Peer Revenue Play credits. Real papers.

Papers

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

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Thursday 12 February

Machine Learning

ANML: Attribution-Native Machine Learning with Guaranteed Robustness

Frontier AI systems increasingly train on specialized expert data, from clinical records to proprietary research to curated datasets, yet current training pipelines treat all samples identically. A Nobel laureate's contribution receives the same weight as an unverified submission. We introduce ANML (Attribution-Native Machine Learning), a framework that weights training samples by four quality factors: gradient-based consistency (q), verification status (v), contributor reputation (r), and temporal relevance (T). By combining what the model observes (gradient signals) with what the system knows about data provenance (external signals), ANML produces per-contributor quality weights that simultaneously improve model performance and enable downstream attribution. Across 5 datasets (178-32,561 samples), ANML achieves 33-72% error reduction over gradient-only baselines. Quality-weighted training is data-efficient: 20% high-quality data outperforms 100% uniformly weighted data by 47%. A Two-Stage Adaptive gating mechanism guarantees that ANML never underperforms the best available baseline, including under strategic joint attacks combining credential faking with gradient alignment. When per-sample detection fails against subtle corruption, contributor-level attribution provides 1.3-5.3x greater improvement than sample-level methods, with the advantage growing as corruption becomes harder to detect.
Read the full abstract

Machine Learning · Cross-listed from cs.DC

LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training

Expert parallelism is vital for effectively training Mixture-of-Experts (MoE) models, enabling different devices to host distinct experts, with each device processing different input data. However, during expert parallel training, dynamic routing results in significant load imbalance among experts: a handful of overloaded experts hinder overall iteration, emerging as a training bottleneck. In this paper, we introduce LAER-MoE, an efficient MoE training framework. The core of LAER-MoE is a novel parallel paradigm, Fully Sharded Expert Parallel (FSEP), which fully partitions each expert parameter by the number of devices and restores partial experts at expert granularity through All-to-All communication during training. This allows for flexible re-layout of expert parameters during training to enhance load balancing. In particular, we perform fine-grained scheduling of communication operations to minimize communication overhead. Additionally, we develop a load balancing planner to formulate re-layout strategies of experts and routing schemes for tokens during training. We perform experiments on an A100 cluster, and the results indicate that our system achieves up to 1.69x acceleration compared to the current state-of-the-art training systems. Source code available at https://github.com/PKU-DAIR/Hetu-Galvatron/tree/laer-moe.
Read the full abstract

All authors Xinyi Liu, Yujie Wang, Fangcheng Fu, Xuefeng Xiao, Huixia Li, Jiashi Li, Bin Cui

Machine Learning

DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity

We present DRACO (Deep Research Accuracy, Completeness, and Objectivity), a benchmark of complex deep research tasks. These tasks, which span 10 domains and draw on information sources from 40 countries, originate from anonymized real-world usage patterns within a large-scale deep research system. Tasks are sampled from a de-identified dataset of Perplexity Deep Research requests, then filtered and augmented to ensure that the tasks are anonymized, open-ended and complex, objectively evaluable, and representative of the broad scope of real-world deep research use cases. Outputs are graded against task-specific rubrics along four dimensions: factual accuracy (accuracy), breadth and depth of analysis (including completeness), presentation quality (including objectivity), and citation quality. DRACO is publicly available at https://hf.co/datasets/perplexity-ai/draco.
Read the full abstract

All authors Joey Zhong, Hao Zhang, Clare Southern, Jeremy Yang, Thomas Wang, Kate Jung, Shu Zhang, Denis Yarats, Johnny Ho, Jerry Ma

Machine Learning · Cross-listed from cs.AI

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces

Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence dynamics under latent reasoning reveals that thinking trajectories ending in incorrect answers contain fewer low-confidence steps than those ending in correct answers. Meanwhile, we suggest that soft embeddings aggregated by multiple low-confidence thinking alternatives may introduce and propagate noise, leading to high confidence in unreliable reasoning trajectories. Motivated by these observations, ThinkRouter, an inference-time confidence-aware routing mechanism is proposed to avoid high confidence and noise for efficient reasoning. ThinkRouter routes thinking to the discrete token space when model confidence is low, and to the latent space otherwise. Extensive experiments on STEM reasoning and coding benchmarks across diverse large reasoning models demonstrate that ThinkRouter outperforms explicit CoT, random routing, and latent reasoning baselines in terms of accuracy, achieving an average improvement of 19.70 points in Pass@1, while reducing generation length by up to 15.55%. Further comprehensive analysis reveals that ThinkRouter can calibrate errors arising from explicit CoT and latent reasoning, and accelerates end-of-thinking token generation by globally lowering model confidence.
Read the full abstract

