with separate excitatory and inhibitory populations trained on an image recognition task with variable luminosity. We find that inhibition-mediated normalization does not improve learning if normalization is applied only during inference. However, when this normalization is extended to include back-propagated errors, performance improves significantly. These results suggest that if inhibition-mediated normalization improves learning in the brain, it additionally requires the normalization of learning signals.
Authors: Jaemin Kim, Jong Chul Ye
Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge, it introduces retrieval-prior conflicts that can degrade generation quality. While this problem has been studied in autoregressive language models, it remains largely unexplored in diffusion-based language models, where the iterative denoising process introduces unique challenges for integrating retrieved context. In this work, we propose Adaptive Retrieval-Augmented Masked Diffusion (ARAM), a training-free adaptive guidance framework for Masked Diffusion Models (MDMs) in RAG settings. ARAM dynamically calibrates the guidance scale during denoising according to the Signal-to-Noise Ratio (SNR) of the distributional shift induced by retrieved context. Intuitively, the model strengthens guidance when the retrieved context provides reliable corrective evidence and suppresses it when the contextual signal is noisy or non-supportive. Extensive experiments on multiple knowledge-intensive QA benchmarks show that ARAM improves overall QA performance over competitive RAG baselines.
Authors: Mohsen Arjmandi
Abstract: Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful hypotheses. We present Sensi, an LLM agent architecture for the ARC-AGI-3 game-playing challenge that introduces structured test-time learning through three mechanisms: (1) a two-player architecture separating perception from action, (2) a curriculum-based learning system managed by an external state machine, and (3) a database-as-control-plane that makes the agents context window programmatically steerable. We further introduce an LLM-as-judge component with dynamically generated evaluation rubrics to determine when the agent has learned enough about one topic to advance to the next. We report results across two iterations: Sensi v1 solves 2 game levels using the two-player architecture alone, while Sensi v2 adds curriculum learning and solves 0 levels - but completes its entire learning curriculum in approximately 32 action attempts, achieving 50-94x greater sample efficiency than comparable systems that require 1600-3000 attempts. We precisely diagnose the failure mode as a self-consistent hallucination cascade originating in the perception layer, demonstrating that the architectural bottleneck has shifted from learning efficiency to perceptual grounding - a more tractable problem.
Authors: Tommaso Giovannelli, Jingfu Tan, Luis Nunes Vicente
Abstract: In this paper, we develop a stochastic set-valued optimization (SVO) framework tailored for robust machine learning. In the SVO setting, each decision variable is mapped to a set of objective values, and optimality is defined via set relations. We focus on SVO problems with hyperbox sets, which can be reformulated as multi-objective optimization (MOO) problems with finitely many objectives and serve as a foundation for representing or approximating more general mapped sets. Two special cases of hyperbox-valued optimization (HVO) are interval-valued (IVO) and rectangle-valued (RVO) optimization. We construct stochastic IVO/RVO formulations that incorporate subquantiles and superquantiles into the objective functions of the MOO reformulations, providing a new characterization for subquantiles. These formulations provide interpretable trade-offs by capturing both lower- and upper-tail behaviors of loss distributions, thereby going beyond standard empirical risk minimization and classical robust models. To solve the resulting multi-objective problems, we adopt stochastic multi-gradient algorithms and select a Pareto knee solution. In numerical experiments, the proposed algorithms with this selection strategy exhibit improved robustness and reduced variability across test replications under distributional shift compared with empirical risk minimization, while maintaining competitive accuracy.
Authors: Matthew Wiesner, Samuele Cornell, Alexander Polok, Lucas Ondel Yang, Luk\'a\v{s} Burget, Sanjeev Khudanpur
Abstract: We propose to model parallel streams of data, such as overlapped speech, using shuffles. Specifically, this paper shows how the shuffle product and partial order finite-state automata (FSAs) can be used for alignment and speaker-attributed transcription of overlapped speech. We train using the total score on these FSAs as a loss function, marginalizing over all possible serializations of overlapping sequences at subword, word, and phrase levels. To reduce graph size, we impose temporal constraints by constructing partial order FSAs. We address speaker attribution by modeling (token, speaker) tuples directly. Viterbi alignment through the shuffle product FSA directly enables one-pass alignment. We evaluate performance on synthetic LibriSpeech overlaps. To our knowledge, this is the first algorithm that enables single-pass alignment of multi-talker recordings. All algorithms are implemented using k2 / Icefall.
Authors: Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Gaiyang Han, Wanqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen
Abstract: Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as pseudo-labels. However, we identify a critical failure mode: as training maximizes self-consistency, output diversity collapses, causing the model to confidently reinforce systematic errors that evade detection. We term this the consensus trap. To escape it, we propose CoVerRL, a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other. Majority voting provides noisy but informative supervision for training the verifier, while the improving verifier progressively filters self-consistent errors from pseudo-labels. This co-evolution creates a virtuous cycle that maintains high reward accuracy throughout training. Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9\% on mathematical reasoning benchmarks. Moreover, self-verification accuracy improves from around 55\% to over 85\%, confirming that both capabilities genuinely co-evolve.
Authors: Romil Imtiaz, Dimitris K. Iakovidis
Abstract: We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event decoding. The system predicts 17 labels, including 5 anatomy classes and 12 pathology classes, from frames resized to 336x336. A major challenge was severe class imbalance, particularly for rare pathology labels. To address this, we used clipped class-wise positive weighting in the training loss, which improved rare-class learning while maintaining stable optimization. At the temporal stage, we found that direct frame-to-event conversion produced fragmented mismatches with the official ground truth. The final submission therefore combined GT-style framewise event composition, anatomy vote smoothing, and anatomy-based pathology gating with a conservative hysteresis decoder. This design improved the final temporal mAP from 0.3801 to 0.4303 on the challenge test set.
Authors: Narjes Ansari, C\'esar Feniou, Nicola\"i Gouraud, Daniele Loco, Siwar Badreddine, Baptiste Claudon, F\'elix Aviat, Marharyta Blazhynska, Kevin Gasperich, Guillaume Michel, Diata Traore, Corentin Villot, Thomas Pl\'e, Olivier Adjoua, Louis Lagard\`ere, Jean-Philip Piquemal
Abstract: Integrating quantum mechanics into drug discovery marks a decisive shift from empirical trial-and-error toward quantitative precision. However, the prohibitive cost of ab initio molecular dynamics has historically forced a compromise between chemical accuracy and computational scalability. This paper identifies the convergence of High-Performance Computing (HPC), Machine Learning (ML), and Quantum Computing (QC) as the definitive solution to this bottleneck. While ML foundation models, such as FeNNix-Bio1, enable quantum-accurate simulations, they remain tethered to the inherent limits of classical data generation. We detail how High-Performance Quantum Computing (HPQC), utilizing hybrid QPU-GPU architectures, will serve as the ultimate accelerator for quantum chemistry data. By leveraging Hilbert space mapping, these systems can achieve true chemical accuracy while bypassing the heuristics of classical approximations. We show how this tripartite convergence optimizes the drug discovery pipeline, spanning from initial system preparation to ML-driven, high-fidelity simulations. Finally, we position quantum-enhanced sampling as the beyond GPU frontier for modeling reactive cellular systems and pioneering next-generation materials.
Authors: Dmitriy Rivkin, Parker Ewen, Lili Gao, Julian Ost, Stefanie Walz, Rasika Kangutkar, Mario Bijelic, Felix Heide
Abstract: Recent video diffusion models achieve high-quality generation through recurrent frame processing where each frame generation depends on previous frames. However, this recurrent mechanism means that training such models in the pixel domain incurs prohibitive memory costs, as activations accumulate across the entire video sequence. This fundamental limitation also makes fine-tuning these models with pixel-wise losses computationally intractable for long or high-resolution videos. This paper introduces ChopGrad, a truncated backpropagation scheme for video decoding, limiting gradient computation to local frame windows while maintaining global consistency. We provide a theoretical analysis of this approximation and show that it enables efficient fine-tuning with frame-wise losses. ChopGrad reduces training memory from scaling linearly with the number of video frames (full backpropagation) to constant memory, and compares favorably to existing state-of-the-art video diffusion models across a suite of conditional video generation tasks with pixel-wise losses, including video super-resolution, video inpainting, video enhancement of neural-rendered scenes, and controlled driving video generation.
Authors: Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse, Sanjeel Parekh, Calvin Murdock, Yuliang Li, W. Owen Brimijoin, Vamsi Krishna Ithapu, Ishwarya Ananthabhotla
Abstract: In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits many downstream media applications. Concretely, we study the narrative-to-play task: inferring stage-play layouts (scenes, speaker positions, movements, and room types) from text that lacks explicit spatial, positional, or relational cues. We then introduce a dramaturgy-inspired deterministic evaluation suite and, finally, a training and inference recipe that combines rejection SFT using Best-of-N sampling with RL from verifiable rewards via GRPO. Experiments on a text-only corpus of classical English literature demonstrate improvements over vanilla models across multiple metrics (character attribution, spatial plausibility, and movement economy), as well as alignment with an LLM-as-a-judge and subjective human preferences.
Authors: Petros Ellinas, Indrajit Chaudhuri, Johanna Vorwerk, Spyros Chatzivasileiadis
Abstract: Physics-informed machine learning surrogates are increasingly explored to accelerate dynamic simulation of generators, converters, and other power grid components. The key question, however, is not only whether a surrogate matches a stand-alone component model on average, but whether it remains accurate after insertion into a differential-algebraic simulator, where the surrogate outputs enter the algebraic equations coupling the component to the rest of the system. This paper formulates that in-simulator use as a verification and validation (V\&V) problem. A finite-horizon bound is derived that links allowable component-output error to algebraic-coupling sensitivity, dynamic error amplification, and the simulation horizon. Two complementary settings are then studied: model-based verification against a reference component solver, and data-based validation through conformal calibration of the component-output variables exchanged with the simulator. The framework is general, but the case study focuses on physics-informed neural-network surrogates of second-, fourth-, and sixth-order synchronous-machine models. Results show that good stand-alone surrogate accuracy does not by itself guarantee accurate in-simulator behavior, that the largest discrepancies concentrate in stressed operating regions, and that small equation residuals do not necessarily imply small state-trajectory errors.
Authors: Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Velickovic
Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs internally generate such scores remains unknown. We address two questions: first, when confidence is computed - just-in-time when requested, or automatically during answer generation and cached for later retrieval; and second, what verbal confidence represents - token log-probabilities, or a richer evaluation of answer quality? Focusing on Gemma 3 27B and Qwen 2.5 7B, we provide convergent evidence for cached retrieval. Activation steering, patching, noising, and swap experiments reveal that confidence representations emerge at answer-adjacent positions before appearing at the verbalization site. Attention blocking pinpoints the information flow: confidence is gathered from answer tokens, cached at the first post-answer position, then retrieved for output. Critically, linear probing and variance partitioning reveal that these cached representations explain substantial variance in verbal confidence beyond token log-probabilities, suggesting a richer answer-quality evaluation rather than a simple fluency readout. These findings demonstrate that verbal confidence reflects automatic, sophisticated self-evaluation -- not post-hoc reconstruction -- with implications for understanding metacognition in LLMs and improving calibration.
Authors: Sergey V. Samsonau
Abstract: Methodology bugs in scientific Python code produce plausible but incorrect results that traditional linters and static analysis tools cannot detect. Several research groups have built ML-specific linters, demonstrating that detection is feasible. Yet these tools share a sustainability problem: dependency on specific pylint or Python versions, limited packaging, and reliance on manual engineering for every new pattern. As AI-generated code increases the volume of scientific software, the need for automated methodology checking (such as detecting data leakage, incorrect cross-validation, and missing random seeds) grows. We present scicode-lint, whose two-tier architecture separates pattern design (frontier models at build time) from execution (small local model at runtime). Patterns are generated, not hand-coded; adapting to new library versions costs tokens, not engineering hours. On Kaggle notebooks with human-labeled ground truth, preprocessing leakage detection reaches 65% precision at 100% recall; on 38 published scientific papers applying AI/ML, precision is 62% (LLM-judged) with substantial variation across pattern categories; on a held-out paper set, precision is 54%. On controlled tests, scicode-lint achieves 97.7% accuracy across 66 patterns.
Authors: Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard
Abstract: Understanding when learning is statistically possible yet computationally hard is a central challenge in high-dimensional statistics. In this work, we investigate this question in the context of single- and multi-index models, classes of functions widely studied as benchmarks to probe the ability of machine learning methods to discover features in high-dimensional data. Our main contribution is to show that a Noise Sensitivity Exponent (NSE) - a simple quantity determined by the activation function - governs the existence and magnitude of statistical-to-computational gaps within a broad regime of these models. We first establish that, in single-index models with large additive noise, the onset of a computational bottleneck is fully characterized by the NSE. We then demonstrate that the same exponent controls a statistical-computational gap in the specialization transition of large separable multi-index models, where individual components become learnable. Finally, in hierarchical multi-index models, we show that the NSE governs the optimal computational rate in which different directions are sequentially learned. Taken together, our results identify the NSE as a unifying property linking noise robustness, computational hardness, and feature specialization in high-dimensional learning.
Authors: Ricardo J. Sandoval, Ian Waudby-Smith, Michael I. Jordan
Abstract: We consider a variant of sequential testing by betting where, at each time step, the statistician is presented with multiple data sources (arms) and obtains data by choosing one of the arms. We consider the composite global null hypothesis $\mathscr{P}$ that all arms are null in a certain sense (e.g. all dosages of a treatment are ineffective) and we are interested in rejecting $\mathscr{P}$ in favor of a composite alternative $\mathscr{Q}$ where at least one arm is non-null (e.g. there exists an effective treatment dosage). We posit an optimality desideratum that we describe informally as follows: even if several arms are non-null, we seek $e$-processes and sequential tests whose performance are as strong as the ones that have oracle knowledge about which arm generates the most evidence against $\mathscr{P}$. Formally, we generalize notions of log-optimality and expected rejection time optimality to more than one arm, obtaining matching lower and upper bounds for both. A key technical device in this optimality analysis is a modified upper-confidence-bound-like algorithm for unobservable but sufficiently "estimable" rewards. In the design of this algorithm, we derive nonasymptotic concentration inequalities for optimal wealth growth rates in the sense of Kelly [1956]. These may be of independent interest.
Authors: Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan, Niloy J. Mitra, Xuelin Chen
Abstract: Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However, optimal tokenization of 3D shapes remains an open question. State-of-the-art (SOTA) methods primarily rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression. These spatial hierarchies are often token-inefficient and lack semantic coherence for AR modeling. We propose Level-of-Semantics Tokenization (LoST), which orders tokens by semantic salience, such that early prefixes decode into complete, plausible shapes that possess principal semantics, while subsequent tokens refine instance-specific geometric and semantic details. To train LoST, we introduce Relational Inter-Distance Alignment (RIDA), a novel 3D semantic alignment loss that aligns the relational structure of the 3D shape latent space with that of the semantic DINO feature space. Experiments show that LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics. Moreover, LoST achieves efficient, high-quality AR 3D generation and enables downstream tasks like semantic retrieval, while using only 0.1%-10% of the tokens needed by prior AR models.
Authors: Jianrui Zhang, Yue Yang, Rohun Tripathi, Winson Han, Ranjay Krishna, Christopher Clark, Yong Jae Lee, Sangho Lee
Abstract: Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the vision transformer (ViT) exclusively for unimodal perception tasks such as action recognition and object segmentation, without adapting to downstream vision-language tasks; or (2) only within the LLM while leaving the ViT output intact, often requiring complex text-conditioned token selection mechanisms. In this paper, we introduce Spatio-Temporal Token Scoring (STTS), a simple and lightweight module that prunes vision tokens across both the ViT and the LLM without text conditioning or token merging, and is fully compatible with end-to-end training. By learning how to score temporally via an auxiliary loss and spatially via LLM downstream gradients, aided by our efficient packing algorithm, STTS prunes 50% of vision tokens throughout the entire architecture, resulting in a 62% improvement in efficiency during both training and inference with only a 0.7% drop in average performance across 13 short and long video QA tasks. Efficiency gains increase with more sampled frames per video. Applying test-time scaling for long-video QA further yields performance gains of 0.5-1% compared to the baseline. Overall, STTS represents a novel, simple yet effective technique for unified, architecture-wide vision token pruning.
Authors: Ling Chen, Jiahui Xu, Binqing Wu, Mingqi Lv, Chaoqun Zhan, Sanjian Chen, Jian Chang
Abstract: Accurately forecasting air quality is critical to protecting general public from lung and heart diseases. This is a challenging task due to the complicated interactions among distinct pollution sources and various other influencing factors. Existing air quality forecasting methods cannot effectively model the diffusion processes of air pollutants between cities and monitoring stations, which may suddenly deteriorate the air quality of a region. In this paper, we propose HighAir, i.e., a hierarchical graph neural network-based air quality forecasting method, which adopts an encoder-decoder architecture and considers complex air quality influencing factors, e.g., weather and land usage. Specifically, we construct a city-level graph and station-level graphs from a hierarchical perspective, which can consider city-level and station-level patterns, respectively. We design two strategies, i.e., upper delivery and lower updating, to implement the inter-level interactions, and introduce message passing mechanism to implement the intra-level interactions. We dynamically adjust edge weights based on wind direction to model the correlations between dynamic factors and air quality. We compare HighAir with the state-of-the-art air quality forecasting methods on the dataset of Yangtze River Delta city group, which covers 10 major cities within 61,500 km2. The experimental results show that HighAir significantly outperforms other methods.
Authors: Bart Cox, Lydia Y. Chen, J\'er\'emie Decouchant
Abstract: Federated Learning (FL) is a popular approach for distributed deep learning that prevents the pooling of large amounts of data in a central server. FL relies on clients to update a global model using their local datasets. Classical FL algorithms use a central federator that, for each training round, waits for all clients to send their model updates before aggregating them. In practical deployments, clients might have different computing powers and network capabilities, which might lead slow clients to become performance bottlenecks. Previous works have suggested to use a deadline for each learning round so that the federator ignores the late updates of slow clients, or so that clients send partially trained models before the deadline. To speed up the training process, we instead propose Aergia, a novel approach where slow clients (i) freeze the part of their model that is the most computationally intensive to train; (ii) train the unfrozen part of their model; and (iii) offload the training of the frozen part of their model to a faster client that trains it using its own dataset. The offloading decisions are orchestrated by the federator based on the training speed that clients report and on the similarities between their datasets, which are privately evaluated thanks to a trusted execution environment. We show through extensive experiments that Aergia maintains high accuracy and significantly reduces the training time under heterogeneous settings by up to 27% and 53% compared to FedAvg and TiFL, respectively.
