Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning

Thursday 30 July

Machine Learning · Cross-listed from cs.CL

Causal Discovery with Inverted Self-attention for Multivariate Time Series

Yusen Liu, Yong Wang, Yifan Yin et al. (+3 more)

Causal discovery in multivariate time series data is challenging due to complex interactions, high dimensionality, and nonlinear dependencies among variables. Existing methods often struggle to capture these complexities, resulting in inaccurate causal structures. To address this issue, we propose a novel framework that leverages self-attention mechanisms within the transformer architecture for causal discovery. Our approach introduces a novel inverted causal self-attention mechanism (CSAM) that emphasizes latent and indirect causal relationships by inverting tokens and inducing sparsity in attention scores, focusing on significant causal interactions and reducing spurious correlations. Additionally, we develop a global causal algorithm to identify global causal links, providing a holistic metric for causal influence, along with a causal verification module to ensure robustness in the identified causal relationships, enhancing the reliability of our framework. Experiments on both linear and nonlinear datasets, along with ablation studies and sensitivity analyses, show that our framework outperforms existing methods, demonstrating its potential for causal discovery in complex multivariate time series.
Read the full abstract

All authors Yusen Liu, Yong Wang, Yifan Yin, Tianqing Zhu, Xiufeng Liu, Huan Huo

Machine Learning · Cross-listed from cs.CR

Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data

Pouya Rajabi and Mohsen Toorani

Federated learning enables multiple institutions to collaboratively train a shared model without exchanging their raw data. However, individual model updates are data-dependent and may reveal information about clients' local training data. This paper presents a privacy-preserving federated learning framework for clinical EEG data that uses masking-based secure aggregation as its core protection mechanism. The framework combines graph-based communication, threshold secret sharing, dropout recovery, local update clipping, an optional Bloom filter-based privacy-preserving record-linkage initialization module, and auxiliary-notary-based verifiability. It supports semi-honest and malicious aggregation settings and is implemented using the Flower federated learning framework. The secure aggregation variants are evaluated in a simulated cross-silo healthcare setting using TUH EEG-derived data under different client configurations. Under the stated assumptions, the secure variants hide individual updates from the aggregation server. The results show that these variants remain compatible with federated model training, although malicious-setting safeguards and lightweight consistency-checking mechanisms introduce additional computation, communication, and round-duration overhead. Among the proposed secure configurations, the base semi-honest variant incurs the lowest overhead; the malicious-server variants add protocol-consistency and authenticity safeguards, and the auxiliary-notary variants add lightweight aggregate-consistency checking.
Read the full abstract

Machine Learning

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks

Mostafa Haghir Chehreghani

Oversmoothing is a fundamental limitation of deep graph neural networks (GNNs), where repeated message passing causes node representations to become increasingly similar, eventually collapsing toward a low-dimensional subspace. This phenomenon limits the effective depth of message-passing architectures and motivates the search for mechanisms that preserve representation diversity. In this paper, we study a recurrent graph neural network in which independent Gaussian noise is injected after every propagation step and analyze the resulting architecture as a stochastic dynamical system. Under a standard global contraction assumption on the deterministic update, we prove that the hidden representations form a geometrically ergodic Markov chain admitting a unique invariant probability measure. Our main theoretical result establishes an explicit positive lower bound on the expected stationary Dirichlet energy, proportional to both the noise variance and the spectral gap of the underlying graph. Consequently, the stationary representations cannot collapse onto the constant manifold, providing a rigorous guarantee that asymptotic oversmoothing is prevented in the sense of non-vanishing Dirichlet energy. Our analysis reveals persistent stochastic perturbations as a fundamentally different mechanism for combating oversmoothing, complementing existing deterministic approaches based on residual connections, normalization, and graph rewiring. Finally, numerical experiments on both linear and nonlinear recurrent graph neural networks closely match the theoretical predictions, illustrating the emergence of a stationary distribution and the predicted dependence of the limiting Dirichlet energy on the noise intensity.
Read the full abstract

Machine Learning

Multi-channel Uplift Policy Learning

Changjian Liu, Tianyu Wang, Xiaoxuan Deng et al. (+7 more)

E-commerce platforms must allocate fixed marketing budgets across multiple channels to maximize business utility. However, standard predict-then-optimize (PTO) paradigms fail in this compositional space due to observational confounding and severe extrapolation. We formulate this challenge as a simplex-constrained uplift decision problem and propose ReAlloc, a fast-slow causal framework. Specifically, an agile Orthogonal Teacher extracts unbiased local gradients from short-term logs, while an Explanation-Guided Student distills them into a structured marginal field over long-term horizons. This design enables support-aware, conservative decisions that capture cross-channel substitutions. Extensive simulations and large-scale online A/B tests on Taobao platform demonstrate that ReAlloc achieves simultaneous lifts in both pay order and income.
Read the full abstract

All authors Changjian Liu, Tianyu Wang, Xiaoxuan Deng, WenTao Zhu, Yuwei Xu, Jungqi Jin, Yong Gao, Chuan Yu, Jian Xu, Bo Zheng