All authors Xin Xu, Tong Yu, Xiang Chen, Haoliang Wang, Julian McAuley, Saayan Mitra

Machine Learning · Cross-listed from stat.ML

Provable Offline Reinforcement Learning for Structured Cyclic MDPs

We introduce a novel cyclic Markov decision process (MDP) framework for multi-step decision problems with heterogeneous stage-specific dynamics, transitions, and discount factors across the cycle. In this setting, offline learning is challenging: optimizing a policy at any stage shifts the state distributions of subsequent stages, propagating mismatch across the cycle. To address this, we propose a modular structural framework that decomposes the cyclic process into stage-wise sub-problems. While generally applicable, we instantiate this principle as CycleFQI, an extension of fitted Q-iteration enabling theoretical analysis and interpretation. It uses a vector of stage-specific Q-functions, tailored to each stage, to capture within-stage sequences and transitions between stages. This modular design enables partial control, allowing some stages to be optimized while others follow predefined policies. We establish finite-sample suboptimality error bounds and derive global convergence rates under Besov regularity, demonstrating that CycleFQI mitigates the curse of dimensionality compared to monolithic baselines. Additionally, we propose a sieve-based method for asymptotic inference of optimal policy values under a margin condition. Experiments on simulated and real-world Type 1 Diabetes data sets demonstrate CycleFQI's effectiveness.
Read the full abstract

Machine Learning

Explainable Machine-Learning based Detection of Knee Injuries in Runners

Running is a widely practiced activity but shows a high incidence of knee injuries, especially Patellofemoral Pain Syndrome (PFPS) and Iliotibial Band Syndrome (ITBS). Identifying gait patterns linked to these injuries can improve clinical decision-making, which requires precise systems capable of capturing and analyzing temporal kinematic data. This study uses optical motion capture systems to enhance detection of injury-related running patterns. We analyze a public dataset of 839 treadmill recordings from healthy and injured runners to evaluate how effectively these systems capture dynamic parameters relevant to injury classification. The focus is on the stance phase, using joint and segment angle time series and discrete point values. Three classification tasks are addressed: healthy vs. injured, healthy vs. PFPS, and healthy vs. ITBS. We examine different feature spaces, from traditional point-based metrics to full stance-phase time series and hybrid representations. Multiple models are tested, including classical algorithms (K-Nearest Neighbors, Gaussian Processes, Decision Trees) and deep learning architectures (CNNs, LSTMs). Performance is evaluated with accuracy, precision, recall, and F1-score. Explainability tools such as Shapley values, saliency maps, and Grad-CAM are used to interpret model behavior. Results show that combining time series with point values substantially improves detection. Deep learning models outperform classical ones, with CNNs achieving the highest accuracy: 77.9% for PFPS, 73.8% for ITBS, and 71.43% for the combined injury class. These findings highlight the potential of motion capture systems coupled with advanced machine learning to identify knee injury-related running patterns.
Read the full abstract

All authors David Fuentes-Jiménez, Sara García-de-Villa, David Casillas-Pérez, Pablo Floría, Francisco-Manuel Melgarejo-Meseguer