Authors: Jun Sun, Wancheng Zhang, Chao Zhou, Zhongjie Mao, Chao Li, Xiao-Jun Wu
Abstract: Semi-supervised learning (SSL) has been proven to be a powerful method for leveraging unlabeled data to alleviate models'dependence on large labeled datasets. The common framework among recent approaches is to train the model on a large amount of unlabeled data with consistency regularization to constrain the model predictions to be invariant to input perturbation. This paper proposes a feature space renormalizati-on (FSR) mechanism for SSL, which imposes consistency on feature representations rather than on labels to enable the model to learn better discriminative features. In order to apply this mechanism to SSL, we design a dual-branch FSR module consisting of a dual-branch header and an FSR block. This module can be seamlessly plugged and played into existing SSL frameworks to enhance the performance of the base SSL. The experimental results show that our proposed FSR module helps the base SSL framework (e.g. CRMatch and FreeMatch), achieve better performance on a variety of standard SSL benchmark datasets, without incurring additional overhead in terms of computation time and GPU memory.
Authors: Bruno Laboissiere Camargos Borges, Bruno Machado Pacheco, Danilo Silva
Abstract: In semantic segmentation, even state-of-the-art deep learning models fall short of the performance required in certain high-stakes applications such as medical image analysis. In these cases, performance can be improved by allowing a model to abstain from making predictions when confidence is low, an approach known as selective prediction. While well-known in the classification literature, selective prediction has been underexplored in the context of semantic segmentation. This paper tackles the problem by focusing on image-level abstention, which involves producing a single confidence estimate for the entire image, in contrast to previous approaches that focus on pixel-level uncertainty. Assuming the Dice coefficient as the evaluation metric for segmentation, two main contributions are provided in this paper: (i) In the case of known marginal posterior probabilities, we derive the optimal confidence estimator, which is observed to be intractable for typical image sizes. Then, an approximation computable in linear time, named Soft Dice Confidence (SDC), is proposed and proven to be tightly bounded to the optimal estimator. (ii) When only an estimate of the marginal posterior probabilities are known, we propose a plug-in version of the SDC and show it outperforms all previous methods, including those requiring additional tuning data. These findings are supported by experimental results on both synthetic data and real-world data from six medical imaging tasks, including out-of-distribution scenarios, positioning the SDC as a reliable and efficient tool for selective prediction in semantic segmentation.
Authors: Chuang Liu, Zelin Yao, Xueqi Ma, Mukun Chen, Luzhi Wang, Jia Wu, Wenbin Hu
Abstract: Graph Masked Autoencoders (GMAEs) have emerged as a notable self-supervised learning approach for graph-structured data. Existing GMAE models primarily focus on reconstructing node-level information, categorizing them as single-scale GMAEs. This methodology, while effective in certain contexts, tends to overlook the complex hierarchical structures inherent in many real-world graphs. For instance, molecular graphs exhibit a clear hierarchical organization in the form of the atoms-functional groups-molecules structure. Therefore, the inability of single-scale GMAE models to incorporate these hierarchical relationships often results in an inadequate capture of crucial high-level graph information, leading to a noticeable decline in performance. To address this limitation, we propose Hierarchical Graph Masked AutoEncoders (Hi-GMAE), a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. First, Hi-GMAE constructs a multi-scale graph hierarchy through graph pooling, enabling the exploration of graph structures across different granularity levels. To ensure masking uniformity of subgraphs across these scales, we propose a novel coarse-to-fine strategy that initiates masking at the coarsest scale and progressively back-projects the mask to finer scales. Furthermore, we integrate a gradual recovery strategy with the masking process to mitigate the learning challenges posed by completely masked subgraphs. Our experiments on 17 graph datasets, covering two graph learning tasks, consistently demonstrate that Hi-GMAE outperforms 29 state-of-the-art self-supervised competitors in capturing comprehensive graph information.
Authors: Francesco Montagna, Max Cairney-Leeming, Dhanya Sridhar, Francesco Locatello
Abstract: Supervised learning for causal discovery from observational data often achieves competitive performance despite seemingly avoiding the explicit assumptions that traditional methods require for identifiability. In this work, we analyze CSIvA (Ke et al., 2023) on bivariate causal models, a transformer architecture for amortized inference promising to train on synthetic data and transfer to real ones. First, we bridge the gap with identifiability theory, showing that the training distribution implicitly defines a prior on the causal model of the test observations: consistent with classical approaches, good performance is achieved when we have a good prior on the test data, and the underlying model is identifiable. Second, we find that CSIvA can not generalize to classes of causal models unseen during training: to overcome this limitation, we theoretically and empirically analyze \textit{when} training CSIvA on datasets generated by multiple identifiable causal models with different structural assumptions improves its generalization at test time. Overall, we find that amortized causal discovery with transformers still adheres to identifiability theory, violating the previous hypothesis from Lopez-Paz et al. (2015) that supervised learning methods could overcome its restrictions.
Authors: Ruining Yang, Yi Xu, Yun Fu, Lili Su
Abstract: Trajectory prediction in autonomous driving has traditionally been studied from a model-centric perspective. However, existing datasets exhibit a strong long-tail distribution in scenario density, where common low-density cases dominate and safety-critical high-density cases are severely underrepresented. This imbalance limits model robustness and hides failure modes when standard evaluations average errors across all scenarios. We revisit trajectory prediction from a data-centric perspective and present Den-TP, a framework for density-aware dataset curation and evaluation. Den-TP first partitions data into density-conditioned regions using agent count as a dataset-agnostic proxy for interaction complexity. It then applies a gradient-based submodular selection objective to choose representative samples within each region while explicitly rebalancing across densities. The resulting subset reduces the dataset size by 50\% yet preserves overall performance and significantly improves robustness in high-density scenarios. We further introduce density-conditioned evaluation protocols that reveal long-tail failure modes overlooked by conventional metrics. Experiments on Argoverse 1 and 2 with state-of-the-art models show that robust trajectory prediction depends not only on data scale, but also on balancing scenario density.
Authors: Jesse Friedbaum, Sudarshan Adiga, Ravi Tandon
Abstract: We propose a new and intuitive metric for aleatoric uncertainty quantification (UQ), the prevalence of class collisions defined as the same input being observed in different classes. We use the rate of class collisions to define the collision matrix, a novel and uniquely fine-grained measure of uncertainty. For a classification problem involving $K$ classes, the $K\times K$ collision matrix $S$ measures the inherent difficulty in distinguishing between each pair of classes. We discuss several applications of the collision matrix, establish its fundamental mathematical properties, and show its relationship with existing UQ methods, including the Bayes error rate (BER). We also address the new problem of estimating the collision matrix using one-hot labeled data by proposing a series of innovative techniques to estimate $S$. First, we learn a pair-wise contrastive model which accepts two inputs and determines if they belong to the same class. We then show that this contrastive model (which is PAC learnable) can be used to estimate the row Gramian matrix of $S$, defined as $G=SS^T$. Finally, we show that under reasonable assumptions, $G$ can be used to uniquely recover $S$, a new result on non-negative matrices which could be of independent interest. With a method to estimate $S$ established, we demonstrate how this estimate of $S$, in conjunction with the contrastive model, can be used to estimate the posterior class probability distribution of any point. Experimental results are also presented to validate our methods of estimating the collision matrix and class posterior distributions on several datasets.
Authors: Aleksandar Vujinovic, Aleksandar Kovacevic
Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to understand the environment. Consequently, they have underdeveloped world models. Self-supervised learning (SSL) offers an alternative, as it can learn a world model from diverse, unlabeled data. However, most SSL methods are inefficient because they operate in raw input space. In this work, we propose ACT-JEPA, a novel architecture that unifies IL and SSL to enhance policy representations. It is trained end-to-end to jointly predict 1) action sequences and 2) latent observation sequences. To learn in latent space, we utilize Joint-Embedding Predictive Architecture, which allows the model to filter out irrelevant details and learn a robust world model. We evaluate ACT-JEPA in different environments and across multiple tasks. Our results show that it outperforms the strongest baseline in all environments. ACT-JEPA achieves up to 40% improvement in world model understanding and up to 10% higher task success rate. Finally, we show that predicting latent observation sequences effectively generalizes to predicting action sequences. This work demonstrates how integrating IL and SSL leads to efficient policy representation learning, an improved world model, and a higher task success rate.
Authors: Xuyang Li, Romit Maulik
Abstract: Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However, real-world control systems, especially those requiring precise and reliable performance, often demand interpretability in the sense of a-priori assessments of agent behavior to identify safe or failure-prone interactions with environments. To address this limitation, this work proposes SALSA-RL (Stability Analysis in the Latent Space of Actions), a novel RL framework that models control actions as dynamic, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system, this approach enables interpretability through local stability analysis, where instantaneous growth in action-norms can be predicted before their execution. It is demonstrated that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation, SALSA-RL provides a powerful tool for advancing the design, analysis, and theoretical understanding of RL systems.
Authors: Yuxiao Wen, Yanjun Han, Zhengyuan Zhou
Abstract: We study regret minimization in repeated first-price auctions (FPAs), where a bidder observes only the realized outcome after each auction -- win or loss. This setup reflects practical scenarios in online display advertising where the actual value of an impression depends on the difference between two potential outcomes, such as clicks or conversion rates, when the auction is won versus lost. We incorporate causal inference into this framework and analyze the challenging case where only the treatment effect admits a simple dependence on observable features. Under this framework, we propose algorithms that jointly estimate private values and optimize bidding strategies under two different feedback types on the highest other bid (HOB): the full-information feedback where the HOB is always revealed, and the binary feedback where the bidder only observes the win-loss indicator. Under both cases, our algorithms are shown to achieve near-optimal regret bounds. Notably, our framework enjoys a unique feature that the treatments are actively chosen, and hence eliminates the need for the overlap condition commonly required in causal inference.
Authors: Ioannis Dimanidis, Tolga Ok, Peyman Mohajerin Esfahani
Abstract: Inspired by the recent successes of Inverse Optimization (IO) across various application domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for continuous state and action spaces, leveraging the convex loss function called ``sub-optimality loss'' from the IO literature. To mitigate the distribution shift commonly observed in ORL problems, we further employ a robust and non-causal Model Predictive Control (MPC) expert steering a nominal model of the dynamics using in-hindsight information stemming from the model mismatch. Unlike the existing literature, our robust MPC expert enjoys an exact and tractable convex reformulation. In the second part of this study, we show that the IO hypothesis class, trained by the proposed convex loss function, enjoys ample expressiveness and {reliably recovers teacher behavior in MuJoCo benchmarks. The method achieves competitive results compared to widely-used baselines in sample-constrained settings, despite using} orders of magnitude fewer parameters. To facilitate the reproducibility of our results, we provide an open-source package implementing the proposed algorithms and the experiments. The code is available at https://github.com/TolgaOk/offlineRLviaIO.
Authors: Xiaohong Yang, Minghui Liwang, Liqun Fu, Yuhan Su, Seyyedali Hosseinalipour, Xianbin Wang, Yiguang Hong
Abstract: Hierarchical Federated Learning (HFL) extends conventional Federated Learning (FL) by introducing intermediate aggregation layers, enabling distributed learning in geographically dispersed environments, particularly relevant for smart IoT systems, such as remote monitoring and battlefield operations, where cellular connectivity is limited. In these scenarios, UAVs serve as mobile aggregators, dynamically connecting terrestrial IoT devices. This paper investigates an HFL architecture with energy-constrained, dynamically deployed UAVs prone to communication disruptions. We propose a novel approach to minimize global training costs by formulating a joint optimization problem that integrates learning configuration, bandwidth allocation, and device-to-UAV association, ensuring timely global aggregation before UAV disconnections and redeployments. The problem accounts for dynamic IoT devices and intermittent UAV connectivity and is NP-hard. To tackle this, we decompose it into three subproblems: \textit{(i)} optimizing learning configuration and bandwidth allocation via an augmented Lagrangian to reduce training costs; \textit{(ii)} introducing a device fitness score based on data heterogeneity (via Kullback-Leibler divergence), device-to-UAV proximity, and computational resources, using a TD3-based algorithm for adaptive device-to-UAV assignment; \textit{(iii)} developing a low-complexity two-stage greedy strategy for UAV redeployment and global aggregator selection, ensuring efficient aggregation despite UAV disconnections. Experiments on diverse real-world datasets validate the approach, demonstrating cost reduction and robust performance under communication disruptions.
Authors: Cheng Zhen, Prayoga, Nischal Aryal, Arash Termehchy, Garrett Biwer, Lubna Alzamil
Abstract: Missing data often exists in real-world datasets, requiring significant time and effort for data repair to learn accurate models. In this paper, we show that imputing all missing values is not always necessary to achieve an accurate ML model. We introduce concepts of minimal and almost minimal repair, which are subsets of missing data items in training data whose imputation delivers accurate and reasonably accurate models, respectively. Imputing these subsets can significantly reduce the time, computational resources, and manual effort required for learning. We show that finding these subsets is NP-hard for some popular models and propose efficient approximation algorithms for wide range of models. Our extensive experiments indicate that our proposed algorithms can substantially reduce the time and effort required to learn on incomplete datasets.
Authors: Zihao Guo, Shuqing Shi, Richard Willis, Tristan Tomilin, Joel Z. Leibo, Yali Du
Abstract: Sequential social dilemmas pose a significant challenge in the field of multi-agent reinforcement learning (MARL), requiring environments that accurately reflect the tension between individual and collective interests. Previous benchmarks and environments, such as Melting Pot, provide an evaluation protocol that measures generalization to new social partners in various test scenarios. However, running reinforcement learning algorithms in traditional environments requires substantial computational resources. In this paper, we introduce SocialJax, a suite of sequential social dilemma environments and algorithms implemented in JAX. JAX is a high-performance numerical computing library for Python that enables significant improvements in operational efficiency. Our experiments demonstrate that the SocialJax training pipeline achieves at least 50\texttimes{} speed-up in real-time performance compared to Melting Pot RLlib baselines. Additionally, we validate the effectiveness of baseline algorithms within SocialJax environments. Finally, we use Schelling diagrams to verify the social dilemma properties of these environments, ensuring that they accurately capture the dynamics of social dilemmas.
Authors: Deshani Geethika Poddenige, Sachith Seneviratne, Asela Hevapathige, Damith Senanayake, Mahesan Niranjan, PN Suganthan, Saman Halgamuge
Abstract: Existing neural architecture representation learning methods focus on continuous representation learning, typically using Variational Autoencoders (VAEs) to map discrete architectures onto a continuous Gaussian distribution. However, sampling from these spaces often leads to a high percentage of invalid or duplicate neural architectures, likely due to the unnatural mapping of inherently discrete architectural space onto a continuous space. In this work, we revisit architecture representation learning from a fundamentally discrete perspective. We propose Arch-VQ, a framework that learns a discrete latent space of neural architectures using a Vector-Quantized Variational Autoencoder (VQ-VAE), and models the latent prior with an autoregressive transformer. This formulation yields discrete architecture representations that are better aligned with the underlying search space while decoupling representation learning from prior modeling. Across NASBench-101, NASBench-201, and DARTS search spaces, Arch-VQ improves the quality of generated architectures, increasing the rate of valid and unique generations by 22%, 26%, and 135%, respectively, over state-of-the-art baselines. We further show that modeling discrete embeddings autoregressively enhances downstream neural predictor performance, establishing the practical utility of this discrete formulation.
Authors: Alireza Aghabagherloo, Aydin Abadi, Sumanta Sarkar, Vishnu Asutosh Dasu, Bart Preneel
Abstract: The accuracy and robustness of machine learning models against adversarial attacks are significantly influenced by factors such as training data quality, model architecture, the training process, and the deployment environment. In recent years, duplicated data in training sets, especially in language models, has attracted considerable attention. It has been shown that deduplication enhances both training performance and model accuracy in language models. While the importance of data quality in training image classifier Deep Neural Networks (DNNs) is widely recognized, the impact of duplicated images in the training set on model generalization and performance has received little attention. In this paper, we address this gap and provide a comprehensive study on the effect of duplicates in image classification. Our analysis indicates that the presence of duplicated images in the training set not only negatively affects the efficiency of model training but also may result in lower accuracy of the image classifier. This negative impact of duplication on accuracy is particularly evident when duplicated data is non-uniform across classes or when duplication, whether uniform or non-uniform, occurs in the training set of an adversarially trained model. Even when duplicated samples are selected in a uniform way, increasing the amount of duplication does not lead to a significant improvement in accuracy.
Authors: Steven E. Wilson, Sina Khanmohammadi
Abstract: Graph Neural Networks (GNNs) have been widely used for various learning tasks, ranging from node classification to link prediction. They have demonstrated excellent performance in multiple domains involving graph-structured data. However, an important but less explored learning task is link weight prediction which is more complex than binary link classification. Link weight prediction becomes even more challenging when considering multilayer networks, where nodes can be connected across multiple layers. To address these challenges, we propose a new method called Multiplex Spatial Graph Convolution Network (MSGCN), which spatially embeds information across multiple layers to predict interlayer link weights. The MSGCN method generalizes spatial graph convolution to multiplex networks and captures the geometric structure of nodes across multiple layers. Extensive experiments using data with known interlayer link information show that the MSGCN model has robust, accurate, and generalizable link weight prediction performance across a wide variety of network structures. We also demonstrate a real-world application of the proposed method using the London transportation network. In this setting, MSGCN accurately predicts passenger loads in the multiplex network, where the interlayer link weights represent the number of passengers traveling between stations that are not directly connected.
Authors: Simone Piaggesi, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi
Abstract: Post-hoc explainability is essential for understanding black-box machine learning models. Surrogate-based techniques are widely used for local and global model-agnostic explanations but have significant limitations. Local surrogates capture non-linearities but are computationally expensive and sensitive to parameters, while global surrogates are more efficient but struggle with complex local behaviors. In this paper, we present ILLUME, a flexible and interpretable framework grounded in representation learning, that can be integrated with various surrogate models to provide explanations for any black-box classifier. Specifically, our approach combines a globally trained surrogate with instance-specific linear transformations learned with a meta-encoder to generate both local and global explanations. Through extensive empirical evaluations, we demonstrate the effectiveness of ILLUME in producing feature attributions and decision rules that are not only accurate but also robust and computationally efficient, thus providing a unified explanation framework that effectively addresses the limitations of traditional surrogate methods.
Authors: Jenni Lampainen, Kaisa Joki, Napsu Karmitsa, Marko M. M\"akel\"a
Abstract: Clustering is a fundamental task in data mining and machine learning, particularly for analyzing large-scale data. In this paper, we introduce Clust-Splitter, an efficient algorithm based on nonsmooth optimization, designed to solve the minimum sum-of-squares clustering problem in very large datasets. The clustering task is approached through a sequence of three nonsmooth optimization problems: two auxiliary problems used to generate suitable starting points, followed by a main clustering formulation. To solve these problems effectively, the limited memory bundle method is combined with an incremental approach to develop the Clust-Splitter algorithm. We evaluate Clust-Splitter on real-world datasets characterized by both a large number of attributes and a large number of data points and compare its performance with several state-of-the-art large-scale clustering algorithms. Experimental results demonstrate the efficiency of the proposed method for clustering very large datasets, as well as the high quality of its solutions, which are on par with those of the best existing methods.