Machine Learning

Search Strategies for Optimal Classification and Regression Trees

Jacobus G. M. van der Linden, Mim van den Bos and Emir Demirović

Optimal decision trees (ODTs) are compact, interpretable machine learning models that globally optimize a given objective, but their scalability remains challenging. While recent work has proposed a variety of search strategies to improve scalability, the precise contribution of each strategy remains unclear. To address this gap, we introduce a general algorithmic framework for ODTs that instantiates previously used search strategies and enables the definition of new ones. This provides a common lens through which to understand and compare different strategies, which we use to empirically investigate the effect of 18 search strategies. Compared to the state of the art, the best strategy in our evaluation achieves significantly better anytime performance for classification, and improves runtime by more than an order of magnitude for regression.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study

Longxia Gao, Linan Wang, Yuhe Han et al. (+3 more)

Deep learning has shown promise for automated tongue diagnosis in traditional Chinese medicine (TCM), yet the design space remains underexplored. We conducted a systematic ablation study spanning 20+ model versions under rigorous 5-fold cross-validation on TongueDx2 (5,109 images, 976 expert-annotated) and a merged dataset of 11,101 samples. We compared six backbone architectures, four loss functions, five augmentation strategies, and six training strategies. The best 976-sample model achieved weighted-F1 of 0.6625 using ConvNeXt-Tiny with restrained augmentation and weak-group ensemble, while the best 11,101-sample model reached weighted-F1 of 0.7761. Six key design principles emerged: (1) ConvNeXt-Tiny offers optimal parameter efficiency; (2) BCE substantially outperforms Asymmetric Loss (+2.7%); (3) restrained color augmentation is critical; (4) weak-group ensemble replacement (+2.1%) outperforms probability averaging; (5) data scaling yielded +20.6% improvement; (6) expanding from 13 to 45 label dimensions caused catastrophic collapse (0.78 to 0.22). These principles are generalizable to multi-label medical image classification with class imbalance.
Read the full abstract

All authors Longxia Gao, Linan Wang, Yuhe Han, Junze Geng, Meng Zhang, Hanqing Zhao

Machine Learning

LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning

Mohand Mezmaz and Grégoire Danoy

Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for a fixed problem class-incurring high pretraining costs and generalizing poorly outside the training distribution. We propose an alternative: a metaheuristic framework that reformulates the randomized constructive phase of GRASP as an online imitation learning task, trained from scratch on each problem instance. A local search procedure acts as an expert oracle, while a decoder-only Transformer serves as the constructive policy. Unlike classical GRASP, which relies on static, myopic heuristic rules based on localized scalar costs, our approach is fully data-driven: the construction policy emerges from high-quality solutions discovered during the search itself, with no problem-specific feature engineering required. We instantiate this as LM-GRASP, a hybrid metaheuristic following an iterative learn-infer-improve cycle, training the policy online via behavioral cloning on a dynamic archive of elite trajectories-no external data or offline pretraining needed. The pipeline interfaces with the domain solely through the objective evaluator used by local search. Evaluated on the Taillard PFSP benchmark (ta51-ta60), the most discriminating block due to half its optima being unknown, LM-GRASP outperforms GPU-GRASP by 28.4 makespan units on average-comparable to the gain from GPU acceleration over sequential execution (27.2 units), though with overlapping standard deviations. This suggests instance-specific, online-trained language models are a promising, practical alternative to hand-engineered constructors, especially for landscapes resistant to classical greedy construction.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement Learning

Giorgos Iacovides, Wuyang Zhou and Danilo Mandic

Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to a market-agnostic, supervised learning paradigm that relies on limited, static and human-annotated datasets, and thus are incapable of adapting to evolving market conditions. To address this limitation, we introduce FinSMART, the first market-aligned reinforcement learning framework for financial sentiment analysis, which directly optimizes sentiment signals using realized market outcomes. To deal with the noisy, non-stationary, and multifactorial nature of financial markets, FinSMART incorporates a signal extraction pipeline that combines market-aware data filtering with a discrete asymmetric trading reward, enabling stable reinforcement learning from economically meaningful market feedback. Experimental results demonstrate that FinSMART significantly outperforms existing state-of-the-art methods in profitability, risk-adjusted performance, and sentiment signal quality, improving cumulative trading returns by 220% over the strongest baseline. Uniquely, the FinSMART framework naturally supports market-aware retraining, at any point in time, by replacing costly manual annotation with newly observed financial articles and their realized market outcomes. Such a retraining strategy enables the model to continuously adapt to changing market dynamics, resulting in consistent performance gains over its static counterpart. These findings demonstrate the practical applicability of market-aligned reinforcement learning and highlight its potential as a next-generation paradigm for developing adaptive financial LLMs.
Read the full abstract

Machine Learning

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

Xu Zheng, Wei Cheng, Zhuomin Chen et al. (+3 more)