Machine Learning

Fully First-Order Algorithms for Online Bilevel Optimization

In this work, we study nonconvex-strongly convex online bilevel optimization (OBO) using only first-order oracle. Existing OBO algorithms are mainly based on hypergradient descent, which requires access to a Hessian-vector product (HVP) oracle and potentially incurs high computational costs. By reformulating the original OBO problem as a single-level online problem with inequality constraints and constructing a sequence of Lagrangian function, we eliminate the need for HVPs arising from implicit differentiation. Specifically, we propose a fully first-order algorithm for OBO, and provide theoretical guarantees showing that it achieves regret of $O(1 + V_T + H_{2,T})$ with a total of $O(T\log T)$ iterations, where $V_T$ measures the variation in function values and $H_{2,T}$ characterizes the drift variation of the inner-level optimal solution. We also establish a sublinear regret bound under the single-loop structure by introducing additional gradient-variation terms. Furthermore, we develop an improved variant with an adaptive inner-iteration scheme, which removes the dependence on $H_{2,T}$ and achieves regret of $O(\log T + V_T)$. Finally, under the stochastic OBO setting, we establish the regret bound for the fully first-order algorithm, i.e., $O(T^{2/3}(1 + \sigma^2) + V_T + H_{2,T})$. Numerical experiments demonstrate the feasibility of our algorithm and support our theoretical findings.
Read the full abstract

Machine Learning

UMAP Is Spectral Clustering on the Fuzzy Nearest-Neighbor Graph

UMAP (Uniform Manifold Approximation and Projection) is among the most widely used algorithms for non linear dimensionality reduction and data visualisation. Despite its popularity, and despite being presented through the lens of algebraic topology, the exact relationship between UMAP and classical spectral methods has remained informal. In this work, we prove that UMAP performs spectral clustering on the fuzzy k nearest neighbour graph. Our proof proceeds in three steps: (1) we show that UMAP's stochastic optimisation with negative sampling is a contrastive learning objective on the similarity graph; (2) we invoke the result of HaoChen et al. [8], establishing that contrastive learning on a similarity graph is equivalent to spectral clustering; and (3) we verify that UMAP's spectral initialisation computes the exact linear solution to this spectral problem. The equivalence is exact for Gaussian kernels, and holds as a first order approximation for UMAP's default Cauchy type kernel. Our result unifies UMAP, contrastive learning, and spectral clustering under a single framework, and provides theoretical grounding for several empirical observations about UMAP's behaviour.
Read the full abstract

Machine Learning

Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs

Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information. Although effective on in-distribution (ID) data, GNNs often fail on out-of-distribution (OOD) nodes with unseen textual or structural patterns, producing overconfident predictions without reliable OOD detection. Existing topology-driven methods mitigate node-level bias through neighboring structures, but typically encode texts as shallow features, underutilizing semantic information. Recent LLM-based approaches instead synthesize pseudo OOD priors from textual knowledge, yet suffer from two key limitations: (1) a trade-off between reliability and informativeness, where generated OOD exposures either deviate from true OOD semantics or introduce substantial ID noise; and (2) dependence on specialized architectures, limiting compatibility with topology-level advances validated in prior work. To address these issues, we propose LG-Plug, an LLM-Guided Plug-and-play framework for TAG OOD detection. LG-Plug aligns topology and text representations to obtain fine-grained node embeddings, then constructs consensus-driven OOD exposure through clustered iterative LLM prompting. To reduce LLM query cost, it further adopts lightweight in-cluster codebooks and heuristic sampling. The generated OOD exposure acts as a regularizer that separates ID and OOD nodes, enabling seamless integration with existing detectors. Experiments on six TAG benchmarks demonstrate that LG-Plug consistently improves topology-driven OOD detectors (>7% FPR95 reduction) and surpasses prior LLM-based methods (>5% FPR95 reduction).
Read the full abstract

All authors Yinlin Zhu, Di Wu, Xu Wang, Guocong Quan, Miao Hu

Machine Learning

TIP: Resisting Gradient Inversion via Targeted Interpretable Perturbation in Federated Learning

Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct private training data with high fidelity. Existing defenses, such as Differential Privacy (DP), typically employ indiscriminate noise injection across all parameters, which severely degrades model utility and convergence stability. To address those limitation, we proposes Targeted Interpretable Perturbation (TIP), a novel defense framework that integrates model interpretability with frequency domain analysis. Unlike conventional methods that treat parameters uniformly, TIP introduces a dual-targeting strategy. First, leveraging Gradient-weighted Class Activation Mapping (Grad-CAM) to quantify channel sensitivity, we dynamically identify critical convolution channels that encode primary semantic features. Second, we transform these selected kernels into the frequency domain via the Discrete Fourier Transform and selectively inject calibrated perturbations into the high-frequency spectrum. By selectively perturbing high-frequency components, TIP effectively destroys the fine-grained details necessary for image reconstruction while preserving the low-frequency information crucial for model accuracy. Extensive experiments on benchmark datasets demonstrate that TIP renders reconstructed images visually unrecognizable against state-of-the-art GIAs, while maintaining global model accuracy comparable to non-private baselines, significantly outperforming existing DP-based defenses in the privacy-utility trade-off and interpretability. Code is available in https://github.com/2766733506/asldkfjssdf_arxiv
Read the full abstract