Authors: Arjun Prakash, Naicheng He, Denizalp Goktas, Jacob Makar-Limanov, Amy Greenwald
Abstract: The dependency of the actor on the critic in actor-critic (AC) reinforcement learning means that AC can be characterized as a bilevel optimization (BLO) problem, also called a Stackelberg game. This characterization motivates two modifications to vanilla AC algorithms. First, the critic's update should be nested to learn a best response to the actor's policy. Second, the actor should update according to a hypergradient that takes changes in the critic's behavior into account. Computing this hypergradient involves finding an inverse Hessian vector product, a process that can be numerically unstable. We thus propose a new algorithm, Bilevel Policy Optimization with Nystr\"om Hypergradients (BLPO), which uses nesting to account for the nested structure of BLO, and leverages the Nystr\"om method to compute the hypergradient. Theoretically, we prove BLPO converges to (a point that satisfies the necessary conditions for) a local strong Stackelberg equilibrium in polynomial time with high probability, assuming a linear parametrization of the critic's objective. Empirically, we demonstrate that BLPO performs on par with or better than PPO on a variety of discrete and continuous control tasks.
Authors: Yasi Zhang, Tianyu Chen, Zhendong Wang, Ying Nian Wu, Mingyuan Zhou, Oscar Leong
Abstract: Learning generative models directly from corrupted observations is a long standing challenge across natural and scientific domains. We introduce Restoration Score Distillation (RSD), a unified framework for learning high fidelity, one step generative models using only degraded data and the mapping $A$ may be the identity or a non invertible corruption operator (e.g., blur, masking, subsampling, Fourier acquisition). RSD first pretrains a corruption aware diffusion teacher on the observed measurements, then distills it into an efficient one step generator whose samples are statistically closer to the clean distribution p_X. The framework subsumes identity corruption (denoising task) as a special case of our general formulation. Empirically, RSD consistently reduces Frechet Inception Distance (FID) relative to corruption aware diffusion teachers across noisy generation (CIFAR 10, FFHQ, CelebA HQ, AFHQ v2), image restoration (Gaussian deblurring, random inpainting, super resolution, and mixtures with additive noise), and multi coil MRI without access to any clean images. The distilled generator inherits one step sampling efficiency, yielding up to 30x speedups over multi step diffusion while surpassing the teachers after substantially fewer training iterations. These results establish score distillation as a practical tool for generative modeling from corrupted data, not merely for acceleration. We provide theoretical support for the use of distillation in enhancing generation quality in the Appendix.
Authors: Aobo Liang, Yan Sun, Xiaohou Shi, Ke Li
Abstract: In the past few years, time series foundation models have achieved superior predicting accuracy. However, real-world time series often exhibit significant diversity in their temporal patterns across different time spans and domains, making it challenging for a single model architecture to fit all complex scenarios. In addition, time series data may have multiple variables exhibiting complex correlations between each other. Recent mainstream works have focused on modeling times series in a channel-independent manner in both pretraining and finetuning stages, overlooking the valuable inter-series dependencies. To this end, we propose Time Tracker for better predictions on multivariate time series data. Firstly, we leverage sparse mixture of experts (MoE) within Transformers to handle the modeling of diverse time series patterns, thereby alleviating the learning difficulties of a single model while improving its generalization. Besides, we propose Any-variate Attention, enabling a unified model structure to seamlessly handle both univariate and multivariate time series, thereby supporting channel-independent modeling during pretraining and channel-mixed modeling for finetuning.Furthermore, we design a graph learning module that constructs relations among sequences from frequency-domain features, providing more precise guidance to capture inter-series dependencies in channel-mixed modeling. Based on these advancements, Time Tracker achieves state-of-the-art performance in predicting accuracy, model generalization and adaptability.
Authors: Naram Mhaisen, George Iosifidis
Abstract: We revisit the Follow the Regularized Leader (FTRL) framework for Online Convex Optimization (OCO) over compact sets, focusing on achieving dynamic regret guarantees. Prior work has highlighted the framework's limitations in dynamic environments due to its tendency to produce "lazy" iterates. However, building on insights showing FTRL's ability to produce "agile" iterates, we show that it can indeed recover known dynamic regret bounds through optimistic composition of future costs and careful linearization of past costs, which can lead to pruning some of them. This new analysis of FTRL against dynamic comparators yields a principled way to interpolate between lazy and agile updates and offers several benefits, including refined control over regret terms, optimism without cyclic dependence, and the application of minimal recursive regularization akin to AdaFTRL. More broadly, we show that it is not the "lazy" projection style of FTRL that hinders (optimistic) dynamic regret, but the decoupling of the algorithm's state (linearized history) from its iterates, allowing the state to grow arbitrarily. Instead, pruning synchronizes these two when necessary.
Authors: Peter Holderrieth, Ezra Erives
Abstract: Diffusion and flow-based models have become the state of the art for generative AI across a wide range of data modalities, including images, videos, shapes, molecules, music, and more. This tutorial provides a self-contained introduction to diffusion and flow-based generative models from first principles. We systematically develop the necessary mathematical background in ordinary and stochastic differential equations and derive the core algorithms of flow matching and denoising diffusion models. We then provide a step-by-step guide to building image and video generators, including training methods, guidance, and architectural design. This course is ideal for machine learning researchers who want to develop a principled understanding of the theory and practice of generative AI.
Authors: Yihong Guo, Yu Yang, Pan Xu, Anqi Liu
Abstract: We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions occurring in parts of the transition space with high dynamics shift. As a result, they optimize the policy using data from low-shift regions, limiting exploration of high-reward states in the target domain that do not fall within these regions. Consequently, such methods often fail when the dynamics shift is significant or the optimal trajectories lie outside the low-shift regions. To overcome this limitation, we propose MOBODY, a Model-Based Off-Dynamics Offline RL algorithm that optimizes a policy using learned target dynamics transitions to explore the target domain, rather than only being trained with the low dynamics-shift transitions. For the dynamics learning, built on the observation that achieving the same next state requires taking different actions in different domains, MOBODY employs separate action encoders for each domain to encode different actions to the shared latent space while sharing a unified representation of states and a common transition function. We further introduce a target Q-weighted behavior cloning loss in policy optimization to avoid out-of-distribution actions, which push the policy toward actions with high target-domain Q-values, rather than high source domain Q-values or uniformly imitating all actions in the offline dataset. We evaluate MOBODY on a wide range of MuJoCo and Adroit benchmarks, demonstrating that it outperforms state-of-the-art off-dynamics RL baselines as well as policy learning methods based on different dynamics learning baselines, with especially pronounced improvements in challenging scenarios where existing methods struggle.
Authors: Igor Urbanik, Pawe{\l} Gajewski
Abstract: Continual learning poses a fundamental challenge for neural systems, which often suffer from catastrophic forgetting when exposed to sequential tasks. Self-Organizing Maps (SOMs), despite their interpretability and efficiency, are not immune to this issue. In this paper, we introduce Saturation Self-Organizing Maps (SatSOM)-an extension of SOMs designed to improve knowledge retention in continual learning scenarios. SatSOM incorporates a novel saturation mechanism that gradually reduces the learning rate and neighborhood radius of neurons as they accumulate information. This effectively freezes well-trained neurons and redirects learning to underutilized areas of the map.
Authors: Zihan Guan, Zhiyuan Zhao, Fengwei Tian, Dung Nguyen, Payel Bhattacharjee, Ravi Tandon, B. Aditya Prakash, Anil Vullikanti
Abstract: Epidemic analyses increasingly rely on heterogeneous datasets, many of which are sensitive and require strong privacy protection. Although differential privacy (DP) has become a standard in machine learning and data sharing, its adoption in epidemiological modeling remains limited. In this work, we introduce DPEpiNN, a unified framework that integrates deep neural networks with a mechanistic SEIRM-based metapopulation model under formal DP guarantees. DPEpiNN supports multiple epidemic tasks (including multi-step forecasting, nowcasting, effective reproduction number $(R_t)$ estimation, and intervention analysis) within a single differentiable pipeline. The framework jointly learns epidemic parameters from heterogeneous public and sensitive datasets, while ensuring privacy via input perturbation mechanisms. We evaluate DPEpiNN using COVID-19 data from three regions. Results show that incorporating sensitive datasets substantially improves predictive performance even under strong privacy constraints. Compared with a deep learning baseline, DPEpiNN achieves higher accuracy in forecasting and nowcasting while producing reliable estimates of $R_t$. Furthermore, the learned epidemic transmission models remain inherently private due to the post-processing property of differential privacy, enabling downstream policy analyses such as simulation of social distancing interventions. Our work demonstrates that interpretability (through mechanistic modeling), predictive accuracy (through neural integration), and rigorous privacy guarantees can be jointly achieved in modern epidemic modeling.
Authors: Luca Stradiotti, Dario Pesenti, Stefano Teso, Jesse Davis
Abstract: Learning to Reject (LtR) frameworks allow ML models to abstain from uncertain predictions and promote user trust. However, since current LtR strategies focus solely on predictive performance, they completely neglect explanation quality. Low-quality explanations -- whether they inaccurately reflect the model's reasoning or fail to satisfy users -- can severely compromise trust assessments and induce over-reliance on incorrect predictions. We argue that models should abstain from making a prediction when they cannot offer a satisfactory explanation for it and introduce a framework for learning to reject low-quality explanations (LtX) in which predictors are equipped with a rejector that evaluates the explanation quality. Focusing on popular attribution techniques, we propose REX (REjector of low-quality eXplanations), which learns a rejector from explanation quality labels combining machine-side judgments with explicit human annotations to assess explanation quality. Our empirical evaluation demonstrates that \method outperforms popular LtR strategies and baselines relying on isolated explanation metrics. Finally, to support future research, we publicly release a novel, larger-scale dataset of 1050 human-annotated machine explanations.
Authors: Jinhyeok Jang, Jaehong Kim, Jung Uk Kim
Abstract: Pre-trained weights have become a cornerstone of modern deep learning, enabling efficient knowledge transfer and improving downstream task performance, especially in data-scarce scenarios. However, a fundamental question remains: how can we obtain better pre-trained weights that encapsulate more knowledge beyond the given dataset? In this work, we introduce KNowledge-Overflowed Weights (KNOW) prediction, a novel strategy that leverages structured forgetting and its inversion to synthesize knowledge-enriched weights. Our key insight is that sequential fine-tuning on progressively downsized datasets induces a structured forgetting process, which can be modeled and reversed to recover knowledge as if trained on a larger dataset. We construct a dataset of weight transitions governed by this controlled forgetting and employ meta-learning to model weight prediction effectively. Specifically, our KNowledge-Overflowed Weights Nowcaster (KNOWN) acts as a hyper-model that learns the general evolution of weights and predicts enhanced weights with improved generalization. Extensive experiments across diverse datasets and architectures demonstrate that KNOW prediction consistently outperforms Naive fine-tuning and simple weight prediction, leading to superior downstream performance. Our work provides a new perspective on reinterpreting forgetting dynamics to push the limits of knowledge transfer. The code and pre-trained model are available at https://github.com/jjh6297/KNOW
Authors: Kazuki Irie, Samuel J. Gershman
Abstract: Recent advances in artificial neural networks for machine learning, and language modeling in particular, have established a family of recurrent neural network (RNN) architectures that, unlike conventional RNNs with vector-form hidden states, use two-dimensional (2D) matrix-form hidden states. Such 2D-state RNNs, known as Fast Weight Programmers (FWPs), can be interpreted as a neural network whose synaptic weights (called fast weights) dynamically change over time as a function of input observations, and serve as short-term memory storage; corresponding synaptic weight modifications are controlled or programmed by another network (the programmer) whose parameters are trained (e.g., by gradient descent). In this Primer, we review the technical foundations of FWPs, their computational characteristics, and their connections to transformers and state space models. We also discuss connections between FWPs and models of synaptic plasticity in the brain, suggesting a convergence of natural and artificial intelligence.
Authors: Zhouyu Zhang, Chih-Yuan Chiu, Glen Chou
Abstract: We present an inverse dynamic game-based algorithm to learn parametric constraints from a given dataset of local Nash equilibrium interactions between multiple agents. Specifically, we introduce mixed-integer linear programs (MILP) encoding the Karush-Kuhn-Tucker (KKT) conditions of the interacting agents, which recover constraints consistent with the local Nash stationarity of the interaction demonstrations. We establish theoretical guarantees that our method learns inner approximations of the true safe and unsafe sets. We also use the interaction constraints recovered by our method to design motion plans that robustly satisfy the underlying constraints. Across simulations and hardware experiments, our methods accurately inferred constraints and designed safe interactive motion plans for various classes of constraints, both convex and non-convex, from interaction demonstrations of agents with nonlinear dynamics.
Authors: Guangli Li, Canbiao Wu, Zhehao Zhou, Na Tian, Li Zhang, Zhen Liang
Abstract: Electroencephalography (EEG)-based emotion recognition plays a critical role in affective Brain-Computer Interfaces (aBCIs), yet its practical deployment remains limited by inter-subject variability, reliance on target-domain data, and unavoidable label noise. To address these challenges, we propose a Multi-domain Aggregation Transfer learning framework with domain-class prototypes (MAT) for emotion recognition under completely unseen target domains. MAT introduces a feature decoupling module to disentangle class-invariant domain features from domain-invariant class features, enabling more robust and interpretable EEG representations. A Hierarchical-Domain Aggregation (HDA) mechanism based on Maximum Mean Discrepancy (MMD) constructs superdomains to model shared distributional structures across subjects, while adaptive prototype updating refines domain and class prototypes to capture stable intrinsic representations. Moreover, a pairwise learning strategy reformulates classification as similarity estimation between sample pairs, effectively mitigating the effect of label noise. Extensive experiments on three public EEG emotion datasets (SEED, SEED-IV, and SEED-V) show that the accuracy of MAT is improved by 2.87%, 3.84%, and 2.05% compared with the state-of-the-art (SOTA) model for unseen target domains. Our results provide a promising direction for emotion recognition under real-world unseen-subject scenarios.The source code is available at https://github.com/WuCB-BCI/MAT.
Authors: Rapha\"el Berthier
Abstract: Diagonal linear networks are neural networks with linear activation and diagonal weight matrices. Their theoretical interest is that their implicit regularization can be rigorously analyzed: from a small initialization, the training of diagonal linear networks converges to the linear predictor with minimal 1-norm among minimizers of the training loss. In this paper, we deepen this analysis showing that the full training trajectory of diagonal linear networks is closely related to the lasso regularization path. In this connection, the training time plays the role of an inverse regularization parameter. Both rigorous results and simulations are provided to illustrate this conclusion. Under a monotonicity assumption on the lasso regularization path, the connection is exact while in the general case, we show an approximate connection.
Authors: Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu
Abstract: Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer from the problem of sparse supervision. To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. By sharing common prefixes, the tree search sampling increases the number of rollouts achievable within a fixed budget of tokens or tool calls. Moreover, we find that the tree-structured trajectory naturally allows the construction of step-wise process supervised signals even using only the outcome reward. Based on this, Tree-GRPO estimates the grouped relative advantages both on intra-tree and inter-tree levels. Through theoretical analysis, we demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning. Experiments across 11 datasets and 3 types of QA tasks demonstrate the superiority of the proposed tree-based RL over the chain-based RL method.
Authors: Aayush Mishra, Daniel Khashabi, Anqi Liu
Abstract: Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapts models during inference with instructions or demonstrations in the prompt. ICL can offer better generalizability and more calibrated responses compared to SFT in data scarce settings, at the cost of more inference compute. In this work, we ask the question: Can ICL's internal computations be used to improve the qualities of SFT? We first show that ICL and SFT produce distinct activation patterns, indicating that the two methods achieve adaptation through different functional mechanisms. Motivated by this observation and to use ICL's rich functionality, we introduce ICL Activation Alignment (IA2), a self-distillation technique which aims to replicate ICL's activation patterns in SFT models and incentivizes ICL-like internal reasoning. Performing IA2 as a priming step before SFT significantly improves the accuracy and calibration of model outputs, as shown by our extensive empirical results on 12 popular benchmarks and two model families. This finding is not only practically useful, but also offers a conceptual window into the inner mechanics of model adaptation.
Authors: Qiushui Xu, Yuhao Huang, Yushu Jiang, Lei Song, Jinyu Wang, Wenliang Zheng, Jiang Bian
Abstract: Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inadequate for capturing the compositional structure of tasks that consist of diverse subtasks. We propose In-context Compositional Q-Learning (ICQL), an offline RL framework that formulates Q-learning as a contextual inference problem and uses linear Transformers to adaptively infer local Q-functions from retrieved transitions without explicit subtask labels. Theoretically, we show that, under two assumptions -- linear approximability of the local Q-function and accurate inference of weights from retrieved context -- ICQL achieves a bounded approximation error for the Q-function and enables near-optimal policy extraction. Empirically, ICQL substantially improves performance in offline settings, achieving gains of up to 16.4% on kitchen tasks and up to 8.8% and 6.3% on MuJoCo and Adroit tasks, respectively. These results highlight the underexplored potential of in-context learning for robust and compositional value estimation and establish ICQL as a principled and effective framework for offline RL.
Authors: Arpit Garg, Hemanth Saratchandran, Ravi Garg, Simon Lucey
Abstract: Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A widely used strategy, the gradient difference method, applies gradient descent to retained data while performing gradient ascent on forgotten data. When combined with cross-entropy, this procedure can trigger the unbounded growth of weights and gradients, degrading both forgetting and retention. We provide a theoretical framework that explains this failure by showing how ascent destabilizes optimization in transformer feedforward MLP layers. Guided by this insight, we propose *Bounded Parameter-Efficient Unlearning*, which stabilizes LoRA-based fine-tuning by applying bounded functions to MLP adapters. This controls the weight dynamics during ascent and enables reliable convergence. We validate the approach on Vision Transformer class deletion on CIFAR-100, where GD+Sine is the only evaluated method to achieve both high forget quality and model utility across ViT-B/16, ViT-L/14, and DeiT-S architectures, and demonstrate generality on language-model benchmarks (TOFU, TDEC, MUSE) across architectures from 22M to 8B parameters, achieving improved forgetting while preserving utility.
Authors: Ziyan Wang, Zheng Wang, Xingwei Qu, Qi Cheng, Jie Fu, Shengpu Tang, Minjia Zhang, Xiaoming Huo
Abstract: Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from low-quality rollouts lead to unstable updates and inefficient exploration. We introduce Slow-Fast Policy Optimization (SFPO), a simple yet efficient framework to address the above limitations via decomposing each step into three stages: a short fast trajectory of inner steps on the same batch, a reposition mechanism to control off-policy drift, and a final slow correction. This reposition-before-update design preserves the objective and rollout process unchanged, making SFPO plug-compatible with existing policy-gradient pipelines. Extensive experiments demonstrate that SFPO consistently improves stability, reduces number of rollouts, and accelerates convergence of reasoning RL training. Specifically, it outperforms GRPO by up to 2.80 points in average on math reasoning benchmarks. It also achieves up to 4.93\texttimes{} fewer rollouts and an up to 4.19\texttimes{} reduction in wall-clock time to match GRPO's best accuracy. Project website is available at https://slow-fast-po.github.io/.