As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves. Although existing interpretable-by-design forecasters reveal their internal structures, they offer no guarantee that these structures faithfully reflect the underlying evidence driving the predictions. In contrast, while faithfulness-oriented methods explicitly verify model behavior, they are almost exclusively designed for post-hoc classification tasks. To bridge this gap, we propose IB-Forecast, an inherently interpretable multivariate time-series forecasting framework. It decomposes forecasting into a learned periodic component and a residual component computed with explainable masks over input tokens. With a budget-constrained information bottleneck, end-to-end optimization enables users to directly control explanation sparsity. With a rigorous faithfulness evaluation protocol, extensive experiments demonstrate that IB-Forecast matches the forecasting error of leading black-box models while providing faithful explanations at no additional inference cost. Furthermore, under a matched sparsity budget, these native explanations consistently surpass gradient-based, occlusion-based, and optimization-based baselines across all evaluated datasets. Ultimately, whereas the native explanations of existing interpretable forecasters exhibit poor faithfulness, IB-Forecast guarantees high explanation fidelity, requiring only 14-20% of the observations to deliver low-error predictions.
Read the full abstract

All authors Xu Zheng, Wei Cheng, Zhuomin Chen, Mo Sha, Jingchao Ni, Dongsheng Luo

Machine Learning

From Expert Reduction to Behavioral Divergence: Tracing Numerical State through Sparse MoE Inference

Tianyang Zhu

Mathematically equivalent expert-reduction orders can produce observably different sparse-MoE executions. We isolate this effect in native DeepSeek-V4-Flash by freezing local MoE state and varying only aggregation semantics. Four schemes separate operand representation from accumulator precision. At one layer-5 fork, 720 A-mode orders yield 10 continuation basins; 720 B-mode orders form 360 exact structural classes and 11 basins. Under one Chinese prompt, the B classes split into 202 layoffs, 113 hiring, and 45 other continuations. Maximum-L-infinity B-branch selection separates 12, 24, and 36 of 50 prompts by 8, 16, and 32 tokens. Across 192 persistent trajectories per scheme, P32, A, and B change every native-reference route trajectory, while C preserves routes, token sequences, and texts. A separate 192-trajectory C check matches native MoE, post-mHC, next-router, and LM states bitwise. For one controlled B branch, exact post-mHC endpoint reconstruction reproduces the measured downstream trajectory. At the next decode boundary, exact FP64 reconstruction of the branch's full persistent state yields agreement for 301 downstream post-mHC states, 301 persistent-state checkpoints, 301 routes, predictions, and text over seven steps, given the same naturally generated next input. These controls identify post-mHC as an intra-token boundary and full persistent state as a cross-token continuation boundary. Identical tokens need not imply identical autoregressive state: divergence can survive a token boundary and become visible later. These results make expert operand conversion, accumulator precision, and reduction order part of a numerical compatibility contract for sparse-MoE runtimes and hardware backends. They establish controlled causal possibility, not deployment incidence; C's order invariance is limited to evaluated six-term states and schedules.
Read the full abstract

Machine Learning · Cross-listed from physics.ao-ph

Meteosat Third Generation imagery improves CNN-based SSI retrieval

Gordei Pribõtkin, Piia Post and Velle Toll

Accurate Surface Solar Irradiance (SSI) estimation is increasingly important for photovoltaic energy monitoring and forecasting. The recently introduced Meteosat Third Generation (MTG) satellite constellation provides imaging data with higher spatial resolution compared to the Meteosat Second Generation (MSG) satellite constellation, but its benefits for machine-learning-based SSI retrieval have not been well established. In this work, we introduce a multi-imager and multi-resolution convolutional neural network architecture for 10-minute SSI retrieval over Northern Europe (Estonia) using MSG/SEVIRI and MTG/FCI satellite imagery together with solar-geometry and clear-sky irradiance features. Model performance is evaluated against ground-based pyranometer measurements from eight Estonian meteorological stations using site-based cross-validation and multiple training seeds. Model performance is also compared with the SARAH-3 physics-based satellite SSI product. The hybrid SEVIRI-FCI model significantly outperformed the SEVIRI-only model under overcast and cloudy conditions, reducing RMSE by 8.2 W m$^{-2}$ and 5.7 W m$^{-2}$, respectively. However, under partly cloudy or clear skies, no statistically significant difference in RMSE was observed between the SEVIRI-FCI hybrid and the SEVIRI-only models. Compared with physics-based SARAH-3, the hybrid model yielded skill scores of 35 % under overcast conditions, 21 % under cloudy conditions, and 20 % overall. Furthermore, both models underperformed SARAH-3 in clear-sky conditions. These results show that higher-resolution MTG/FCI imagery improves CNN-based SSI retrieval when clouds dominate irradiance variability, but also indicate that higher spatial resolution alone is insufficient to address clear-sky limitations in machine-learning-based SSI retrieval.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

On a joint simultaneous learning of relevant feature subsets and subspaces in regression-like problems