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

Enforcing Reciprocity in Operator Learning for Seismic Wave Propagation

Accurate and efficient wavefield modeling underpins seismic structure and source studies. Traditional methods comply with physical laws but are computationally intensive. Data-driven methods, while opening new avenues for advancement, have yet to incorporate strict physical consistency. The principle of reciprocity is one of the most fundamental physical laws in wave propagation. We introduce the Reciprocity-Enforced Neural Operator (RENO), a transformer-based architecture for modeling seismic wave propagation that hard-codes the reciprocity principle. The model leverages the cross-attention mechanism and commutative operations to guarantee invariance under swapping source and receiver positions. Beyond improved physical consistency, the proposed architecture supports simultaneous realizations for multiple sources. This yields an order-of-magnitude inference speedup at a similar memory footprint over a conventional neural operator on a realistic multi-source configuration. We demonstrate the functionality using the reciprocity relation for particle velocity fields under single forces. This architecture is also applicable to pressure fields under dilatational sources and travel-time fields governed by the eikonal equation, paving the way for encoding more complex reciprocity relations.
Read the full abstract

All authors Caifeng Zou, Yaozhong Shi, Zachary E. Ross, Robert W. Clayton, Kamyar Azizzadenesheli

Machine Learning

GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks

Graph Prompt Learning (GPL) has recently emerged as a promising paradigm for downstream adaptation of pre-trained graph models, mitigating the misalignment between pre-training objectives and downstream tasks. Recently, the focus of GPL has shifted from in-domain to cross-domain scenarios, which is closer to the real world applications, where the pre-training source and downstream target often differ substantially in data distribution. However, why GPLs remain effective under such domain shifts is still unexplored. Empirically, we observe that representative GPL methods are competitive with two simple baselines in cross-domain settings: full fine-tuning (FT) and linear probing (LP), motivating us to explore a deeper understanding of the prompting mechanism. We provide a theoretical analysis demonstrating that jointly leveraging these two complementary branches yields a smaller estimation error than using either branch alone, formally proving that cross-domain GPL benefits from the integration between pre-trained knowledge and task-specific adaptation. Based on this insight, we propose GP2F, a dual-branch GPL method that explicitly instantiates the two extremes: (1) a frozen branch that retains pre-trained knowledge, and (2) an adapted branch with lightweight adapters for task-specific adaptation. We then perform adaptive fusion under topology constraints via a contrastive loss and a topology-consistent loss. Extensive experiments on cross-domain few-shot node and graph classification demonstrate that our method outperforms existing methods.
Read the full abstract

All authors Dongxiao He, Wenxuan Sun, Yongqi Huang, Jitao Zhao, Di Jin

Machine Learning · Cross-listed from cs.CV

PLESS: Pseudo-Label Enhancement with Spreading Scribbles for Weakly Supervised Segmentation

Weakly supervised learning with scribble annotations uses sparse user-drawn strokes to indicate segmentation labels on a small subset of pixels. This annotation reduces the cost of dense pixel-wise labeling, but suffers inherently from noisy and incomplete supervision. Recent scribble-based approaches in medical image segmentation address this limitation using pseudo-label-based training; however, the quality of the pseudo-labels remains a key performance limit. We propose PLESS, a generic pseudo-label enhancement strategy which improves reliability and spatial consistency. It builds on a hierarchical partitioning of the image into a hierarchy of spatially coherent regions. PLESS propagates scribble information to refine pseudo-labels within semantically coherent regions. The framework is model-agnostic and easily integrates into existing pseudo-label methods. Experiments on two public cardiac MRI datasets (ACDC and MSCMRseg) across four scribble-supervised algorithms show consistent improvements in segmentation accuracy. Code will be made available on GitHub upon acceptance.
Read the full abstract