Authors: Xuwang Yin, Claire Zhang, Julie Steele, Nir Shavit, Tony T. Wang
Abstract: Simultaneously achieving robust classification and high-fidelity generative modeling within a single framework presents a significant challenge. Hybrid approaches, such as Joint Energy-Based Models (JEM), interpret classifiers as EBMs but are often limited by the instability and poor sample quality inherent in training based on Stochastic Gradient Langevin Dynamics (SGLD). We address these limitations by proposing a novel training framework that integrates adversarial training (AT) principles for both discriminative robustness and stable generative learning. The proposed method introduces three key innovations: (1) the replacement of SGLD-based JEM learning with a stable, AT-based approach that optimizes the energy function through a Binary Cross-Entropy (BCE) loss that discriminates between real data and contrastive samples generated via Projected Gradient Descent (PGD); (2) adversarial training for the discriminative component that enhances classification robustness while implicitly providing the gradient regularization needed for stable EBM training; and (3) a two-stage training strategy that addresses normalization-related instabilities and enables leveraging pretrained robust classifiers, generalizing effectively across architectures. Experiments on CIFAR-10/100 and ImageNet demonstrate that our approach: (1) is the first EBM-based hybrid to scale to high-resolution datasets with high training stability, simultaneously achieving state-of-the-art discriminative and generative performance on ImageNet 256x256; (2) uniquely combines generative quality with adversarial robustness, enabling faithful counterfactual explanations; and (3) functions as a competitive standalone generative model, matching autoregressive models and surpassing diffusion models while offering additional versatility.
Authors: Reda Marzouk, Shahaf Bassan, Guy Katz
Abstract: Although Shapley additive explanations (SHAP) can be computed in polynomial time for simple models like decision trees, they unfortunately become NP-hard to compute for more expressive black-box models like neural networks - where generating explanations is often most critical. In this work, we analyze the problem of computing SHAP explanations for *Tensor Networks (TNs)*, a broader and more expressive class of models than those for which current exact SHAP algorithms are known to hold, and which is widely used for neural network abstraction and compression. First, we introduce a general framework for computing provably exact SHAP explanations for general TNs with arbitrary structures. Interestingly, we show that, when TNs are restricted to a *Tensor Train (TT)* structure, SHAP computation can be performed in *poly-logarithmic* time using *parallel* computation. Thanks to the expressiveness power of TTs, this complexity result can be generalized to many other popular ML models such as decision trees, tree ensembles, linear models, and linear RNNs, therefore tightening previously reported complexity results for these families of models. Finally, by leveraging reductions of binarized neural networks to Tensor Network representations, we demonstrate that SHAP computation can become *efficiently tractable* when the network's *width* is fixed, while it remains computationally hard even with constant *depth*. This highlights an important insight: for this class of models, width - rather than depth - emerges as the primary computational bottleneck in SHAP computation.
Authors: Hyunsik Yoo, Ting-Wei Li, SeongKu Kang, Zhining Liu, Charlie Xu, Qilin Qi, Hanghang Tong
Abstract: While large language models (LLMs) achieve strong performance in recommendation, they face challenges in continual learning as users, items, and user preferences evolve over time. Existing LoRA-based continual methods primarily focus on preserving performance on previous tasks, but this overlooks the unique nature of recommendation: the goal is not to predict past preferences, and outdated preferences can even harm performance when current interests shift significantly. To address this, we propose PESO (Proximally rEgularized Single evolving lOra, a continual adaptation method for LoRA in recommendation. PESO introduces a proximal regularizer that anchors the current adapter to its most recent frozen state, enabling the model to flexibly balance adaptation and preservation, and to better capture recent user behaviors. Theoretically, we show that this proximal design provides data-aware, direction-wise guidance in the LoRA subspace. Empirically, PESO consistently outperforms existing LoRA-based continual learning methods.
Authors: Kang Yang, Yuanlin Yang, Yuning Chen, Sikai Yang, Xinyu Zhang, Wan Du
Abstract: Precision agriculture demands continuous and accurate monitoring of soil moisture (M) and key macronutrients, including nitrogen (N), phosphorus (P), and potassium (K), to optimize yields and conserve resources. Wireless soil sensing has been explored to measure these four components; however, current solutions require recalibration (i.e., retraining the data processing model) to handle variations in soil texture, characterized by aluminosilicates (Al) and organic carbon (C), limiting their practicality. To address this, we introduce SoilX, a calibration-free soil sensing system that jointly measures six key components: {M, N, P, K, C, Al}. By explicitly modeling C and Al, SoilX eliminates texture- and carbon-dependent recalibration. SoilX incorporates Contrastive Cross-Component Learning (3CL), with two customized terms: the Orthogonality Regularizer and the Separation Loss, to effectively disentangle cross-component interference. Additionally, we design a novel tetrahedral antenna array with an antenna-switching mechanism, which can robustly measure soil dielectric permittivity independent of device placement. Extensive experiments demonstrate that SoilX reduces estimation errors by 23.8% to 31.5% over baselines and generalizes well to unseen fields.
Authors: Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma, Keyue Jiang, Kai Zhao, Wee Peng Tay
Abstract: Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective, which limits their ability to capture multi-scale structural patterns. We present an augmentation-free, multi-view GCL framework grounded in fractional-order continuous dynamics. By varying the fractional derivative order $\alpha \in (0,1]$, our encoders produce a continuous spectrum of views: small $\alpha$ yields localized features, while large $\alpha$ induces broader, global aggregation. We treat $\alpha$ as a learnable parameter so the model can adapt diffusion scales to the data and automatically discover informative views. This principled approach generates diverse, complementary representations without manual augmentations. Extensive experiments on standard benchmarks demonstrate that our method produces more robust and expressive embeddings and outperforms state-of-the-art GCL baselines.
Authors: Jorge Paz-Ruza, Jo\~ao Gama, Amparo Alonso-Betanzos, Bertha Guijarro-Berdi\~nas
Abstract: Sustainability and efficiency have become essential considerations in the development and deployment of Artificial Intelligence systems, but existing regulatory practices for Green AI still lack standardized, model-agnostic evaluation protocols. Recently, sustainability auditing pipelines for ML and usual practices by researchers show three main pitfalls: 1) they disproportionally emphasize epoch/batch learning settings, 2) they do not formally model the long-term sustainability cost of adapting and re-training models, and 3) they effectively measure the sustainability of sterile experiments, instead of estimating the environmental impact of real-world, long-term AI lifecycles. In this work, we propose a novel evaluation protocol for assessing the long-term sustainability of ML models, based on concepts inspired by Online ML, which measures sustainability and performance through incremental/continual model retraining parallel to real-world data acquisition. Through experimentation on diverse ML tasks using a range of model types, we demonstrate that traditional static train-test evaluations do not reliably capture sustainability under evolving datasets, as they overestimate, underestimate and/or erratically estimate the actual cost of maintaining and updating ML models. Our proposed sustainability evaluation pipeline also draws initial evidence that, in real-world, long-term ML life-cycles, higher environmental costs occasionally yield little to no performance benefits.
Authors: Nathan Breslow, Aayush Mishra, Mahler Revsine, Michael C. Schatz, Anqi Liu, Daniel Khashabi
Abstract: In-context learning (ICL) -- the capacity of a model to infer and apply abstract patterns from examples provided within its input -- has been extensively studied in large language models trained for next-token prediction on human text. In fact, prior work often attributes this emergent behavior to distinctive statistical properties in human language. This raises a fundamental question: can ICL arise organically in other sequence domains purely through large-scale predictive training? To explore this, we turn to genomic sequences, an alternative symbolic domain rich in statistical structure. Specifically, we study the Evo2 genomic model, trained predominantly on next-nucleotide (A/T/C/G) prediction, at a scale comparable to mid-sized LLMs. We develop a controlled experimental framework comprising symbolic reasoning tasks instantiated in both linguistic and genomic forms, enabling direct comparison of ICL across genomic and linguistic models. Our results show that genomic models, like their linguistic counterparts, exhibit log-linear gains in pattern induction as the number of in-context demonstrations increases. To the best of our knowledge, this is the first evidence of organically emergent ICL in genomic sequences, supporting the hypothesis that ICL arises as a consequence of large-scale predictive modeling over rich data. These findings extend emergent meta-learning beyond language, pointing toward a unified, modality-agnostic view of in-context learning.
Authors: Leo Elmecker-Plakolm, Pierre Fasterling, Philip Sosnin, Calvin Tsay, Matthew Wicker
Abstract: Safety-critical environments are inherently dynamic. Distribution shifts, emerging vulnerabilities, and evolving requirements demand continuous updates to machine learning models. Yet even benign parameter updates can have unintended consequences, such as catastrophic forgetting in classical models or alignment drift in foundation models. Existing heuristic approaches (e.g., regularization, parameter isolation) can mitigate these effects but cannot certify that updated models continue to satisfy required performance specifications. We address this problem by introducing a framework for provably safe model updates. Our approach first formalizes the problem as computing the largest locally invariant domain (LID): a connected region in parameter space where all points are certified to satisfy a given specification. While exact maximal LID computation is intractable, we show that relaxing the problem to parameterized abstract domains (orthotopes, zonotopes) yields a tractable primal-dual formulation. This enables efficient certification of updates - independent of the data or algorithm used - by projecting them onto the safe domain. Our formulation further allows computation of multiple approximately optimal LIDs, incorporation of regularization-inspired biases, and use of lookahead data buffers. Across continual learning and foundation model fine-tuning benchmarks, our method matches or exceeds heuristic baselines for avoiding forgetting while providing formal safety guarantees.
Authors: Zhongjian Qiao, Rui Yang, Jiafei Lyu, Chenjia Bai, Xiu Li, Siyang Gao, Shuang Qiu
Abstract: Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to the underlying dynamics misalignment between source and target domains, naively merging the two datasets may incur inferior performance. Recent advances address this issue by selectively leveraging source domain samples whose dynamics align well with the target domain. However, our work demonstrates that dynamics alignment alone is insufficient, by examining the limitations of prior frameworks and deriving a new target domain sub-optimality bound for the policy learned on the source domain. More importantly, our theory underscores an additional need for \textit{value alignment}, i.e., selecting high-quality, high-value samples from the source domain, a critical dimension overlooked by existing works. Motivated by such theoretical insight, we propose \textbf{\underline{D}}ynamics- and \textbf{\underline{V}}alue-aligned \textbf{\underline{D}}ata \textbf{\underline{F}}iltering (DVDF) method, a novel unified cross-domain RL framework that selectively incorporates source domain samples exhibiting strong alignment in \textit{both dynamics and values}. We empirically study a range of dynamics shift scenarios, including kinematic and morphology shifts, and evaluate DVDF on various tasks and datasets, even in the challenging setting where the target domain dataset contains an extremely limited amount of data. Extensive experiments demonstrate that DVDF consistently outperforms strong baselines with significant improvements.
Authors: Vedant Shah, Johan Obando-Ceron, Vineet Jain, Brian Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Nikolay Malkin, Moksh Jain, Siddarth Venkatraman, Aaron Courville
Abstract: The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL objective for LLM training involves a regularization term, which is the reverse Kullback-Leibler (KL) divergence between the trained policy and the reference policy. Since computing the KL divergence exactly is intractable, various estimators are used in practice to estimate it from on-policy samples. Despite its wide adoption, including in several open-source libraries, there is no systematic study analyzing the numerous ways of incorporating KL estimators in the objective and their effect on the downstream performance of RL-trained models. Recent works show that prevailing practices for incorporating KL regularization do not provide correct gradients for stated objectives, creating a discrepancy between the objective and its implementation. In this paper, we further analyze these practices and study the gradients of several estimators configurations, revealing how design choices shape gradient bias. We substantiate these findings with empirical observations by RL fine-tuning \texttt{Qwen2.5-7B}, \texttt{Llama-3.1-8B-Instruct} and \texttt{Qwen3-4B-Instruct-2507} with different configurations and evaluating their performance on both in- and out-of-distribution tasks. Through our analysis, we observe that, in on-policy settings: (1) estimator configurations with biased gradients can result in training instabilities; and (2) using estimator configurations resulting in unbiased gradients leads to better performance on in-domain as well as out-of-domain tasks. We also investigate the performance resulting from different KL configurations in off-policy settings and observe that KL regularization can help stabilize off-policy RL training resulting from asynchronous setups.
Authors: Zhehao Huang, Baijiong Lin, Jingyuan Zhang, Jingying Wang, Yuhang Liu, Ning Lu, Tao Li, Xiaolin Huang
Abstract: Multi-model routing has evolved from an engineering technique into essential infrastructure, yet existing work lacks a systematic, reproducible benchmark for evaluating vision-language models (VLMs). We present VL-RouterBench to assess the overall capability of VLM routing systems systematically. The benchmark is grounded in raw inference and scoring logs from VLMs and constructs quality and cost matrices over sample-model pairs. In scale, VL-RouterBench covers 14 datasets across 3 task groups, totaling 30,540 samples, and includes 15 open-source models and 2 API models, yielding 519,180 sample-model pairs and a total input-output token volume of 34,494,977. The evaluation protocol jointly measures average accuracy, average cost, and throughput, and builds a ranking score from the harmonic mean of normalized cost and accuracy to enable comparison across router configurations and cost budgets. On this benchmark, we evaluate 10 routing methods and baselines and observe a significant routability gain, while the best current routers still show a clear gap to the ideal Oracle, indicating considerable room for improvement in router architecture through finer visual cues and modeling of textual structure. We will open-source the complete data construction and evaluation toolchain to promote comparability, reproducibility, and practical deployment in multimodal routing research.
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, margin dependent 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 the majority of settings. We also find language models' 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: Zhengyang Zhao, Lu Ma, Yizhen Jiang, Xiaochen Ma, Zimo Meng, Chengyu Shen, Lexiang Tang, Haoze Sun, Peng Pei, Wentao Zhang
Abstract: The prevailing post-training paradigm for Large Reasoning Models (LRMs) - Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) - suffers from an intrinsic optimization mismatch: the rigid supervision inherent in SFT induces distributional collapse, thereby exhausting the exploration space necessary for subsequent RL. In this paper, we reformulate SFT to reconcile post-training objectives and propose Gibbs Initialization with Finite Temperature (GIFT). We characterize standard SFT as a degenerate zero-temperature limit that suppresses base priors. Conversely, GIFT incorporates supervision as a finite-temperature energy potential, establishing a distributional bridge that promotes objective consistency throughout the post-training pipeline. Our experiments demonstrate that GIFT significantly outperforms standard SFT and other competitive baselines when utilized for RL initialization, providing a mathematically principled pathway to preserve exploration and align the two post-training stages. Our code is available at https://github.com/zzy1127/GIFT.
Authors: Ming Li
Abstract: Gradient-based methods are widely used to solve various optimization problems, however, they are either constrained by local optima dilemmas, simple convex constraints, and continuous differentiability requirements, or limited to low-dimensional simple problems. This work solve these limitations and restrictions by unifying all optimization problems with various complex constraints as a general hierarchical optimization objective without constraints, which is optimized by gradient obtained through score matching. The proposed method is verified through simple-constructed and complex-practical experiments. Even more importantly, it reveals the profound connection between global optimization and diffusion based generative modeling.
Authors: Wei Chen, Xingyu Guo, Shuang Li, Zhao Zhang, Yan Zhong, Fuzhen Zhuang, Deqing wang
Abstract: Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs but is challenged by complex, multi-faceted distributional shifts. Existing methods attempt to reduce distributional shifts by aligning manually selected graph elements (e.g., node attributes or structural statistics), which typically require manually designed graph filters to extract relevant features before alignment. However, such approaches are inflexible: they rely on scenario-specific heuristics, and struggle when dominant discrepancies vary across transfer scenarios. To address these limitations, we propose \textbf{ADAlign}, an Adaptive Distribution Alignment framework for GDA. Unlike heuristic methods, ADAlign requires no manual specification of alignment criteria. It automatically identifies the most relevant discrepancies in each transfer and aligns them jointly, capturing the interplay between attributes, structures, and their dependencies. This makes ADAlign flexible, scenario-aware, and robust to diverse and dynamically evolving shifts. To enable this adaptivity, we introduce the Neural Spectral Discrepancy (NSD), a theoretically principled parametric distance that provides a unified view of cross-graph shifts. NSD leverages neural characteristic function in the spectral domain to encode feature-structure dependencies of all orders, while a learnable frequency sampler adaptively emphasizes the most informative spectral components for each task via minimax paradigm. Extensive experiments on 10 datasets and 16 transfer tasks show that ADAlign not only outperforms state-of-the-art baselines but also achieves efficiency gains with lower memory usage and faster training.
Authors: Jialin Yu, Mo\"ise Blanchard
Abstract: We study a sequential prediction problem in which an adversary is allowed to inject arbitrarily many adversarial instances in a stream of i.i.d. instances, but at each round, the learner may also abstain from making a prediction without incurring any penalty if the instance was indeed corrupted. This semi-adversarial setting naturally sits between the classical stochastic case with i.i.d. instances for which function classes with finite VC dimension are learnable; and the adversarial case with arbitrary instances, known to be significantly more restrictive. For this problem, Goel et al. (2023) showed that, if the learner knows the distribution $\mu$ of clean samples in advance, learning can be achieved for all VC classes without restrictions on adversary corruptions. This is, however, a strong assumption in both theory and practice: a natural question is whether similar learning guarantees can be achieved without prior distributional knowledge, as is standard in classical learning frameworks (e.g., PAC learning or asymptotic consistency) and other non-i.i.d. models (e.g., smoothed online learning). We therefore focus on the distribution-free setting where $\mu$ is unknown and propose an algorithm AbstainBoost based on a boosting procedure of weak learners, which guarantees sublinear error for general VC classes in distribution-free abstention learning for oblivious adversaries. These algorithms also enjoy similar guarantees for adaptive adversaries, for structured function classes including linear classifiers. These results are complemented with corresponding lower bounds, which reveal an interesting polynomial trade-off between misclassification error and number of erroneous abstentions.
Authors: Danning Jing, Xinhai Chen, Xifeng Pu, Jie Hu, Chao Huang, Xuguang Chen, Qinglin Wang, Jie Liu
Abstract: Accurately modeling the spatio-temporal dynamics of blast wave propagation remains a longstanding challenge due to its highly nonlinear behavior, sharp gradients, and burdensome computational cost. While machine learning-based surrogate models offer fast inference as a promising alternative, they suffer from degraded accuracy, particularly evaluated on complex urban layouts or out-of-distribution scenarios. Moreover, autoregressive prediction strategies in such models are prone to error accumulation over long forecasting horizons, limiting their robustness for extended-time simulations. To address these limitations, we propose RGD-Blast, a robust and generalizable deep surrogate model for high-fidelity, long-term blast wave forecasting. RGD-Blast incorporates a multi-scale module to capture both global flow patterns and local boundary interactions, effectively mitigating error accumulation during autoregressive prediction. We introduce a dynamic-static feature coupling mechanism that fuses time-varying pressure fields with static source and layout features, thereby enhancing out-of-distribution generalization. Experiments demonstrate that RGD-Blast achieves a two-order-of-magnitude speedup over traditional numerical methods while maintaining comparable accuracy. In generalization tests on unseen building layouts, the model achieves an average RMSE below 0.01 and an R2 exceeding 0.89 over 280 consecutive time steps. Additional evaluations under varying blast source locations and explosive charge weights further validate its generalization, substantially advancing the state of the art in long-term blast wave modeling.