Illia Horenko

We extend a recently introduced Entropy-Optimal Manifold Clustering (EOMC) to allow for a joint simultaneous identification of subsets and subspaces of relevant features in nonstationary and nonlinear regression problems. It is shown that the proposed extension - that we coin as Entropy-Optimal Manifold Regression (EOMR) - allows a robust learning with linearly-scaling iteration and memory complexities. EOMR is compared to the most complete set of state-of-the-art tools from the Artificial Intelligence (AI) and Machine Learning (ML) that is available to the author, on the very challenging problems from chaotic and fluid dynamics: (i) on predicting the Lorenz-96 systems dynamics in strongly- and very-strongly chaotic regimes (with forcing parameter being $F=8$ and $F=12$, respectively); and, (ii) on a data from the Hasegawa-Wakatani model on the edge of the tokamak plasma. It is demonstrated that the proposed benchmarks (i) and (ii), indeed, are the very challenging problems for the state of the art ML and AI tools - since both the general-purpose gradient boosted random forests and deep neuronal networks, as well as transformer-based AI tools like TabPFN v.03 (more spezialised for large-dimensional small data learning problems) - result in orders of magnitude inferior root mean squared prediction errors, and orders of magnitude larger model complexities, when compared to the EOMR. For a Hasegawa-Wakatani example, EOMR distills a very simple entropy-optimal and skilful description of the leading Essential Orthogonal Function (EOF) dynamics, given by linear, causal and weakly-stationary autoregressive process described by just 8 parameters.
Read the full abstract

Machine Learning

Chem World: A Large-Scale Benchmark and Physics-Informed Framework for Trustworthy Chemical Property Prediction

Tianyou Bai, Huan Wang, Mingchen Gao et al. (+4 more)

Chemical property prediction plays a critical role in accelerating scientific discovery in chemistry, materials science, and drug development. However, existing benchmarks often suffer from limited task diversity, fragmented datasets, and inconsistent evaluation protocols, making it challenging to systematically assess the reliability and generalization of AI models. In this work, we introduce Chem World, a comprehensive benchmark for chemical property prediction that integrates 17 diverse chemical datasets with over 800,000 molecular samples, covering various properties including density, electrical conductivity, solubility, and other molecular characteristics. Chem World provides a unified platform for evaluating AI models across multiple property prediction tasks. Furthermore, we propose Mixture-PINN, a physics-informed neural network based prediction framework that incorporates chemical prior knowledge into data-driven learning, improving the accuracy, robustness, and reliability of chemical property prediction. Extensive experiments on Chem World demonstrate the effectiveness of our approach compared with existing methods. By combining large-scale standardized evaluation with physics-informed learning, Chem World establishes a foundation for developing trustworthy AI systems for computational chemistry and advancing AI-driven scientific discovery.
Read the full abstract

All authors Tianyou Bai, Huan Wang, Mingchen Gao, Fangyue Lin, Pinze Ren, Zhenlin Zhao, Siming Dong

Machine Learning · Cross-listed from cs.AI

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

Binbin Zheng, Zijun Xie, Guanqun Zhao et al. (+4 more)

Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recurring mistakes, and incidental choices entangled in the same outcome signal. Existing agentic self-distillation methods enrich sparse supervision with natural-language skills, but skills retrieved externally or extracted from a single trajectory by stronger models may mismatch current experience, exceed the policy's capability, or remain path-specific. We propose Group-Reflective Self-Distillation (GRSD), which derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts. For each prompt, the policy reflects on each verified trajectory in an on-policy group, and a stop-gradient snapshot contrasts the resulting reflections from successful and failed rollouts to construct group-level privileged guidance. Conditioned on this guidance, a self-teacher refines turn-level credit assignment by modulating outcome-based advantages while preserving the verifier-determined learning direction. Experiments across multiple agentic environments and model scales demonstrate that GRSD consistently outperforms competitive baselines and generalizes more effectively to unseen tasks.
Read the full abstract

All authors Binbin Zheng, Zijun Xie, Guanqun Zhao, Enlei Gong, Xing Ma, Xiaoliang Fu, Zeyu Chen

Machine Learning · Cross-listed from cs.AI

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Yash Pandya, Sahil Gupta, Sarthak Harne et al. (+10 more)

Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and stateful, so synthetic environments stand in for them. Recent pipelines generate such environments in bulk, which moves the bottleneck from how many exist to what is inside each one. The returns, we find, come from three properties: how much behavioural depth an environment carries, whether it targets the interaction an agent actually fails, and whether it improves alongside the model. We present Echoverse, which compiles specifications into stateful applications whose tasks are graded against the application's own database, and a co-evolution loop that reads every graded rollout twice: as repairs to the environment, its tasks and its verifier, and as training signal for the model. Trained on twelve such environments, a 9B model improves from $36.5\%$ to $67.1\%$ across fourteen evaluation splits, within fourteen points of the much larger frontier model that taught it. We examine each property in turn. On the same domains, shallow environments push live-site accuracy below the base model ($80.0 \to 75.0$) while deep ones raise it ($80.0 \to 85.0$ and $48.0 \to 65.0$); drilling one interface control across many renderings transfers to held-out widget families and to the open web; and repairing a single environment lifts the model trained on it from $16.2\%$ to $38.5\%$. The same worlds serve as reinforcement-learning environments, where a reward combining the grounded verifier with a dense per-step judge raises held-out score from $58.8\%$ to $68.0\%$. We release four environments as a benchmark, with their applications, seed data and grounded graders. Code: https://aka.ms/echoverse
Read the full abstract