Machine Learning

ArGEnT: Arbitrary Geometry-encoded Transformer for Operator Learning

Learning solution operators on arbitrary geometries remains a central challenge in scientific machine learning, especially for many-query simulation, physics-informed learning, and evolving geometries requiring accurate, geometry-aware predictions at arbitrary spatial locations. Existing operator-learning methods often rely on structured discretizations, explicit geometry parameterizations, or point-cloud formulations that couple geometric representation with solution-query sampling, limiting flexibility on irregular and non-parameterized domains. We propose the Arbitrary Geometry-encoded Transformer (ArGEnT), a geometry-conditioned attention framework that decouples geometry encoding from query-point evaluation. We develop three variants: self-attention, cross-attention, and hybrid-attention. ArGEnT can be used independently or integrated with neural operators to incorporate non-geometric physical inputs. In the cross-attention variant, geometry is represented by an independently sampled point cloud used to construct keys and values, while arbitrary solution-query points construct queries. This design enables mesh-independent field prediction, reduces sensitivity to query-point distribution, and allows compact geometric representations to condition large-scale solution evaluations. Across benchmarks in fluid dynamics, solid mechanics, and electrochemical systems, ArGEnT consistently improves accuracy and generalization over standard DeepONet, point-cloud-based operator learning, and geometry-aware transformer baselines. In several cases, it reduces prediction errors by more than an order of magnitude while requiring substantially lower training cost than transformer-based baselines. These results demonstrate that decoupled geometry-query attention provides an accurate, scalable, and flexible framework for operator learning on arbitrary geometries.
Read the full abstract

All authors Wenqian Chen, Zhi-Feng Wei, Yucheng Fu, Michael Penwarden, Pratanu Roy, Panos Stinis

Machine Learning

TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees

We revisit the use of probabilistic values, which include the well-known Shapley and Banzhaf values, to rank features for explaining the local predicted values of decision trees. The quality of feature rankings is typically assessed with the insertion and deletion metrics. Empirically, we observe that co-optimizing these two metrics is closely related to a joint optimization that selects a subset of features to maximize the local predicted value while minimizing it for the complement. However, we theoretically show that probabilistic values are generally unreliable for solving this joint optimization. Therefore, we explore deriving feature rankings by directly optimizing the joint objective. As the backbone, we propose TreeGrad, which computes the gradients of the multilinear extension of the joint objective in $O(L)$ time for decision trees with $L$ leaves; these gradients include weighted Banzhaf values. Building upon TreeGrad, we introduce TreeGrad-Ranker, which aggregates the gradients while optimizing the joint objective to produce feature rankings, and TreeGrad-Shap, a numerically stable algorithm for computing Beta Shapley values with integral parameters. In particular, the feature scores computed by TreeGrad-Ranker satisfy all the axioms uniquely characterizing probabilistic values, except for linearity, which itself leads to the established unreliability. Empirically, we demonstrate that the numerical error of Linear TreeShap can be up to $10^{15}$ times larger than that of TreeGrad-Shap when computing the Shapley value. As a by-product, we also develop TreeProb, which generalizes Linear TreeShap to support all probabilistic values. In our experiments, TreeGrad-Ranker performs significantly better on both insertion and deletion metrics. Our code is available at https://github.com/watml/TreeGrad.
Read the full abstract

Machine Learning

How Well Do Large-Scale Chemical Language Models Transfer to Downstream Tasks?

Chemical Language Models (CLMs) pre-trained on large scale molecular data are widely used for molecular property prediction. However, the common belief that increasing training resources such as model size, dataset size, and training compute improves both pretraining loss and downstream task performance has not been systematically validated in the chemical domain. In this work, we evaluate this assumption by pretraining CLMs while scaling training resources and measuring transfer performance across diverse molecular property prediction (MPP) tasks. We find that while pretraining loss consistently decreases with increased training resources, downstream task performance shows limited improvement. Moreover, alternative metrics based on the Hessian or loss landscape also fail to estimate downstream performance in CLMs. We further identify conditions under which downstream performance saturates or degrades despite continued improvements in pretraining metrics, and analyze the underlying task dependent failure modes through parameter space visualizations. These results expose a gap between pretraining based evaluation and downstream performance, and emphasize the need for model selection and evaluation strategies that explicitly account for downstream task characteristics.
Read the full abstract