Authors: Nazal Mohamed, Ayush Mohanty, Nagi Gebraeel
Abstract: Networks of interdependent industrial assets (clients) are tightly coupled through physical processes and control inputs, raising a key question: how would the output of one client change if another client were operated differently? This is difficult to answer because client-specific data are high-dimensional and private, making centralization of raw data infeasible. Each client also maintains proprietary local models that cannot be modified. We propose a federated framework for causal representation learning in state-space systems that captures interdependencies among clients under these constraints. Each client maps high-dimensional observations into low-dimensional latent states that disentangle intrinsic dynamics from control-driven influences. A central server estimates the global state-transition and control structure. This enables decentralized counterfactual reasoning where clients predict how outputs would change under alternative control inputs at others while only exchanging compact latent states. We prove convergence to a centralized oracle and provide privacy guarantees. Our experiments demonstrate scalability, and accurate cross-client counterfactual inference on synthetic and real-world industrial control system datasets.
Authors: Yuandong Zhang, Othmane Echchabi, Tianshu Feng, Wenyi Zhang, Hsuai-Kai Liao, Charles Chang
Abstract: Transportation mode detection is an important topic within GeoAI and transportation research. In this study, we introduce SpeedTransformer, a novel Transformer-based model that relies solely on speed inputs to infer transportation modes from dense smartphone GPS trajectories. In benchmark experiments, SpeedTransformer outperformed traditional deep learning models, such as the Long Short-Term Memory (LSTM) network. Moreover, the model demonstrated strong flexibility in transfer learning, achieving high accuracy across geographical regions after fine-tuning with small datasets. Finally, we deployed the model in a real-world experiment, where it consistently outperformed baseline models under complex built environments and high data uncertainty. These findings suggest that Transformer architectures, when combined with dense GPS trajectories, hold substantial potential for advancing transportation mode detection and broader mobility-related research.
Authors: Harry Amad, Mihaela van der Schaar
Abstract: Neural networks (NNs) often have critical behavioural trade-offs that are set at design time with hyperparameters-such as reward weights in reinforcement learning or quantile targets in regression. Post-deployment, however, user preferences can evolve, making initial settings undesirable, necessitating potentially expensive retraining. To circumvent this, we introduce the task of Hyperparameter Trajectory Inference (HTI): to learn, from observed data, how a NN's conditional output distribution changes with its hyperparameters, and construct a surrogate model that approximates the NN at unobserved hyperparameter settings. HTI requires extending existing trajectory inference approaches to incorporate conditions, exacerbating the challenge of ensuring inferred paths are feasible. We propose an approach based on conditional Lagrangian optimal transport, jointly learning the Lagrangian function governing hyperparameter-induced dynamics along with the associated optimal transport maps and geodesics between observed marginals, which form the surrogate model. We incorporate inductive biases based on the manifold hypothesis and least-action principles into the learned Lagrangian, improving surrogate model feasibility. We empirically demonstrate that our approach reconstructs NN outputs across various hyperparameter spectra better than other alternatives.
Authors: Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, Yuke Zhu
Abstract: Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively small behavior cloning (BC) policy models trained from scratch, its behavior in modern large-scale pretrained Vision-Language-Action (VLA) models remains underexplored. In this work, we found that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch. Simple Experience Replay (ER) works surprisingly well on VLAs, sometimes achieving zero forgetting even with a small replay data size. Our analysis reveals that pretraining plays a critical role in downstream continual learning performance: large pretrained models mitigate forgetting with a small replay buffer size while maintaining strong forward learning capabilities. Furthermore, we found that VLAs can retain relevant knowledge from prior tasks despite performance degradation during learning new tasks. This knowledge retention enables rapid recovery of seemingly forgotten skills through finetuning. Together, these insights imply that large-scale pretraining fundamentally changes the dynamics of continual learning, enabling models to continually acquire new skills over time with simple replay. Code and more information can be found at https://continual-vlas.github.io/forget-me-not/
Authors: Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang
Abstract: Standard transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations (value transfer). We show that selection requires only $O(\log N)$ dimensions to distinguish among $N$ relevant token categories (e.g., syntactic roles, semantic clusters, positional patterns) -- far fewer than value transfer needs. We introduce factored keys, which exploit this asymmetry to physically shrink the KV cache of any pretrained model without retraining from scratch -- unlike GQA and MLA, which must be designed into the architecture before pretraining. We factorize each key projection $W_K \approx A_{d \times r} B_{r \times d}$ via truncated SVD (where $r = d_{\text{select}}$), set $W_K' = A$ as the new key projection producing compact $r$-dimensional keys for the cache, and absorb $B^\top$ into the query projection ($W_Q' = W_Q B^\top$) at zero cost -- since queries are never cached. At 7B scale, training from scratch with $r = d_{\text{model}}/4$ matches full-attention perplexity (9.2 vs 9.3 PPL after 20B tokens) while using 12% fewer parameters and training 8% faster. For existing models, SVD + QK fine-tuning (3 epochs, less than 1% of pretraining data) achieves 75% key cache savings at approximately 2% quality cost on both GPT-2 and Mistral-7B. The approach composes with GQA and quantization for up to $16\times$ combined key cache compression. For a 7B model serving 128K context, factored keys save 25 GB of KV cache per user, enabling approximately 60% more concurrent users on identical hardware.
Authors: Fengxiang Nie, Yasuhiro Suzuki
Abstract: Data-driven surrogate models can significantly accelerate the simulation of continuous dynamical systems, yet the step-wise accumulation of errors during autoregressive time-stepping often leads to spectral blow-up and unphysical divergence. Existing global regularization techniques can enforce contractive dynamics but uniformly damp high-frequency features, causing over-smoothing; meanwhile, long-horizon trajectory optimization methods are severely constrained by memory bottlenecks. This paper proposes Jacobian-Adaptive Weighting for Stability (JAWS), which reformulates operator learning as a Maximum A Posteriori (MAP) estimation problem with spatially heteroscedastic uncertainty, enabling the regularization strength to adapt automatically based on local physical complexity: enforcing contraction in smooth regions to suppress noise while relaxing constraints near singular features such as shocks to preserve gradient information. Experiments demonstrate that JAWS serves as an effective spectral pre-conditioner for trajectory optimization, allowing short-horizon, memory-efficient training to match the accuracy of long-horizon baselines. Validations on the 1D viscous Burgers' equation and 2D flow past a cylinder (Re=400 out-of-distribution generalization) confirm the method's advantages in long-term stability, preservation of physical conservation properties, and computational efficiency. This significant reduction in memory usage makes the method particularly well-suited for stable and efficient long-term simulation of large-scale flow fields in practical engineering applications. Our source code and implementation are publicly available at https://github.com/jyohosyo-dot/JAWS_2D.
Authors: Jialei Tan, Zheng Lin, Xiangming Cai, Ruoxi Zhu, Zihan Fang, Pingping Chen, Wei Ni
Abstract: Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs significant communication overhead, particularly when a large number of client devices are involved. To address this challenge, we propose an adaptive channel pruning-aided SL (ACP-SL) scheme. In ACP-SL, a label-aware channel importance scoring (LCIS) module is designed to generate channel importance scores, distinguishing important channels from less important ones. Based on these scores, an adaptive channel pruning (ACP) module is developed to prune less important channels, thereby compressing the corresponding smashed data and reducing the communication overhead. Experimental results show that ACP-SL consistently outperforms benchmark schemes in test accuracy. Furthermore, it reaches a target test accuracy in fewer training rounds, thereby reducing communication overhead.
Authors: Teng Xiao, Yige Yuan, Hamish Ivison, Huaisheng Zhu, Faeze Brahman, Nathan Lambert, Pradeep Dasigi, Noah A. Smith, Hannaneh Hajishirzi
Abstract: This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single independent episode with sparse rewards, MR-Search trains a policy that conditions on past episodes and adapts its search strategy across episodes. MR-Search learns to learn a search strategy with self-reflection, allowing search agents to improve in-context exploration at test-time. Specifically, MR-Search performs cross-episode exploration by generating explicit self-reflections after each episode and leveraging them as additional context to guide subsequent attempts, thereby promoting more effective exploration during test-time. We further introduce a multi-turn RL algorithm that estimates a dense relative advantage at the turn level, enabling fine-grained credit assignment on each episode. Empirical results across various benchmarks demonstrate the advantages of MR-Search over baselines based RL, showing strong generalization and relative improvements of 9.2% to 19.3% across eight benchmarks. Our code and data are available at https://github.com/tengxiao1/MR-Search.
Authors: Barth\'el\'emy Dang-Nhu, Louis Annabi, Sylvain Argentieri
Abstract: Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentanglement have required strong prior knowledge of the symmetry group's structure, or restrictive assumptions about the subgroup properties. In this work, we remove these constraints by proposing a method whereby an embodied agent autonomously discovers the group structure of its action space through unsupervised interaction with the environment. We prove the identifiability of the true symmetry group decomposition under minimal assumptions, and derive two algorithms: one for discovering the group decomposition from interaction data, and another for learning Linear Symmetry-Based Disentangled (LSBD) representations without assuming specific subgroup properties. Our method is validated on three environments exhibiting different group decompositions, where it outperforms existing LSBD approaches.
Authors: Alma Lago
Abstract: Mechanistic interpretability has transformed the analysis of transformer circuits by decomposing model behavior into competing algorithms, identifying phase transitions during training, and deriving closed-form predictions for when and why strategies shift. However, this program has remained largely confined to sequence-prediction architectures, leaving embodied control systems without comparable mechanistic accounts. Here we extend this framework to sensorimotor-cognitive development, using infant motor learning as a model system. We show that foundational inductive biases give rise to causal control circuits, with learned gating mechanisms converging toward theoretically motivated uncertainty thresholds. The resulting dynamics reveal a clean phase transition in the arbitration gate whose commitment behavior is well described by a closed-form exponential moving-average surrogate. We identify context window k as the critical parameter governing circuit formation: below a minimum threshold (k$\leq$4) the arbitration mechanism cannot form; above it (k$\geq$8), gate confidence scales asymptotically as log k. A two-dimensional phase diagram further reveals task-demand-dependent route arbitration consistent with the prediction that prospective execution becomes advantageous only when prediction error remains within the task tolerance window. Together, these results provide a mechanistic account of how reactive and prospective control strategies emerge and compete during learning. More broadly, this work sharpens mechanistic accounts of cognitive development and provides principled guidance for the design of interpretable embodied agents.
Authors: Jingpu Cheng, Qianxiao Li, Ting Lin, Zuowei Shen
Abstract: We investigate the dependence of the approximation capacity of deep residual networks on its depth in a continuous dynamical systems setting. This can be formulated as the general problem of quantifying the minimal time-horizon required to approximate a diffeomorphism by flows driven by a given family $\mathcal F$ of vector fields. We show that this minimal time can be identified as a geodesic distance on a sub-Finsler manifold of diffeomorphisms, where the local geometry is characterised by a variational principle involving $\mathcal F$. This connects the learning efficiency of target relationships to their compatibility with the learning architectural choice. Further, the results suggest that the key approximation mechanism in deep learning, namely the approximation of functions by composition or dynamics, differs in a fundamental way from linear approximation theory, where linear spaces and norm-based rate estimates are replaced by manifolds and geodesic distances.
Authors: Hao Wu, Yongheng Zhang, Yuan Gao, Fan Xu, Fan Zhang, Ruobing Xie, Ruijian Gou, Yuxuan Liang, Xiaomeng Huang, Xian Wu
Abstract: Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous spatiotemporal dynamics governed by Partial Differential Equations (PDEs), often resulting in non-physical hallucinations. Existing approaches typically resort to costly, domain-specific fine-tuning, which severely limits cross-domain generalization and interpretability. To bridge this gap, we propose OMNIFLOW, a neuro-symbolic architecture designed to ground frozen multimodal LLMs in fundamental physical laws without requiring domain-specific parameter updates. OMNIFLOW introduces a novel \textit{Semantic-Symbolic Alignment} mechanism that projects high-dimensional flow tensors into topological linguistic descriptors, enabling the model to perceive physical structures rather than raw pixel values. Furthermore, we construct a Physics-Guided Chain-of-Thought (PG-CoT) workflow that orchestrates reasoning through dynamic constraint injection (e.g., mass conservation) and iterative reflexive verification. We evaluate OMNIFLOW on a comprehensive benchmark spanning microscopic turbulence, theoretical Navier-Stokes equations, and macroscopic global weather forecasting. Empirical results demonstrate that OMNIFLOW significantly outperforms traditional deep learning baselines in zero-shot generalization and few-shot adaptation tasks. Crucially, it offers transparent, physically consistent reasoning reports, marking a paradigm shift from black-box fitting to interpretable scientific reasoning.
Authors: Dibakar Sigdel, Namuna Panday
Abstract: We present PhasorFlow, an open-source Python library introducing a computational paradigm operating on the $S^1$ unit circle. Inputs are encoded as complex phasors $z = e^{i\theta}$ on the $N$-Torus ($\mathbb{T}^N$). As computation proceeds via unitary wave interference gates, global norm is preserved while individual components drift into $\mathbb{C}^N$, allowing algorithms to natively leverage continuous geometric gradients for predictive learning. PhasorFlow provides three core contributions. First, we formalize the Phasor Circuit model ($N$ unit circle threads, $M$ gates) and introduce a 22-gate library covering Standard Unitary, Non-Linear, Neuromorphic, and Encoding operations with full matrix algebra simulation. Second, we present the Variational Phasor Circuit (VPC), analogous to Variational Quantum Circuits (VQC), enabling optimization of continuous phase parameters for classical machine learning tasks. Third, we introduce the Phasor Transformer, replacing expensive $QK^TV$ attention with a parameter-free, DFT-based token mixing layer inspired by FNet. We validate PhasorFlow on non-linear spatial classification, time-series prediction, financial volatility detection, and neuromorphic tasks including neural binding and oscillatory associative memory. Our results establish unit circle computing as a deterministic, lightweight, and mathematically principled alternative to classical neural networks and quantum circuits. It operates on classical hardware while sharing quantum mechanics' unitary foundations. PhasorFlow is available at https://github.com/mindverse-computing/phasorflow.
Authors: Joe Standridge, Daniel Livescu, Paul Cizmas
Abstract: Stiff dynamical systems present a challenge for machine-learning reduced-order models (ML-ROMs), as explicit time integration becomes unstable in stiff regimes while implicit integration within learning loops is computationally expensive and often degrades training efficiency. Time reparameterization (TR) offers an alternative by transforming the independent variable so that rapid physical-time transients are spread over a stretched-time coordinate, enabling stable explicit integration on uniformly sampled grids. Although several TR strategies have been proposed, their effect on learnability in ML-ROMs remains incompletely understood. This work investigates time reparameterization as a stiffness-mitigation mechanism for neural ODE reduced-order modeling and introduces a trajectory-optimized TR (TOTR) formulation. The proposed approach casts time reparameterization as an optimization problem in arc-length coordinates, in which a traversal-speed profile is selected to penalize acceleration in stretched time. By targeting the smoothness of the training dynamics, this formulation produces reparameterized trajectories that are better conditioned and easier to learn than existing TR methods. TOTR is evaluated on three stiff problems: a parameterized stiff linear system, the van der Pol oscillator, and the HIRES chemical kinetics model. Across all cases, the proposed approach yields smoother reparameterizations and improved physical-time predictions under identical training regimens than other TR approaches. Quantitative results demonstrate loss reductions of one to two orders of magnitude compared to benchmark algorithms. These results highlight that effective stiffness mitigation in ML-ROMs depends critically on the regularity and learnability of the time map itself, and that optimization-based TR provides a robust framework for explicit reduced-order modeling of multiscale dynamical systems.
Authors: Jackson Trager, Alireza S. Ziabari, Elnaz Rahmati, Aida Mostafazadeh Davani, Preni Golazizian, Farzan Karimi-Malekabadi, Ali Omrani, Zhihe Li, Brendan Kennedy, Georgios Chochlakis, Nils Karl Reimer, Melissa Reyes, Kelsey Cheng, Mellow Wei, Christina Merrifield, Arta Khosravi, Evans Alvarez, Morteza Dehghani
Abstract: Moral framing and sentiment can affect a variety of online and offline behaviors, including donation, environmental action, political engagement, and protest. Various computational methods in Natural Language Processing (NLP) have been used to detect moral sentiment from textual data, but achieving strong performance in such subjective tasks requires large, hand-annotated datasets. Previous corpora annotated for moral sentiment have proven valuable, and have generated new insights both within NLP and across the social sciences, but have been limited to Twitter. To facilitate improving our understanding of the role of moral rhetoric, we present the Moral Foundations Reddit Corpus, a collection of 16,123 English Reddit comments that have been curated from 12 distinct subreddits, hand-annotated by at least three trained annotators for 8 categories of moral sentiment (i.e., Care, Proportionality, Equality, Purity, Authority, Loyalty, Thin Morality, Implicit/Explicit Morality) based on the updated Moral Foundations Theory (MFT) framework. We evaluate baselines using large language models (Llama3-8B, Ministral-8B) in zero-shot, few-shot, and PEFT (Parameter-Efficient Fine-Tuning) settings, comparing their performance to fine-tuned encoder-only models like BERT (Bidirectional Encoder Representations from Transformers). The results show that LLMs continue to lag behind fine-tuned encoders on this subjective task, underscoring the ongoing need for human-annotated moral corpora for AI alignment evaluation. Keywords: moral sentiment annotation, moral values, moral foundations theory, multi-label text classification, large language models, benchmark dataset, evaluation and alignment resource
Authors: Zhikai Li, Xiaoxuan Liu, Banghua Zhu, Zhen Dong, Qingyi Gu, Kurt Keutzer
Abstract: Large Language Models (LLMs) have showcased remarkable impacts across a wide spectrum of natural language processing tasks. Fine-tuning these pretrained models on downstream datasets provides further significant performance gains; however, this process typically requires a large number of expensive, high-end GPUs. Although there have been efforts focused on parameter-efficient fine-tuning, they cannot fully unlock the powerful potential of full-parameter fine-tuning. In this paper, we propose QFT, a Quantized Full-parameter Tuning framework for LLMs that quantizes and stores all training states, including weights, gradients, and optimizer states, in INT8 format to reduce training memory, thereby enabling full-parameter fine-tuning on existing GPUs at an affordable cost. To ensure training performance, we make two key efforts: i) for quantized gradients and optimizer states, we theoretically prove that the Lion optimizer, with its property of consistent update magnitudes, is highly robust to quantization; ii) and for quantized weights, we employ the hybrid feature quantizer, which identifies and protects a small subset of sparse critical features while quantizing the remaining dense features, thus ensuring accurate weight updates without FP32 backups. Moreover, to support backpropagation in the integer context, we develop a stack-based gradient flow scheme with O(1) complexity, forming a unified integer training pipeline. As a result, QFT reduces the model state memory to 21% of the standard solution while achieving comparable performance, e.g., tuning a LLaMA-7B model requires only <30GB of memory, making it feasible on a single A6000 GPU.