All authors Yash Pandya, Sahil Gupta, Sarthak Harne, Archana Yadav, Kavyansh Chourasia, Hussein Mozannar, Vibhav Vineet, Sara Abdali, Corby Rosset, Yash Lara, Ahmed Awadallah, Ece Kamar, Akshay Nambi

Machine Learning

GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios

Yiming Xu, Jihua Kang, Chunsai Du et al. (+5 more)

In demanding professional environments and meeting review scenarios, lengthy text often imposes a high cognitive load. To facilitate efficient information communication, transforming verbose text into logically clear diagrams is essential. Scalable Vector Graphics (SVG) provide an effective representation for this purpose due to their editability and resolution independence. However, current research on Text-to-SVG generation remains hindered by three major challenges: (1) the scarcity of datasets for complex, logic-rich diagrams; (2) the absence of explicit layout priors, which leads to chaotic spatial arrangements; and (3) the lack of fine-grained visual feedback to validate rendered outputs and correct aesthetic defects. To address these challenges, at the data level, we introduce DocMeetSVG-100K, a large-scale SVG dataset tailored for document authoring and meeting review scenarios. At the model level, we propose GVR-Coder, a novel framework designed to generate high-quality logical diagrams from lengthy professional texts. Specifically, we adopt a curriculum-driven rejection sampling fine-tuning to progressively enhance the model's capability in modeling complex structures, while explicitly incorporating layout constraint knowledge during training. In addition, we introduce reinforcement learning from dual rendering feedback, a mechanism that provides implicit feedback through reward signals to jointly optimize structural complexity and visual aesthetics. Furthermore, we design a generate-verify-repair agent loop, which improves generation quality through explicit, fine-grained feedback and targeted refinement. Extensive experiments demonstrate that GVR-Coder outperforms competitive baselines and reliably produces logically coherent and visually appealing diagrams. Code and data are available at https://github.com/CurryaNa/GVR-Coder.
Read the full abstract

All authors Yiming Xu, Jihua Kang, Chunsai Du, Qifan Zhang, Wangqiu Zhou, Yiting Wu, Tianqi Li, Qi Song

Machine Learning · Cross-listed from cs.GR

A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes

Alper Sahistan, Haichao Miao, Zhimin Li et al. (+3 more)

Time-varying implicit neural representations (INRs) provide a compact representation of scientific volumes and, for modalities such as dynamic X-ray computed tomography (CT), are often the only practical way to represent the data. However, interactive volume rendering of INRs is challenging, as cheap memory lookups are replaced by expensive neural inferences, hindering the performance. Therefore, conventional volume rendering methods such as ray marching with dense sampling are often impractical. While resampling, caching, and retraining can mitigate this cost, they compromise convenience and accuracy and become impractical for time-varying data. We tackle these challenges using a query-efficient stochastic volume rendering framework based on delta tracking. Our system employs a four-stage pipeline that exploits heterogeneous parallelism, using ray tracing cores for traversal and tensor cores for batched neural evaluation. Furthermore, we present strategies to reduce INR queries via ray budgeting and query pruning, thereby increasing per-frame performance. Using our renderer, many time-varying INRs can be rendered directly from their original representation. The system achieves ~30-40 FPS at 1024x1024 resolution on an RTX 4090 GPU and converges to high-fidelity images. Moreover, the system enables interactive temporal exploration of the continuous domain, with timestep updates taking approximately 1-2 ms.
Read the full abstract

All authors Alper Sahistan, Haichao Miao, Zhimin Li, Peer-Timo Bremer, Joshua A Levine, Valerio Pascucci

Machine Learning

ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents

Xingjian Wu, Xuhang Zhu, Xingchen Liu et al. (+6 more)

As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks. In this work, we present ClawTrack, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score). ClawTrack comprises 320 tasks across 8 domains with 25+ deterministic mock services. A Process Grader scores each reasoning turn along four dimensions (goal alignment, efficiency, information utilization, and result verification), anchored by 12,541 task-specific rubric items. Evaluating 21 models over 16,000+ trials, we find that: (1) process scores effectively attribute success and failure to specific reasoning dimensions, filtering lucky passes invisible to outcome-only evaluation; (2) the four dimensions are complementary, with result verification as the systematic bottleneck; (3) the framework is robust to evaluator choice across different judge LLMs; and (4) process-based trajectory filtering yields consistent post-training improvements across model scales.
Read the full abstract

All authors Xingjian Wu, Xuhang Zhu, Xingchen Liu, Junlin Liu, Jianing Wang, Linsen Guo, Xiaoyu Li, Xuezhi Cao, Xunliang Cai

Machine Learning

Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers

Rémy Vallot, Florian de Vuyst, Thibault Dairay et al. (+1 more)