Authors: Akash Kundu, Leopoldo Sarra
Abstract: Quantum computing offers exciting opportunities for simulating complex quantum systems and optimizing large scale combinatorial problems, but its practical use is limited by device noise and constrained connectivity. Designing quantum circuits, which are fundamental to quantum algorithms, is therefore a central challenge in current quantum hardware. Existing reinforcement learning based methods for circuit design lose accuracy when restricted to hardware native gates and device level compilation. Here, we introduce gadget reinforcement learning (GRL), which combines learning with program synthesis to automatically construct composite gates that expand the action space while respecting hardware constraints. We show that this approach improves accuracy, hardware compatibility, and scalability for transverse-field Ising and quantum chemistry problems, reaching systems of up to ten qubits within realistic computational budgets. This framework demonstrates how learned, reusable circuit building blocks can guide the co-design of algorithms and hardware for quantum processors.
Authors: Giacomo Belli, Marco Mordacci, Michele Amoretti
Abstract: In this work, a novel quantum neural network is introduced as a means to approximate any unitary evolution through the Standard Recursive Block Basis (SRBB) and is subsequently redesigned with the number of CNOTs asymptotically reduced by an exponential contribution. This algebraic approach to the problem of unitary synthesis exploits Lie algebras and their topological features to obtain scalable parameterizations of unitary operators. First, the original SRBB-based scalability scheme, already known in the literature only from a theoretical point of view, is reformulated for efficient algorithm implementation and complexity management. Remarkably, 2-qubit operators emerge as a special case of the original scaling scheme. Furthermore, an algorithm is proposed to reduce the number of CNOT gates in the scalable variational quantum circuit, thus deriving a new implementable scaling scheme that requires only one layer of approximation. The single layer CNOT-reduced quantum neural network is implemented, and its performance is assessed with a variety of different unitary matrices, both sparse and dense, up to 6 qubits via the PennyLane library. The effectiveness of the approximation is measured with different metrics in relation to two optimizers: a gradient-based method and the Nelder-Mead method. The approximate CNOT-reduced SRBB-based synthesis algorithm is also tested on real hardware and compared with other valid approximation and decomposition methods available in the literature.
Authors: Quyu Kong, Yixuan Zhang, Yang Liu, Panrong Tong, Enqi Liu, Feng Zhou
Abstract: Temporal Point Processes (TPPs) have been widely used for modeling event sequences on the Web, such as user reviews, social media posts, and online transactions. However, traditional TPP models often struggle to effectively incorporate the rich textual descriptions that accompany these events, while Large Language Models (LLMs), despite their remarkable text processing capabilities, lack mechanisms for handling the temporal dynamics inherent in Web-based event sequences. To bridge this gap, we introduce Language-TPP, a unified framework that seamlessly integrates TPPs with LLMs for enhanced Web event sequence modeling. Our key innovation is a novel temporal encoding mechanism that converts continuous time intervals into specialized byte-tokens, enabling direct integration with standard language model architectures for TPP modeling without requiring TPP-specific modifications. This approach allows Language-TPP to achieve state-of-the-art performance across multiple TPP benchmarks, including event time prediction and type prediction, on real-world Web datasets spanning e-commerce reviews, social media and online Q&A platforms. More importantly, we demonstrate that our unified framework unlocks new capabilities for TPP research: incorporating temporal information improves the quality of generated event descriptions, as evidenced by enhanced ROUGE-L scores, and better aligned sentiment distributions. Through comprehensive experiments, including qualitative analysis of learned distributions and scalability evaluations on long sequences, we show that Language-TPP effectively captures both temporal dynamics and textual patterns in Web user behavior, with important implications for content generation, user behavior understanding, and Web platform applications. Code is available at https://github.com/qykong/Language-TPP.
Authors: Neeraj Gangwar, Suma P Bhat, Nickvash Kani
Abstract: While large models pre-trained on high-quality data exhibit excellent performance on mathematical reasoning (e.g., GSM8k, MultiArith), it remains challenging to specialize smaller models for these tasks. Common approaches to address this challenge include knowledge distillation from large teacher models and data augmentation (e.g., rephrasing questions and generating synthetic solutions). Despite these efforts, smaller models struggle with arithmetic computations, leading to errors in mathematical reasoning. In this work, we leverage a synthetic arithmetic dataset generated programmatically to enhance the reasoning capabilities of smaller models. We investigate two key approaches to incorporate this dataset: (1) intermediate fine-tuning, in which a model is fine-tuned on the arithmetic dataset before training it on a reasoning dataset, and (2) integrating the arithmetic dataset into an instruction-tuning mixture, allowing the model to learn arithmetic skills alongside general instruction-following abilities. Our experiments on multiple reasoning benchmarks demonstrate that incorporating an arithmetic dataset, whether through targeted fine-tuning or within an instruction-tuning mixture, enhances models' arithmetic capabilities, thereby improving their mathematical reasoning performance.
Authors: Sofia Faltenbacher, Jonas Wahl, Rebecca Herman, Jakob Runge
Abstract: Causal discovery methods based on the PC algorithm are proven to be sound if all structural assumptions are fulfilled and all conditional independence tests are correct. This idealized setting is rarely given in real data. In this work, we first analyze how local errors can propagate throughout the output graph of a PC-based method, highlighting how consequential seemingly innocuous errors can become. Next, we introduce coherency scores to find assumption violations and small sample errors in the absence of a ground truth. These scores do not require statistical tests beyond those already executed by the causal discovery algorithm. Errors detected by our approach extend the set of errors that can be detected by comparable existing methods. We place our computationally cheap global error detection and quantification scores as a bridge between computationally expensive global answer-set-programming-based methods and less expensive local error detection methods. The scores are analyzed on simulated and real-world datasets.
Authors: Sacha Braun, Liviu Aolaritei, Michael I. Jordan, Francis Bach
Abstract: Conformal prediction provides a principled framework for constructing predictive sets with finite-sample validity. While much of the focus has been on univariate response variables, existing multivariate methods either impose rigid geometric assumptions or rely on flexible but computationally expensive approaches that do not explicitly optimize prediction set volume. We propose an optimization-driven framework based on a novel loss function that directly learns minimum-volume covering sets while ensuring valid coverage. This formulation naturally induces a new nonconformity score for conformal prediction, which adapts to the residual distribution and covariates. Our approach optimizes over prediction sets defined by arbitrary norm balls, including single and multi-norm formulations. Additionally, by jointly optimizing both the predictive model and predictive uncertainty, we obtain prediction sets that are tight, informative, and computationally efficient, as demonstrated in our experiments on real-world datasets.
Authors: Jing Liu, Yao Du, Kun Yang, Jiaqi Wu, Yan Wang, Xiping Hu, Zehua Wang, Yang Liu, Peng Sun, Azzedine Boukerche, Victor C. M. Leung
Abstract: Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications, integrating cloud resources with edge devices to enable efficient, low-latency processing. Recent advancements in AI, particularly deep learning and large language models (LLMs), have dramatically enhanced the capabilities of these distributed systems, yet introduce significant challenges in model deployment and resource management. In this survey, we comprehensive examine the intersection of distributed intelligence and model optimization within edge-cloud environments, providing a structured tutorial on fundamental architectures, enabling technologies, and emerging applications. Additionally, we systematically analyze model optimization approaches, including compression, adaptation, and neural architecture search, alongside AI-driven resource management strategies that balance performance, energy efficiency, and latency requirements. We further explore critical aspects of privacy protection and security enhancement within ECCC systems and examines practical deployments through diverse applications, spanning autonomous driving, healthcare, and industrial automation. Performance analysis and benchmarking techniques are also thoroughly explored to establish evaluation standards for these complex systems. Furthermore, the review identifies critical research directions including LLMs deployment, 6G integration, neuromorphic computing, and quantum computing, offering a roadmap for addressing persistent challenges in heterogeneity management, real-time processing, and scalability. By bridging theoretical advancements and practical deployments, this survey offers researchers and practitioners a holistic perspective on leveraging AI to optimize distributed computing environments, fostering innovation in next-generation intelligent systems.
Authors: Hung Pham, Aiden Ren, Ibrahim Tahir, Jiatai Tong, Thiago Serra
Abstract: In constraint learning, we use a neural network as a surrogate for part of the constraints or of the objective function of an optimization model. However, the tractability of the resulting model is heavily influenced by the size of the neural network used as a surrogate. One way to obtain a more tractable surrogate is by pruning the neural network first. In this work, we consider how to approach the setting in which the neural network is actually a given: how can we solve an optimization model embedding a large and predetermined neural network? We propose surrogating the neural network itself by pruning it, which leads to a sparse and more tractable optimization model, for which we hope to still obtain good solutions with respect to the original neural network. For network verification and function maximization models, that indeed leads to better solutions within a time limit, especially -- and surprisingly -- if we skip the standard retraining step known as finetuning. Hence, a pruned network with worse inference for lack of finetuning can be a better surrogate.
Authors: Rebecca Pelke, Jos\'e Cubero-Cascante, Nils Bosbach, Niklas Degener, Florian Idrizi, Lennart M. Reimann, Jan Moritz Joseph, Rainer Leupers
Abstract: Using Resistive Random Access Memory (RRAM) crossbars in Computing-in-Memory (CIM) architectures offers a promising solution to overcome the von Neumann bottleneck. Due to non-idealities like cell variability, RRAM crossbars are often operated in binary mode, utilizing only two states: Low Resistive State (LRS) and High Resistive State (HRS). Binary Neural Networks (BNNs) and Ternary Neural Networks (TNNs) are well-suited for this hardware due to their efficient mapping. Existing software projects for RRAM-based CIM typically focus on only one aspect: compilation, simulation, or Design Space Exploration (DSE). Moreover, they often rely on classical 8 bit quantization. To address these limitations, we introduce CIM-Explorer, a modular toolkit for optimizing BNN and TNN inference on RRAM crossbars. CIM-Explorer includes an end-to-end compiler stack, multiple mapping options, and simulators, enabling a DSE flow for accuracy estimation across different crossbar parameters and mappings. CIM-Explorer can accompany the entire design process, from early accuracy estimation for specific crossbar parameters, to selecting an appropriate mapping, and compiling BNNs and TNNs for a finalized crossbar chip. In DSE case studies, we demonstrate the expected accuracy for various mappings and crossbar parameters. CIM-Explorer can be found on GitHub.
Authors: Santiago Acevedo, Andrea Mascaretti, Riccardo Rende, Mat\'eo Mahaut, Marco Baroni, Alessandro Laio
Abstract: It was recently observed that the representations of different models that process identical or semantically related inputs tend to align. We analyze this phenomenon using the Information Imbalance, an asymmetric rank-based measure that quantifies the capability of a representation to predict another, providing a proxy of the cross-entropy which can be computed efficiently in high-dimensional spaces. By measuring the Information Imbalance between representations generated by DeepSeek-V3 processing translations, we find that semantic information is spread across many tokens, and that semantic predictability is strongest in a set of central layers of the network, robust across six language pairs. We measure clear information asymmetries: English representations are systematically more predictive than those of other languages, and DeepSeek-V3 representations are more predictive of those in a smaller model such as Llama3-8b than the opposite. In the visual domain, we observe that semantic information concentrates in middle layers for autoregressive models and in final layers for encoder models, and these same layers yield the strongest cross-modal predictability with textual representations of image captions. Notably, two independently trained models (DeepSeek-V3 and DinoV2) achieve stronger cross-modal predictability than the jointly trained CLIP model, suggesting that model scale may outweigh explicit multimodal training. Our results support the hypothesis of semantic convergence across languages, modalities, and architectures, while showing that directed predictability between representations varies strongly with layer-depth, model scale, and language.
Authors: Selina Carter, Arun K Kuchibhotla
Abstract: The construction of confidence intervals and hypothesis tests for functionals is a cornerstone of statistical inference. Traditionally, the most efficient procedures - such as the Wald interval or the Likelihood Ratio Test - require both a point estimator and a consistent estimate of its asymptotic variance. However, when estimators are derived from online or sequential algorithms, computational constraints often preclude multiple passes over the data, complicating variance estimation. In this article, we propose a computationally efficient, rate-optimal wrapper method (HulC) that wraps around any online algorithm to produce asymptotically valid confidence regions bypassing the need for explicit asymptotic variance estimation. The method is provably valid for any online algorithm that yields an asymptotically normal estimator. We evaluate the practical performance of the proposed method primarily using Stochastic Gradient Descent (SGD) with Polyak-Ruppert averaging. Furthermore, we provide extensive numerical simulations comparing the performance of our approach (HulC) when used with other online algorithms, including implicit-SGD and ROOT-SGD.
Authors: Mathew J. Koretsky, Maya Willey, Owen Bianchi, Chelsea X. Alvarado, Tanay Nayak, Nicole Kuznetsov, Sungwon Kim, Mike A. Nalls, Daniel Khashabi, Faraz Faghri
Abstract: Biomedical researchers increasingly rely on large-scale structured databases for complex analytical tasks. However, current text-to-SQL systems often struggle to map qualitative scientific questions into executable SQL, particularly when implicit domain reasoning is required. We introduce BiomedSQL, the first benchmark explicitly designed to evaluate scientific reasoning in text-to-SQL generation over a real-world biomedical knowledge base. BiomedSQL comprises 68,000 question/SQL query/answer triples generated from templates and grounded in a harmonized BigQuery knowledge base that integrates gene-disease associations, causal inference from omics data, and drug approval records. Each question requires models to infer domain-specific criteria, such as genome-wide significance thresholds, effect directionality, or trial phase filtering, rather than rely on syntactic translation alone. We evaluate a range of open- and closed-source LLMs across prompting strategies and interaction paradigms. Our results reveal a substantial performance gap: Gemini-3-Pro achieves 58.1% execution accuracy, while our custom multi-step agent, BMSQL, reaches 62.6%, both well below the expert baseline of 90.0%. BiomedSQL provides a new foundation for advancing text-to-SQL systems capable of supporting scientific discovery through robust reasoning over structured biomedical knowledge bases. Our dataset is publicly available at https://huggingface.co/datasets/NIH-CARD/BiomedSQL, and our code is open-source at https://github.com/NIH-CARD/biomedsql.
URLs: https://huggingface.co/datasets/NIH-CARD/BiomedSQL,, https://github.com/NIH-CARD/biomedsql.
Authors: Andrei Paleyes, Radzim Sendyka, Diana Robinson, Christian Cabrera, Neil D. Lawrence
Abstract: Code generation is one of the most active areas of application of Large Language Models (LLMs). While LLMs lower barriers to writing code and accelerate development process, the overall quality of generated programs depends on the quality of given prompts. Specifically, functionality and quality of generated code can be sensitive to user's background and familiarity with software development. It is therefore important to quantify LLM's sensitivity to variations in the input. To this end we propose an evaluation pipeline for LLM code generation with a focus on measuring sensitivity to prompt augmentations, completely agnostic to a specific programming tasks and LLMs, and thus widely applicable. We provide extensive experimental evidence illustrating utility of our method and share our code for the benefit of the community.
Authors: Zhen Qian, Sebastian Bathiany, Teng Liu, Lana L. Blaschke, Hoong Chen Teo, Niklas Boers
Abstract: Forest ecosystems are vital to the global carbon cycle, yet their long-term aboveground carbon (AGC) dynamics remain uncertain. Here, we integrate multi-source satellite observations with probabilistic deep learning models to reconstruct a harmonized, uncertainty-aware global forest AGC record from 1988 to 2021 at 0.25-deg. We find that, although global forests sequestered 6.2 PgC, moist tropical and boreal forests have progressively transitioned toward carbon sources since the early 2000s. This shift coincides with a strengthening negative correlation between tropical AGC variability and atmospheric CO2 growth rates (r = -0.63 in 2011-2021), suggesting tropical forests increasingly modulate the global carbon cycle. Notably, in the Brazilian Amazon, the contribution of intact forests to the year-to-year variations in AGC losses increased from 33% in the 1990s to 76% in the 2010s, surpassing that of deforested areas (from 60% to 13%). Our findings highlight the vulnerability of carbon stocks in key biomes and provide a benchmark to track emerging sink-source shifts under anthropogenic climate change.
Authors: Gunjan Auti, Hirofumi Daiguji, Gouhei Tanaka
Abstract: Physical transport processes organize through local interactions that redistribute imbalance while preserving conservation. Classical solvers enforce this organization by applying fixed discrete operators on rigid grids. We introduce the Hebbian Physics Network (HPN), a computational framework that replaces this rigid scaffolding with a plastic transport geometry. An HPN is a coupled dynamical system of physical states on nodes and constitutive weights on edges in a graph. Residuals--local violations of continuity, momentum balance, or energy conservation--act as thermodynamic forces that drive the joint evolution of both the state and the operator (i.e. the adaptive weights). The weights adapt through a three-factor Hebbian rule, which we prove constitutes a strictly local gradient descent on the residual energy. This mechanism ensures thermodynamic stability: near equilibrium, the learned operator naturally converges to a symmetric, positive-definite form, rigorously reproducing Onsager\'s reciprocal relations without explicit enforcement. Far from equilibrium, the system undergoes a self-organizing search for a transport topology that restores global coercivity. Unlike optimization-based approaches that impose physics through global loss functions, HPNs embed conservation intrinsically: transport is restored locally by the evolving operator itself, without a global Poisson solve or backpropagated objective. We demonstrate the framework on scalar diffusion and incompressible lid-driven cavity flow, showing that physically consistent transport geometries and flow structures emerge from random initial conditions solely through residual-driven local adaptation. HPNs thus reframe computation not as the solution of a fixed equation, but as a thermodynamic relaxation process where the constitutive geometry and physical state co-evolve.
Authors: Minwei Zhao, Guosheng Yang, Zhuoni Zhang, Filip Biljecki, Hanzhi Zu, Cai Wu
Abstract: Urban streets are essential everyday health infrastructure, yet their capacity to support physical activity is unevenly distributed. This study develops a theory-informed and explainable framework to diagnose street-level exercise deprivation by integrating Lefebvre's spatial triad with multi-source urban data and SHAP-based analysis. Using Shenzhen as a case study, we show that while conceived spatial attributes have the strongest overall influence on exercise intensity, local deprivation mechanisms vary substantially across contexts. We identify a seven-mode typology of deprivation and locate high-demand but low-support street segments as priority areas for intervention. The study offers both a theory-grounded analytical framework and a practical diagnostic tool for promoting spatial justice in everyday physical activity.