It is well known that Newton's method converges faster when the initial guess is closer to a root of a system of nonlinear equations. In this paper, a two-stage Newton initial guess strategy is proposed by learning features from a parameter-space sampling and a database of precomputed solutions. The method uses discrete Newton trajectories to construct two complementary reduced spaces: a solution feature space, built from converged states, and a corrective search direction feature space, built from intermediate Newton increments. For an unseen parameter, a regression model is used to predict a surrogate solution approximation. Then, in a second step, a residual-minimizing correction is computed using a dedicated GMRES-based approach. The resulting state is then used as an initial guess for the high-fidelity Newton method, which completes convergence. The corrective step is computationally inexpensive since it only requires residual evaluations and the solution of a small least-squares problem. The methodology is weakly intrusive once the high-fidelity residual fields and a script-based programming interface are available. This strategy reduces the number of Newton iterations and decreases the overall CPU time. Numerical experiments on representative PDE problems show quantifiable speedups compared with standalone surrogate initialization. Significant speedups are observed. This generic approach can be applied to a broad class of large-scale nonlinear problems.
Read the full abstract

All authors Rémy Vallot, Florian de Vuyst, Thibault Dairay, Mathilde Mougeot

Machine Learning

Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

Tianen Shen, Zhengyu Li, Yutong Li et al. (+4 more)

Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental sensing. Their core challenges stem from asynchronous observations, non-uniform sampling intervals, and the fact that temporal patterns themselves carry critical dynamic information. Existing approaches either rely on discretization-based preprocessing (e.g., interpolation, imputation, or aggregation), which disrupts the underlying continuous-time semantics, or adopt continuous-time modeling via ODE-based frameworks, which typically require specialized architectures and incur substantial computational overhead due to numerical solvers. To address these limitations, we propose WrapFlow, a continuous-time modeling framework for irregular time series forecasting. On the input side, WrapFlow introduces Continuous-Time Tokenization, which directly encodes raw observation events and explicitly models long unobserved intervals via gap-aware tokens. The resulting continuous-time tokens are then processed by a standard Transformer backbone to capture long-range temporal dependencies. On the output side, we develop a simulation-free training paradigm for Residual Flow Matching, which learns conditional residual vector fields around base predictions while avoiding numerical-solver simulation and backpropagation during training. This design enables high-quality continuous forecasting using only a small number of fixed rollout steps at inference. Extensive experiments on multiple real-world datasets demonstrate that WrapFlow achieves state-of-the-art performance.
Read the full abstract

All authors Tianen Shen, Zhengyu Li, Yutong Li, Xiangfei Qiu, Xingjian Wu, Bin Yang, Jilin Hu

Machine Learning

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

Xingjian Wu, Junlin Liu, Xingchen Liu et al. (+6 more)

Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher. In multi-turn agentic settings, this leads to reasoning route convergence and the loss of clear optimization directions. To tackle these challenges, we introduce Contrastive Reinforced Policy Optimization (CRPO), which reformulates agentic OPSD from a contrastive learning perspective. By leveraging predictive entropy to distinguish between positive positions (reflective exploration) and negative positions (exposure bias), CRPO conducts group-wise contrast to preserve reliable, fine-grained optimization signals. Extensive evaluations across 13 challenging reasoning and deep-search benchmarks demonstrate that CRPO consistently outperforms existing reinforcement learning and self-distillation baselines, significantly enhancing training stability and generalization in long-horizon interactions.
Read the full abstract

All authors Xingjian Wu, Junlin Liu, Xingchen Liu, Xuhang Zhu, Jianing Wang, Linsen Guo, Xiaoyu Li, Xuezhi Cao, Xunliang Cai

Machine Learning

Flux-OPD: On-Policy Distillation with Evolving Contexts

Yuran Wang, Zekun Wang, Bohan Zeng et al. (+10 more)

Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts derived from task feedback can provide richer supervision, yet fixed contexts cannot adapt as the student evolves, motivating contexts that evolve with student performance. However, directly using evolving contexts as in-training supervision results in unstable distillation targets and conflicting distributions, requiring mechanisms to stabilize the target and downweight conflicts. In this paper, we characterize context distillation through a reverse-KL decomposition, showing that the student is distilled toward the geometric mean of context-conditioned teachers, while the objective contains a conflict term measuring disagreement among these teachers. Motivated by this characterization, we propose Flux-OPD, an OPD paradigm that uses evolving contexts as in-training supervision to incorporate contextual signals derived from task feedback. Flux-OPD treats differences between context-conditioned and context-free teachers as contextual difference signals, injects them as contextual corrections into the context-free teacher, and weights the correction strength using the conflict term. Experiments show that Flux-OPD achieves the best results among OPD paradigms, highlighting the potential of combining teacher supervision with evolving contexts as in-training supervision.
Read the full abstract

All authors Yuran Wang, Zekun Wang, Bohan Zeng, Ruixu Zhang, Wenxuan Liu, Liu Yang, Yifan Dai, Yang Shi, Bozhou Li, Chengzhuo Tong, Daili Hua, Yuanxing Zhang, Wentao Zhang

Machine Learning

Building a User Foundation Model for the Open Web

Solal Vernier, Ivan Can Arisoy, Merwan Barlier et al. (+1 more)

User foundation models have demonstrated strong results in e-commerce and social recommendation, but most industrial deployments assume environments where user identity is stable and persistent. Open-web real-time bidding (RTB) operates on a structurally different data distribution: user identity is fragmented and non-persistent across browsing sessions, and the availability of browsing history depends on user privacy choices. Consequently, a significant portion of traffic carries no historical data, and available records often consist of relatively short, disjointed sessions. As a result, historical signals in this domain are typically represented as aggregated counters and recency buckets, leaving the sequential structure unexploited. To address this limitation, we present a user foundation model that applies self-supervised learning on user browsing histories and show that the learned representation improves multiple downstream production tasks, demonstrating the viability of this approach on the open web. We pre-train a Transformer encoder with masked language modeling and a sequence-level contrastive objective, then fine-tune it on the click prediction task. We optimize the encoder's pre-training pipeline with an LLM-in-the-loop search over a curated catalog of reviewable, code-level edits (lifters), instantiating the LLM-as-optimizer paradigm in an industrial setting. The same encoder representation yields +1.197% RIG on the production bid win-rate model and +1.354% RIG on the production CTR ranker; a 7-day live A/B test confirms +2.13% CTR, -1.13% eCPC (80% CI excluding zero on both metrics).
Read the full abstract

All authors Solal Vernier, Ivan Can Arisoy, Merwan Barlier, Blaž Škrlj

Machine Learning · Cross-listed from stat.ML

The Noise Premium in Adversarial Training for Kernel Regression

Yiling Xie and Xiaoming Huo

Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency. We study this trade-off in kernel regression over a reproducing kernel Hilbert space (RKHS). It is shown that, under squared loss, adversarial training in RKHS introduces a term involving the product of the function norm with the mean absolute value of the response noise, which we call the noise premium. Our analysis shows that the noise premium makes the prediction error of adversarial training converge strictly more slowly than the nonparametric minimax benchmark even after balancing approximation and estimation errors. Moreover, for a fixed perturbation budget, once the budget exceeds a certain threshold, the solution to adversarial training collapses to the zero function. To mitigate these effects of the noise premium, we propose noise-debiased adversarial training. The resulting noise-debiased estimator can attain the minimax optimal rate up to a logarithmic factor for the prediction error, raises the collapse threshold, and admits an explicit bound on the increase in adversarial loss. Numerical experiments on synthetic and real data support the theoretical findings and validate the effectiveness of the proposed noise-debiased method.
Read the full abstract

Machine Learning · Cross-listed from cs.CR

Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks

Spyridon Raptis and Haralampos-G. Stratigopoulos

Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on neuromorphic hardware and motivating their use in always-on, battery-powered edge systems. We show that this same efficiency advantage creates a distinct security risk: sponge attacks can increase inference-time spike activity and synaptic workload, inflating energy consumption while remaining difficult to detect through correctness-based monitoring alone. Prior input-space efficiency attacks on SNNs have focused on per-sample optimization, primarily in rate-coded settings. We extend this threat to native event-based binary inputs and study two attack models. First, we develop a per-sample sponge attack that crafts a custom adversarial spike train for each input via gradient-based optimization. This attack increases per-inference SynOps by 1.5-2.6x on three SNN models for the NMNIST, SHD, and IBM DVS Gesture datasets, while preserving the predicted class on at least 98% of evaluated samples. Second, to the best of our knowledge, we introduce the first universal sponge attack for native event-based SNN inputs: a fixed binary perturbation computed offline and applied via XOR to all subsequent inputs. Although weaker, it still inflates SynOps by 1.09-1.24x across all three datasets and represents a more realistic deployment threat because it requires no per-input optimization. Mapping SynOp inflation to estimated Loihi-1 energy yields per-inference overheads from 14 $\mu$J to 13.24 mJ. These results show that native event-based SNNs are vulnerable to practical input-space efficiency attacks, and that reusable universal perturbations can accumulate into meaningful battery drain in continuously deployed edge systems.
Read the full abstract

Machine Learning

It's All Just Vectorization: einx, a Universal Notation for Tensor Operations

Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner et al. (+1 more)

Tensor operations represent a cornerstone of modern scientific computing. However, the Numpy-like notation adopted by predominant tensor frameworks is often difficult to read and write and prone to so-called shape errors, i.a., due to following inconsistent rules across a large, complex collection of operations. Alternatives like einsum and einops have gained popularity, but are inherently restricted to few operations and lack the generality required for a universal model of tensor programming. To derive a better paradigm, we revisit vectorization as a function for transforming tensor operations, and use it to both lift lower-order operations to higher-order operations, and conceptually decompose higher-order operations to lower-order operations and their vectorization. Building on the universal nature of vectorization, we introduce einx, a universal notation for tensor operations. It uses declarative, pointful expressions that are defined by analogy with loop notation and represent the vectorization of tensor operations. The notation reduces the large APIs of existing frameworks to a small set of elementary operations, applies consistent rules across all operations, and enables a clean, readable and writable representation in code. We provide an implementation of einx that is embedded in Python and integrates seamlessly with existing tensor frameworks: https://github.com/fferflo/einx
Read the full abstract