Authors: Rickard Karlsson, Piersilvio De Bartolomeis, Issa J. Dahabreh, Jesse H. Krijthe
Abstract: Randomized trials are typically designed to detect average treatment effects but often lack the statistical power to uncover individual-level treatment effect heterogeneity, limiting their value for personalized decision-making. To address this, we propose the QR-learner, a model-agnostic learner that estimates conditional average treatment effects (CATE) within the trial population by leveraging external data from other trials or observational studies. The proposed method is robust: it can reduce the mean squared error relative to a trial-only CATE learner, and is guaranteed to recover the true CATE even when the external data are not aligned with the trial. Moreover, we introduce a procedure that combines the QR-learner with a trial-only CATE learner and show that it asymptotically matches or exceeds both component learners in terms of mean squared error. We examine the performance of our approach in simulation studies and apply the methods to a real-world dataset, demonstrating improvements in both CATE estimation and statistical power for detecting heterogeneous effects.
Authors: Peng Ding
Abstract: Large Language Model (LLM) applications are increasingly relying on external tools to extend their capabilities beyond text generation. However, current tool integration approaches suffer from fragmentation, protocol limitations, and implementation complexity, leading to substantial development overhead. This paper presents ToolRegistry, a protocol-agnostic tool management system that has evolved from a single library into a modular three-package ecosystem: a core registry for tool management and execution, a server package providing protocol adapters (MCP, OpenAPI) and routing, and a hub package offering curated, production-tested tool implementations. Beyond the original contributions of unified registration, automated schema generation, and dual-mode concurrent execution, the ecosystem now includes an independent MCP client supporting four transport mechanisms, a web-based admin panel for runtime management, an event system for change propagation, and fine-grained tool lifecycle control. Our evaluation demonstrates that ToolRegistry achieves 60-80% reduction in tool integration code, up to 3.1x performance improvements through concurrent execution, and broad compatibility with OpenAI function calling standards. Real-world case studies show significant improvements in development efficiency and code maintainability across diverse integration scenarios. ToolRegistry is open-source and available at https://github.com/Oaklight/ToolRegistry, with comprehensive documentation at https://toolregistry.readthedocs.io/.
URLs: https://github.com/Oaklight/ToolRegistry,, https://toolregistry.readthedocs.io/.
Authors: Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar
Abstract: Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why performance varies drastically between similar models, remains elusive. These questions can be answered through the generalisation error, which measures the discrepancy between a model's predictions and the true values it is meant to recover. Although several works have derived generalisation error bounds, learning theoretical bounds are typically loose, restricted to a single architecture, and offer limited insight into what governs generalisation in practice. In this work, we take a fundamentally different approach by deriving the exact generalisation error for a broad range of linear GNNs, including convolutional, PageRank-based, and attention-based models, through the lens of signal processing. Our exact generalisation error exposes a strong benchmark bias in existing literature: commonly used datasets exhibit high alignment between node features and the graph structure, inherently favouring architectures that rely on it. We further show that the similarity between connected nodes (homophily) decisively governs which architectures are best suited for a given graph, thereby explaining how specific benchmark properties systematically shape the reported performance in the literature. Together, these results explain when and why GNNs can effectively leverage structure and feature information, supporting the reliable application of GNNs.
Authors: Gautam Sreekumar, Vishnu Naresh Boddeti
Abstract: Large multimodal models (LMMs) encode physical laws observed during training, such as momentum conservation, as parametric knowledge. It allows LMMs to answer physical reasoning queries, such as the outcome of a potential collision event from visual input. However, since parametric knowledge includes only the physical laws seen during training, it is insufficient for reasoning in inference scenarios that follow physical laws unseen during training. In such novel physical environments, humans could adapt their physical reasoning based on provided demonstrations. This inductive physical reasoning ability is indispensable for LMMs if they are to replace human agents in safety-critical applications. Despite its importance, existing visual benchmarks do not evaluate inductive physical reasoning and only consider the parametric knowledge in LMMs. To this end, we propose InPhyRe, the first visual question answering benchmark to measure inductive physical reasoning in LMMs. InPhyRe evaluates LMMs' ability to predict the outcome of collision events in algorithmically generated synthetic videos. By inspecting over 13 open-source and proprietary LMMs, InPhyRe informs us that (1) LMMs struggle to apply their limited parametric knowledge about universal physical laws to reasoning, (2) inductive physical reasoning in LMMs is weak when the physical laws underlying inference scenarios were unseen during training, and (3) inductive physical reasoning in LMMs suffers from language bias and may ignore the visual inputs, questioning the trustworthiness of LMMs regarding visual inputs.
Authors: Tianyu Chen, Yasi Zhang, Zhi Zhang, Peiyu Yu, Shu Wang, Zhendong Wang, Kevin Lin, Xiaofei Wang, Zhengyuan Yang, Linjie Li, Chung-Ching Lin, Jianwen Xie, Oscar Leong, Lijuan Wang, Ying Nian Wu, Mingyuan Zhou
Abstract: Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images, resulting in limited coverage and inheriting biases from prior generative models or (ii) rely solely on zero-shot vision language models (VLMs), whose prompt-based assessments of instruction following, content consistency, and visual quality are often imprecise. To address this, we introduce EdiVal, an automated and fine-grained evaluation framework grounded in an object-centric perspective, designed to assess not only standard single-turn but also multi-turn instruction-based editing with precision. Given an input image, EdiVal first decomposes it into semantically meaningful objects, then synthesizes diverse, context-aware editing instructions while dynamically updating object pools across turns. These two stages enable two novel object centric metrics tailored for multi turn evaluation and one global metric of visual quality: 1) EdiVal-IF, which measures instruction following by combining open vocabulary object detectors for symbolic checks with VLMs for semantic verification on detector guided crops; 2) EdiVal-CC, which evaluates content consistency by calculating semantic similarity of unchanged objects and background using the evolving object pools; and 3) EdiVal-VQ, which quantifies changes in overall visual quality with human preference models. Instantiating this pipeline, we build EdiVal Bench, a multi-turn editing benchmark covering 9 instruction types and 16 state-of-the-art editing models, spanning in-context, flow-matching, and diffusion paradigms. We demonstrate that EdiVal can be used to identify existing failure modes, thereby informing the development of the next generation of editing models.
Authors: Yongding Tao, Tian Wang, Yihong Dong, Huanyu Liu, Kechi Zhang, Xiaolong Hu, Ge Li
Abstract: Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance. While detection methods have been developed for the pre-training and Supervised Fine-Tuning stages, a critical research gap exists for the increasingly significant phase of Reinforcement Learning (RL) post-training. As RL post-training becomes pivotal for advancing LLM reasoning, the absence of specialized contamination detection methods in this paradigm presents a critical vulnerability. To address this, we conduct the first systematic study of data detection within RL post-training scenario and propose Self-Critique. Our method is motivated by a key observation: after RL phase, the output entropy distribution of LLMs tends to collapse into highly specific and sparse modes. Self-Critique probes for the underlying policy collapse, i.e., the model's convergence to a narrow reasoning path, which causes this entropy reduction. To facilitate this research, we also introduce RL-MIA, a benchmark constructed to simulate this specific contamination scenario. Extensive experiments show that Self-Critique significantly outperforms baseline methods across multiple models and contamination tasks, achieving an AUC improvement of up to 30%. Whereas existing methods are close to a random guess for RL-phase contamination, our method makes detection possible.
Authors: Francesco Montagna
Abstract: Causal discovery from i.i.d. observational data is known to be generally ill-posed. We demonstrate that if we have access to the distribution {induced} by a structural causal model, and additional data from (in the best case) \textit{only two} environments that sufficiently differ in the noise statistics, the unique causal graph is identifiable. Notably, this is the first result in the literature that guarantees the entire causal graph recovery with a constant number of environments and arbitrary nonlinear mechanisms. Our only constraint is the Gaussianity of the noise terms; however, we propose potential ways to relax this requirement. Of interest on its own, we expand on the well-known duality between independent component analysis (ICA) and causal discovery; recent advancements have shown that nonlinear ICA can be solved from multiple environments, at least as many as the number of sources: we show that the same can be achieved for causal discovery while having access to much less auxiliary information.
Authors: Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames
Abstract: Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer a principled method to enforce dynamic safety -- traditionally deployed online via safety filters. While the result is safe behavior, the fact that the RL policy does not have knowledge of the CBF can lead to conservative behaviors. This paper proposes CBF-RL, a framework for generating safe behaviors with RL by enforcing CBFs in training. CBF-RL has two key attributes: (1) minimally modifying a nominal RL policy to encode safety constraints via a CBF term, (2) and safety filtering of the policy rollouts in training. Theoretically, we prove that continuous-time safety filters can be deployed via closed-form expressions on discrete-time roll-outs. Practically, we demonstrate that CBF-RL internalizes the safety constraints in the learned policy -- both enforcing safer actions and biasing towards safer rewards -- enabling safe deployment without the need for an online safety filter. We validate our framework through ablation studies on navigation tasks and on the Unitree G1 humanoid robot, where CBF-RL enables safer exploration, faster convergence, and robust performance under uncertainty, enabling the humanoid robot to avoid obstacles and climb stairs safely in real-world settings without a runtime safety filter.
Authors: Chuansen Peng, Xiaojing Shen
Abstract: This paper tackles the challenging problem of jointly inferring time-varying network topologies and imputing missing data from partially observed graph signals. We propose a unified non-convex optimization framework to simultaneously recover a sequence of graph Laplacian matrices while reconstructing the unobserved signal entries. Unlike conventional decoupled methods, our integrated approach facilitates a bidirectional flow of information between the graph and signal domains, yielding superior robustness, particularly in high missing-data regimes. To capture realistic network dynamics, we introduce a fused-lasso type regularizer on the sequence of Laplacians. This penalty promotes temporal smoothness by penalizing large successive changes, thereby preventing spurious variations induced by noise while still permitting gradual topological evolution. For solving the joint optimization problem, we develop an efficient Alternating Direction Method of Multipliers (ADMM) algorithm, which leverages the problem's structure to yield closed-form solutions for both the graph and signal subproblems. This design ensures scalability to large-scale networks and long time horizons. On the theoretical front, despite the inherent non-convexity, we establish a convergence guarantee, proving that the proposed ADMM scheme converges to a stationary point. Furthermore, we derive non-asymptotic statistical guarantees, providing high-probability error bounds for the graph estimator as a function of sample size, signal smoothness, and the intrinsic temporal variability of the graph. Extensive numerical experiments validate the approach, demonstrating that it significantly outperforms state-of-the-art baselines in both convergence speed and the joint accuracy of graph learning and signal recovery.
Authors: Dailan He, Guanlin Feng, Xingtong Ge, Yazhe Niu, Yi Zhang, Bingqi Ma, Guanglu Song, Yu Liu, Hongsheng Li
Abstract: Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching models is challenging because of its deterministic sampling paradigm. Current methods address this issue by converting Ordinary Differential Equations (ODEs) to Stochastic Differential Equations (SDEs), which introduce stochasticity. However, this SDE-based GRPO suffers from issues of inefficient credit assignment and incompatibility with high-order solvers for fewer-step sampling. In this paper, we first reinterpret existing SDE-based GRPO methods from a distance optimization perspective, revealing their underlying mechanism as a form of contrastive learning. Based on this insight, we propose Neighbor GRPO, a novel alignment algorithm that completely bypasses the need for SDEs. Neighbor GRPO generates a diverse set of candidate trajectories by perturbing the initial noise conditions of the ODE and optimizes the model using a softmax distance-based surrogate leaping policy. We establish a theoretical connection between this distance-based objective and policy gradient optimization, rigorously integrating our approach into the GRPO framework. Our method fully preserves the advantages of deterministic ODE sampling, including efficiency and compatibility with high-order solvers. We further introduce symmetric anchor sampling for computational efficiency and group-wise quasi-norm reweighting to address reward flattening. Extensive experiments demonstrate that Neighbor GRPO significantly outperforms SDE-based counterparts in terms of training cost, convergence speed, and generation quality.
Authors: Chuang-Chieh Lin, Chi-Jen Lu, Po-An Chen, Chih-Chieh Hung
Abstract: We formulate two-party policy competition as a two-player non-cooperative game, generalizing Lin et al.'s work (2021). Each party selects a real-valued policy vector as its strategy from a compact subset of Euclidean space, and a voter's utility for a policy is given by the inner product with their preference vector. To capture the uncertainty in the competition, we assume that a policy's winning probability increases monotonically with its total utility across all voters, and we formalize this via an affine isotonic function. A player's payoff is defined as the expected utility received by its supporters. In this work, we first test and validate the isotonicity hypothesis through voting simulations. Next, we prove the existence of a pure-strategy Nash equilibrium (PSNE) in both one- and multi-dimensional settings. Although we construct a counterexample demonstrating the game's non-monotonicity, our experiments show that a decentralized gradient-based algorithm typically converges rapidly to an approximate PSNE. Finally, we present a grid-based search algorithm that finds an $\epsilon$-approximate PSNE of the game in time polynomial in the input size and $1/\epsilon$.
Authors: Syed Naveed Mahmood, Md. Rezaur Rahman Bhuiyan, Tasfia Zaman, Jareen Tasneem Khondaker, Md. Sameer Sakib, K. M. Shadman Wadith, Nazia Tasnim, Farig Sadeque
Abstract: Selective knowledge erasure from LLMs is critical for GDPR compliance and model safety, yet current unlearning methods conflate behavioral suppression with true knowledge removal, allowing latent capabilities to persist beneath surface-level refusals. In this work, we address this challenge by introducing Knowledge Immunization Framework (KIF), a representation-aware architecture that distinguishes genuine erasure from obfuscation by targeting internal activation signatures rather than surface outputs. Our approach combines dynamic suppression of subject-specific representations with parameter-efficient adaptation, enabling durable unlearning without full model retraining. KIF achieves near-oracle erasure (FQ approx 0.99 vs. 1.00) while preserving utility at oracle levels (MU = 0.62), effectively breaking the stability-erasure tradeoff that has constrained all prior work. We evaluate both standard foundation models (Llama and Mistral) and reasoning-prior models (Qwen and DeepSeek) across 3B to 14B parameters. Our observation shows that standard models exhibit scale-independent true erasure (<3% utility drift), while reasoning-prior models reveal fundamental architectural divergence. Our comprehensive dual-metric evaluation protocol, combining surface-level leakage with latent trace persistence, operationalizes the obfuscation - erasure distinction and enables the first systematic diagnosis of mechanism-level forgetting behavior across model families and scales.
Authors: Shahbaz Shaik, Sourav Chatterjee, Sayantan Pramanik, Indranil Chakrabarty
Abstract: We introduce a physics-informed Generative Adversarial Network framework that recasts quantum resource-state generation as an inverse-design task. By embedding task-specific utility functions into training, the model learns to generate valid two-qubit states optimized for teleportation and entanglement broadcasting. Comparing decomposition-based and direct-generation architectures reveals that structural enforcement of Hermiticity, trace-one, and positivity yields higher fidelity and training stability than loss-only approaches. The framework reproduces theoretical resource boundaries for Werner-like and Bell-diagonal states with fidelities exceeding ~98%, establishing adversarial learning as a lightweight yet effective method for constraint-driven quantum-state discovery. This approach provides a scalable foundation for automated design of tailored quantum resources for information-processing applications, exemplified with teleportation and broadcasting of entanglement, and it opens up the possibility of using such states in efficient quantum network design.
Authors: Gionni Marchetti
Abstract: We address the intrinsic dimensionality (ID) of high-dimensional trajectories, comprising $n_s = 4\,000\,000$ data points, of the Fermi-Pasta-Ulam-Tsingou (FPUT) $\beta$ model with $N = 32$ oscillators. To this end, a deep autoencoder (DAE) is used to infer the ID in the weakly nonlinear regime where energy recurrences are observed ($\beta \lesssim 1$). We find that the trajectories lie on a nonlinear Riemannian manifold of dimension $m^{\ast} = 2$ embedded in a $64$-dimensional phase space. By contrast, principal component analysis (PCA) together with the Participation Ratio (PR) method provides only a reasonable upper bound on the ID for each value of $\beta$. Our DAE further reveals that the ID increases to $m^{\ast} = 3$ at $\beta = 1.1$, coinciding with a symmetry-breaking (SB) phenomenon characteristic of the $\beta$ model, in which additional energy modes with even wave numbers $k = 2, 4$ become excited. Notably, the SB phenomenon cannot be detected by the linear approach provided by PCA.
Authors: Dhruv S. Kushwaha, Zoleikha A. Biron
Abstract: Reinforcement Learning (RL) has achieved remarkable success in solving complex sequential decision-making problems. However, its application to safety-critical physical systems remains constrained by the lack of stability guarantees. Standard RL algorithms prioritize reward maximization, often yielding policies that may induce oscillations or unbounded state divergence. There has been significant work in incorporating Lyapunov-based stability guarantees in RL algorithms with key challenges being selecting a candidate Lyapunov function, computational complexity by using excessive function approximators and conservative policies by incorporating stability criterion in the learning process. In this work we propose a novel Lyapunov-constrained Soft Actor-Critic (LC-SAC) algorithm using Koopman operator theory. We propose use of extended dynamic mode decomposition (EDMD) to produce a linear approximation of the system and use this approximation to derive a closed form solution for candidate Lyapunov function. This derived Lyapunov function is incorporated in the SAC algorithm to further provide guarantees for a policy that stabilizes the nonlinear system. The results are evaluated trajectory tracking of a 2D Quadrotor environment based on safe-control-gym. The proposed algorithm shows training convergence and decaying violations for Lyapunov stability criterion compared to baseline vanilla SAC algorithm. GitHub Repository: https://github.com/DhruvKushwaha/LC-SAC-Quadrotor-Trajectory-Tracking
URLs: https://github.com/DhruvKushwaha/LC-SAC-Quadrotor-Trajectory-Tracking
Authors: Ethan Rathbun, Wo Wei Lin, Alina Oprea, Christopher Amato
Abstract: Simulated environments are a key piece in the success of Reinforcement Learning (RL), allowing practitioners and researchers to train decision making agents without running expensive experiments on real hardware. Simulators remain a security blind spot, however, enabling adversarial developers to alter the dynamics of their released simulators for malicious purposes. Therefore, in this work we highlight a novel threat, demonstrating how simulator dynamics can be exploited to stealthily implant action-level backdoors into RL agents. The backdoor then allows an adversary to reliably activate targeted actions in an agent upon observing a predefined ``trigger'', leading to potentially dangerous consequences. Traditional backdoor attacks are limited in their strong threat models, assuming the adversary has near full control over an agent's training pipeline, enabling them to both alter and observe agent's rewards. As these assumptions are infeasible to implement within a simulator, we propose a new attack ``Daze'' which is able to reliably and stealthily implant backdoors into RL agents trained for real world tasks without altering or even observing their rewards. We provide formal proof of Daze's effectiveness in guaranteeing attack success across general RL tasks along with extensive empirical evaluations on both discrete and continuous action space domains. We additionally provide the first example of RL backdoor attacks transferring to real, robotic hardware. These developments motivate further research into securing all components of the RL training pipeline to prevent malicious attacks.
Authors: Qiuming Luo, Yuebing Li, Feng Li, Chang Kong
Abstract: Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment. To address this, we propose PAND (Prompt-Aware Neighborhood Distillation), a two-stage framework that decouples semantic calibration from structural transfer. First, we incorporate Prompt-Aware Semantic Calibration to generate adaptive semantic anchors. Second, we introduce a neighborhood-aware structural distillation strategy to constrain the student's local decision structure. PAND consistently outperforms state-of-the-art methods on four FGVC benchmarks. Notably, our ResNet-18 student achieves 76.09% accuracy on CUB-200, surpassing the strong baseline VL2Lite by 3.4%. Code is available at https://github.com/LLLVTA/PAND.
Authors: Tarun Advaith Kumar, Yijian Zou, Amir-Reza Negari, Roger G. Melko, Timothy H. Hsieh
Abstract: We identify fundamental limitations in machine learning by demonstrating that non-trivial mixed-state phases of matter are computationally hard to learn. Focusing on unsupervised learning of distributions, we show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states. We demonstrate that conditional mutual information (CMI) is a useful diagnostic for LI: we show that for classical distributions, long-range CMI of a state implies a spatially LI partner. By introducing a restricted statistical query model, we prove that nontrivial phases with long-range CMI, such as strong-to-weak spontaneous symmetry breaking phases, are hard to learn. We validate our claims by using recurrent, convolutional, and Transformer neural networks to learn the syndrome and physical distributions of toric/surface code under bit flip noise. Our findings suggest hardness of learning as a diagnostic tool for detecting mixed-state phases and transitions and error-correction thresholds, and they suggest CMI and more generally ``non-local Gibbsness'' as metrics for how hard a distribution is to learn.
Authors: Minghan Wang, Ye Bai, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari
Abstract: Inference-time scaling (ITS) in latent reasoning models typically relies on heuristic perturbations, such as dropout or fixed Gaussian noise, to generate diverse candidate trajectories. However, we show that stronger perturbations do not necessarily yield better sampling quality: they often induce larger distribution shifts without producing more useful reasoning paths or better final decisions. A key limitation is that these perturbations inject stochasticity without defining an explicit conditional sampling distribution, making latent exploration difficult to control or optimize. To address this, we propose the Gaussian Thought Sampler (GTS), a lightweight module that reformulates latent exploration as sampling from a learned conditional distribution over continuous reasoning states. GTS predicts context-dependent perturbation distributions and is trained with GRPO-style policy optimization while keeping the backbone frozen, turning heuristic perturbation into an explicit probabilistic sampling policy. Experiments across multiple benchmarks and two latent reasoning architectures show that GTS yields more reliable inference-time scaling than heuristic baselines, suggesting that effective latent ITS requires better-controlled and optimizable sampling rather than simply amplifying stochasticity.
Authors: Qingyong Zhu, Yumin Tan, Xiang Gu, Dong Liang
Abstract: Fully unsupervised deep generative modeling (FU-DGM) is promising for compressively sampled MRI (CS-MRI) when training data or compute are limited. Classical FU-DGMs such as DIP and INR rely on architectural priors, but the ill-conditioned inverse problem often demands many iterations and easily overfits measurement noise. We propose CogGen, a cognitive-load-informed FU-DGM that casts CS-MRI as staged inversion and regulates task-side "cognitive load" by progressively scheduling intrinsic difficulty and extraneous interference. CogGen replaces uniform data fitting with an easy-to-hard k-space weighting/selection strategy: early iterations emphasize low-frequency, high-SNR, structure-dominant samples, while higher-frequency or noise-dominated measurements are introduced later. We realize this schedule through self-paced curriculum learning (SPCL) with complementary criteria: a student mode that reflects what the model can currently learn and a teacher mode that indicates what it should follow, supporting both soft weighting and hard selection. Experiments and analyses show that CogGen-DIP and CogGen-INR improve reconstruction fidelity and convergence behavior compared with strong unsupervised baselines and competitive supervised pipelines.
Authors: Reza Ghane, Danil Akhtiamov, Babak Hassibi
Abstract: In this work we study the convergence properties of the Dual Space Preconditioned Gradient Descent, encompassing optimizers such as Normalized Gradient Descent, Gradient Clipping and Adam. We consider preconditioners of the form $\nabla K$, where $K: \mathbb{R}^p \to \mathbb{R}$ is convex and assume that the latter is applied to train an over-parameterized linear model with loss of the form $\ell({X} {W} - {Y})$, for weights ${W} \in \mathbb{R}^{d \times k}$, labels ${Y} \in \mathbb{R}^{n \times k}$ and data ${X} \in \mathbb{R}^{n \times d}$. Under the aforementioned assumptions, we prove that the iterates of the preconditioned gradient descent always converge to a point ${W}_{\infty} \in \mathbb{R}^{d \times k}$ satisfying ${X}{W}_{\infty} = {Y}$. Our proof techniques are of independent interest as we introduce a novel version of the Bregman Divergence with accompanying identities that allow us to establish convergence. We also study the implicit bias of Dual Space Preconditioned Gradient Descent. First, we demonstrate empirically that, for general $K(\cdot)$, ${W}_\infty$ depends on the chosen learning rate, hindering a precise characterization of the implicit bias. Then, for preconditioners of the form $K({G}) = h(\|{G}\|_F)$, known as \textit{isotropic preconditioners}, we show that ${W}_\infty$ minimizes $\|{W}_\infty - {W}_0\|_F^2$ subject to ${X}{W}_\infty = {Y}$, where ${W}_0$ is the initialization. Denoting the convergence point of GD initialized at ${W}_0$ by ${W}_{\text{GD}, \infty}$, we thus note ${W}_{\infty} = {W}_{\text{GD}, \infty}$ for isotropic preconditioners. Finally, we show that a similar fact holds for general preconditioners up to a multiplicative constant, namely, $\|{W}_0 - {W}_{\infty}\|_F \le c \|{W}_0 - {W}_{\text{GD}, \infty}\|_F$ for a constant $c>0$.
Authors: Shaily Roy, Harshit Sharma, Daniel A. Adler, Tanzeem Choudhury, Asif Salekin
Abstract: Computational models are increasingly embedded in human-centered domains such as healthcare, education, workplace analytics, and digital well-being, where their predictions directly influence individual outcomes and collective welfare. In such contexts, achieving high accuracy alone is insufficient; models must also act ethically and equitably across diverse populations. However, fair AI approaches that rely on demographic attributes are impractical, as such information is often unavailable, privacy-sensitive, or restricted by regulatory frameworks. Moreover, conventional parity-based fairness approaches, while aiming for equity, can inadvertently violate core ethical principles by trading off subgroup performance or stability. To address this challenge, we present Flare (Fisher-guided LAtent-subgroup learning with do-no-harm REgularization), the first demographic-agnostic framework that aligns algorithmic fairness with ethical principles through the geometry of optimization. Flare leverages Fisher Information to regularize curvature, uncovering latent disparities in model behavior without access to demographic or sensitive attributes. By integrating representation, loss, and curvature signals, it identifies hidden performance strata and adaptively refines them through collaborative but do-no-harm optimization, enhancing each subgroup's performance while preserving global stability and ethical balance. We also introduce BHE (Beneficence-Harm Avoidance-Equity), a novel metric suite that operationalizes ethical fairness evaluation beyond statistical parity. Extensive evaluations across diverse physiological (EDA), behavioral (IHS), and clinical (OhioT1DM) datasets show that Flare consistently enhances ethical fairness compared to state-of-the-art baselines.
Authors: Chika Maduabuchi
Abstract: State-of-the-art text-to-video models often look realistic frame-by-frame yet fail on simple interactions: motion starts before contact, actions are not realized, objects drift after placement, and support relations break. We argue this stems from frame-first denoising, which updates latent state everywhere at every step without an explicit notion of when and where an interaction is active. We introduce Event-Driven Video Generation (EVD), a minimal DiT-compatible framework that makes sampling event-grounded: a lightweight event head predicts token-aligned event activity, event-grounded losses couple activity to state change during training, and event-gated sampling (with hysteresis and early-step scheduling) suppresses spurious updates while concentrating updates during interactions. On EVD-Bench, EVD consistently improves human preference and VBench dynamics, substantially reducing failure modes in state persistence, spatial accuracy, support relations, and contact stability without sacrificing appearance. These results indicate that explicit event grounding is a practical abstraction for reducing interaction hallucinations in video generation.
Authors: Zhaoyuan Gu, Yipu Chen, Zimeng Chai, Alfred Cueva, Thong Nguyen, Yifan Wu, Huishu Xue, Minji Kim, Isaac Legene, Fukang Liu, Matthew Kim, Ayan Barula, Yongxin Chen, Ye Zhao
Abstract: Humanoid loco-manipulation requires coordinated high-level motion plans with stable, low-level whole-body execution under complex robot-environment dynamics and long-horizon tasks. While diffusion policies (DPs) show promise for learning from demonstrations, deploying them on humanoids poses critical challenges: the motion planner trained offline is decoupled from the low-level controller, leading to poor command tracking, compounding distribution shift, and task failures. The common approach of scaling demonstration data is prohibitively expensive for high-dimensional humanoid systems. To address this challenge, we present REFINE-DP (REinforcement learning FINE-tuning of Diffusion Policy), a hierarchical framework that jointly optimizes a DP high-level planner and an RL-based low-level loco-manipulation controller. The DP is fine-tuned via a PPO-based diffusion policy gradient to improve task success rate, while the controller is simultaneously updated to accurately track the planner's evolving command distribution, reducing the distributional mismatch that degrades motion quality. We validate REFINE-DP on a humanoid robot performing loco-manipulation tasks, including door traversal and long-horizon object transport. REFINE-DP achieves an over $90\%$ success rate in simulation, even in out-of-distribution cases not seen in the pre-trained data, and enables smooth autonomous task execution in real-world dynamic environments. Our proposed method substantially outperforms pre-trained DP baselines and demonstrates that RL fine-tuning is key to reliable humanoid loco-manipulation. https://refine-dp.github.io/REFINE-DP/
Authors: Agnimitra Dasgupta, Ali Fardisi, Mehrnegar Aminy, Brianna Binder, Bryan Shaddy, Assad Oberai
Abstract: This study presents a conditional flow matching framework for solving physics-constrained Bayesian inverse problems. In this setting, samples from the joint distribution of inferred variables and measurements are assumed available, while explicit evaluation of the prior and likelihood densities is not required. We derive a simple and self-contained formulation of both the unconditional and conditional flow matching algorithms, tailored specifically to inverse problems. In the conditional setting, a neural network is trained to learn the velocity field of a probability flow ordinary differential equation that transports samples from a chosen source distribution directly to the posterior distribution conditioned on observed measurements. This black-box formulation accommodates nonlinear, high-dimensional, and potentially non-differentiable forward models without restrictive assumptions on the noise model. We further analyze the behavior of the learned velocity field in the regime of finite training data. Under mild architectural assumptions, we show that overtraining can induce degenerate behavior in the generated conditional distributions, including variance collapse and a phenomenon termed selective memorization, wherein generated samples concentrate around training data points associated with similar observations. A simplified theoretical analysis explains this behavior, and numerical experiments confirm it in practice. We demonstrate that standard early-stopping criteria based on monitoring test loss effectively mitigate such degeneracy. The proposed method is evaluated on several physics-based inverse problems. We investigate the impact of different choices of source distributions, including Gaussian and data-informed priors. Across these examples, conditional flow matching accurately captures complex, multimodal posterior distributions while maintaining computational efficiency.
Authors: Yuan-Hao Wei, Fu-Hao Deng, Lin-Yong Cui, Yan-Jie Sun
Abstract: Blind source separation (BSS) seeks to recover latent source signals from observed mixtures. Variational autoencoders (VAEs) offer a natural perspective for this problem: the latent variables can be interpreted as source components, the encoder can be viewed as a demixing mapping from observations to sources, and the decoder can be regarded as a remixing process from inferred sources back to observations. In this work, we propose AR-Flow VAE, a novel VAE-based framework for BSS in which each latent source is endowed with a parameter-adaptive autoregressive flow prior. This prior significantly enhances the flexibility of latent source modeling, enabling the framework to capture complex non-Gaussian behaviors and structured dependencies, such as temporal correlations, that are difficult to represent with conventional priors. In addition, the structured prior design assigns distinct priors to different latent dimensions, thereby encouraging the latent components to separate into different source signals under heterogeneous prior constraints. Experimental results validate the effectiveness of the proposed architecture for blind source separation. More importantly, this work provides a foundation for future investigations into the identifiability and interpretability of AR-Flow VAE.
Authors: Surendra Pathak, Bo Han
Abstract: While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction strategies attempt to accelerate inference, such methods inadequately exploit attention values and fail to address token redundancy. More critically, they overlook the ``attention shift'' phenomenon inherent in LVLMs, which skews token attention scores. In this work, we propose ASAP, a novel training-free, KV-Cache-compatible pruning recipe that comprehensively addresses these limitations. First, we mitigate the attention shift by utilizing a dynamic bidirectional soft attention mask, ensuring the selection of genuinely informative tokens rather than naive attention-based selection. Second, we posit that high semantic redundancy within the token set degrades performance. We therefore introduce a weighted soft merging component that merges semantically similar tokens, preserving only the most feature-dense visual patches for subsequent layers. ASAP achieves virtually lossless compression of visual context, retaining 99.02% of the original LLaVA-NeXT-7B performance while aggressively slashing computational FLOPs by ~80%.
Authors: Haoyuan Sun, Ali Jadbabaie
Abstract: We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy the best controller for the unknown system by periodically selecting among a collection of $N$ candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds. Conversely, current non-asymptotic methods in both online learning and system identification require restrictive assumptions that are incompatible in a control setting, such as system stability, which preclude testing potentially unstable controllers. To bridge this gap, we propose a novel, non-asymptotic analysis of supervisory control that adapts multi-armed bandit algorithms to a control-theoretic setting. The proposed data-driven algorithm evaluates candidate controllers via scoring criteria that leverage system observability to isolate the effects of state history, enabling both detection of destabilizing controllers and accurate system identification. We present two algorithmic variants with dimension-free, finite-time guarantees, where each identifies the most suitable controller in $\mathcal{O}(N \log N)$ steps, while simultaneously achieving finite $L_2$-gain with respect to system disturbances.
Authors: Tuan-Anh Yang, Bao V. Q. Bui, Chanh-Quang Vo-Van, Truong-Son Hy
Abstract: We propose a deep learning framework for COVID-19 detection and disease classification from chest CT scans that integrates both 2.5D and 3D representations to capture complementary slice-level and volumetric information. The 2.5D branch processes multi-view CT slices (axial, coronal, sagittal) using a DINOv3 vision transformer to extract robust visual features, while the 3D branch employs a ResNet-18 architecture to model volumetric context and is pretrained with Variance Risk Extrapolation (VREx) followed by supervised contrastive learning to improve cross-source robustness. Predictions from both branches are combined through logit-level ensemble inference. Experiments on the PHAROS-AIF-MIH benchmark demonstrate the effectiveness of the proposed approach: for binary COVID-19 detection, the ensemble achieves 94.48% accuracy and a 0.9426 Macro F1-score, outperforming both individual models, while for multi-class disease classification the 2.5D DINOv3 model achieves the best performance with 79.35% accuracy and a 0.7497 Macro F1-score. These results highlight the benefit of combining pretrained slice-based representations with volumetric modeling for robust multi-source medical imaging analysis. Code is available at https://github.com/HySonLab/PHAROS-AIF-MIH
Authors: Omer Ben Hayun, Roy Betser, Meir Yossef Levi, Levi Kassel, Guy Gilboa
Abstract: Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at https://omerbenhayun.github.io/stall-video.
Authors: Aliyu Agboola Alege
Abstract: Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural aggregation methods) or rely on manually engineered discrete predicates (probabilistic logic frameworks), limiting scalability to unstructured data. We introduce Latent Posterior Factors (LPF), a framework that transforms Variational Autoencoder (VAE) latent posteriors into soft likelihood factors for Sum-Product Network (SPN) inference, enabling tractable probabilistic reasoning over unstructured evidence while preserving calibrated uncertainty estimates. We instantiate LPF as LPF-SPN (structured factor-based inference) and LPF-Learned (end-to-end learned aggregation), enabling a principled comparison between explicit probabilistic reasoning and learned aggregation under a shared uncertainty representation. Across eight domains (seven synthetic and the FEVER benchmark), LPF-SPN achieves high accuracy (up to 97.8%), low calibration error (ECE 1.4%), and strong probabilistic fit, substantially outperforming evidential deep learning, LLMs and graph-based baselines over 15 random seeds. Contributions: (1) A framework bridging latent uncertainty representations with structured probabilistic reasoning. (2) Dual architectures enabling controlled comparison of reasoning paradigms. (3) Reproducible training methodology with seed selection. (4) Evaluation against EDL, BERT, R-GCN, and large language model baselines. (5) Cross-domain validation. (6) Formal guarantees in a companion paper.
Authors: Aliyu Agboola Alege
Abstract: We present a complete theoretical characterization of Latent Posterior Factors (LPF), a principled framework for aggregating multiple heterogeneous evidence items in probabilistic prediction tasks. Multi-evidence reasoning arises pervasively in high-stakes domains including healthcare diagnosis, financial risk assessment, legal case analysis, and regulatory compliance, yet existing approaches either lack formal guarantees or fail to handle multi-evidence scenarios architecturally. LPF encodes each evidence item into a Gaussian latent posterior via a variational autoencoder, converting posteriors to soft factors through Monte Carlo marginalization, and aggregating factors via exact Sum-Product Network inference (LPF-SPN) or a learned neural aggregator (LPF-Learned). We prove seven formal guarantees spanning the key desiderata for trustworthy AI: Calibration Preservation (ECE <= epsilon + C/sqrt(K_eff)); Monte Carlo Error decaying as O(1/sqrt(M)); a non-vacuous PAC-Bayes bound with train-test gap of 0.0085 at N=4200; operation within 1.12x of the information-theoretic lower bound; graceful degradation as O(epsilon*delta*sqrt(K)) under corruption, maintaining 88% performance with half of evidence adversarially replaced; O(1/sqrt(K)) calibration decay with R^2=0.849; and exact epistemic-aleatoric uncertainty decomposition with error below 0.002%. All theorems are empirically validated on controlled datasets spanning up to 4,200 training examples. Our theoretical framework establishes LPF as a foundation for trustworthy multi-evidence AI in safety-critical applications.
Authors: Andrew Qing He, Wei Cai
Abstract: In this paper, we extend the Weak Adversarial Neural Pushforward Method to the Fokker--Planck equation on compact embedded Riemannian manifolds. The method represents the solution as a probability distribution via a neural pushforward map that is constrained to the manifold by a retraction layer, enforcing manifold membership and probability conservation by construction. Training is guided by a weak adversarial objective using ambient plane-wave test functions, whose intrinsic differential operators are derived in closed form from the geometry of the embedding, yielding a fully mesh-free and chart-free algorithm. Both steady-state and time-dependent formulations are developed, and numerical results on a double-well problem on the two-sphere demonstrate the capability of the method in capturing multimodal invariant distributions on curved spaces.