All authors Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner, Michael Arens

Machine Learning

Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness

Kağan Akman, Naci Saldi and Serdar Yüksel

We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probability laws on pairs of empirical input-output measures, allowing us to interpret the training problem as a finite-horizon Markovian control problem. We then analyze a quantized model, derived by quantizing the state, action, and measure-state spaces, and derive explicit finite-sample generalization bounds using concentration inequalities for empirical laws on finite metric spaces together with a Lipschitz stability estimate for the value function. These bounds are transferred to the base model at the cost of an explicit approximation error. Finally, we show that the same machinery yields a distributionally robust control formulation of the training problem, connecting Transformer generalization to Wasserstein distributionally robust optimization.
Read the full abstract

Machine Learning

TAPO: Transition-Aware Policy Optimization for LLM Agents

Cong Li, Peixi Peng, Yisen Zhao et al. (+4 more)

Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents. However, existing methods predominantly rely on sparse task rewards for policy optimization, failing to fully exploit another class of inherently dense supervisory signals naturally present during online interaction: environmental feedback following action execution. Recent theoretical studies suggest that generalization in multi-step, goal-oriented tasks hinges on predictive knowledge of environmental consequences. Inspired by this, we propose TAPO: Transition-Aware Policy Optimization for LLM Agents, a unified training framework that alternates between policy optimization and transition supervision. Beyond standard RL updates, TAPO repurposes rollout data to apply action-conditioned next-observation prediction supervision on a shared backbone model. This approach enhances the model's sensitivity to environmental transition dynamics and action consequences while concurrently optimizing the policy. It serves as a computationally lightweight, plug-and-play enhancement module for existing agent RL algorithms, requiring no additional expert data, extra sampling costs, or inference-time overhead. We conduct systematic experiments on WebShop and ALFWorld, integrating foundation models of various scales with different policy optimization algorithms. Empirical results demonstrate that TAPO consistently improves task performance over pure policy optimization baselines.
Read the full abstract

All authors Cong Li, Peixi Peng, Yisen Zhao, Xinyu Hu, Shudong Liu, Zhan Su, Zhuojian Li

Machine Learning

Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning

Efstratios Zaradoukas, Davide Gabrielli, Bardh Prenkaj et al. (+1 more)

Machine unlearning seeks to selectively remove specific knowledge from trained language models without full retraining, a growing necessity under privacy regulations such as GDPR and the EU AI Act. Recent work has reformulated unlearning as a Reinforcement Learning with Verifiable Rewards (RLVR) problem, where models are optimized against verifiable rewards computed directly from their outputs. However, existing methods rely on sparse binary rewards that provide minimal learning signal, indicating only whether forbidden content was avoided, and limiting convergence speed. In this paper, we study how reward design affects unlearning efficiency within the Reinforcement Unlearning (RUL) framework. We introduce a principled reward decomposition framework that decouples verifiability from sparsity, and propose two new reward functions: an exponential reward that provides graded penalties based on the count of forbidden-concept occurrences, and a PageRank inspired reward that weights penalties by semantic importance. We conduct experiments on the Real World Knowledge Unlearning (RWKU) benchmark, demonstrating that both rewards consistently outperform the binary setting, while reaching similar forgetting performance up to $3\times$ faster and preserving general model utility. Our results show that reward design is a key driver of unlearning efficiency offering a practical path toward scalable and efficient machine unlearning.
Read the full abstract

All authors Efstratios Zaradoukas, Davide Gabrielli, Bardh Prenkaj, Gjergji Kasneci

Machine Learning

What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models

Dongxiao He, Siqi Liu, Jitao Zhao et al. (+3 more)

Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for general-purpose graph learning, aiming to learn reusable knowledge that generalizes across diverse graph domains and downstream tasks, reducing the need for specific model development. Achieving this goal requires reconciling the substantial heterogeneity in node features, graph structures, and semantic information across domains. Among them, heterogeneous node features constitute a fundamental input-level barrier, as their dimensionality and semantics vary substantially across datasets. Existing studies typically project or map heterogeneous node features into a fixed-dimensional space, often implicitly equating dimensional uniformity with effective feature unification. Yet dimensional consistency alone does not ensure that the unified features preserve informative semantics and capture transferable patterns that can support cross-domain knowledge transfer. To bridge this conceptual gap, we distill four desiderata for cross-domain graph feature unification: formal uniformity, cross-domain transferability, information preservation, and backbone compatibility. Guided by these principles, we propose SliGFM, a graph foundation model built upon topology-aware sliding-window feature encoding and generative reconstruction. SliGFM orders feature dimensions by topological smoothness and scans the reordered features with a shared sliding-window feature encoder, transforming heterogeneous features into a common space of ordered fixed-dimensional feature tokens. This formulation enables a smoothness-aware transformer to capture transferable relational patterns among feature tokens within each node, while the generative reconstruction objective encourages preservation of the original feature information.
Read the full abstract

All authors Dongxiao He, Siqi Liu, Jitao Zhao, Yawen Li, Yi Wang, Di Jin