Machine Learning

SkillRater: Untangling Capabilities in Multimodal Data

Data curation methods typically assign samples a single quality score. We argue this scalar framing is fundamentally limited: when training requires multiple distinct capabilities, a monolithic scorer cannot maximize useful signals for all of them simultaneously. Quality is better understood as multidimensional, with each dimension corresponding to a capability the model must acquire. We introduce SkillRater, a framework that decomposes data filtering into specialized raters - one per capability, each trained via meta-learning on a disjoint validation objective - and composes their scores through a progressive selection rule: at each training stage, a sample is retained if any rater ranks it above a threshold that tightens over time, preserving diversity early while concentrating on high-value samples late. We validate this approach on vision language models, decomposing quality into three capability dimensions: visual understanding, OCR, and STEM reasoning. At 2B parameters, SkillRater improves over unfiltered baselines by 5.63% on visual understanding, 2.00% on OCR, and 3.53% on STEM on held out benchmarks. The learned rater signals are near orthogonal, confirming that the decomposition captures genuinely independent quality dimensions and explaining why it outperforms both unfiltered training and monolithic learned filtering.
Read the full abstract

All authors Naveen Sahi, Jeremy Dohmann, Armen Aghajanyan, Akshat Shrivastava

Machine Learning

Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite these advantages, MDMs face a fundamental limitation: once tokens are unmasked, they remain fixed, leading to error accumulation and ultimately degrading sample quality. We address this by proposing a framework that trains a model to perform both unmasking and correction. By reusing outputs from the MDM denoising network as inputs for corrector training, we train a model to recover from potential mistakes. During generation we apply additional corrective refinement steps between unmasking ones in order to change decoded tokens and improve outputs. We name our training and sampling method Progressive Self-Correction (ProSeCo) for its unique ability to iteratively refine an entire sequence, including already generated tokens. We conduct extensive experimental validation across multiple conditional and unconditional tasks, demonstrating that ProSeCo yields better quality-efficiency trade-offs (up to ~4x faster sampling while still outperforming the best accuracy baseline method) and enables further gains through inference-time compute scaling (up to ~1.2x improvement on benchmarks when allowing for slower, high-NFE decoding).
Read the full abstract

All authors Yair Schiff, Omer Belhasin, Roy Uziel, Guanghan Wang, Marianne Arriola, Gilad Turok, Ran Zilberstein, Michael Elad, Volodymyr Kuleshov

Machine Learning

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization

It is commonly believed that gradient compression in federated learning (FL) enjoys significant improvement in communication efficiency with negligible performance degradation. In this paper, we find that gradient compression induces sharper loss landscapes in federated learning, particularly under non-IID data distributions, which suggests hindered generalization capability. The recently emerging Sharpness Aware Minimization (SAM) effectively searches for a flat minima by incorporating a gradient ascent step (i.e., perturbing the model with gradients) before the celebrated stochastic gradient descent. Nonetheless, the direct application of SAM in FL suffers from inaccurate estimation of the global perturbation due to data heterogeneity. Existing approaches propose to utilize the model update from the previous communication round as a rough estimate. However, its effectiveness is hindered when model update compression is incorporated. In this paper, we propose FedSynSAM, which leverages the global model trajectory to construct synthetic data and facilitates an accurate estimation of the global perturbation. The convergence of the proposed algorithm is established, and extensive experiments are conducted to validate its effectiveness.
Read the full abstract

All authors Yujie Gu, Richeng Jin, Zhaoyang Zhang, Huaiyu Dai

Machine Learning · Cross-listed from cs.AI

The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why – A Survey from MARL to Emergent Language and LLMs

Multi-agent sequential decision-making powers many real-world systems, from autonomous vehicles and robotics to collaborative AI assistants. In dynamic, partially observable environments, communication is often what reduces uncertainty and makes collaboration possible. This survey reviews multi-agent communication (MA-Comm) through the Five Ws: who communicates with whom, what is communicated, when communication occurs, and why communication is beneficial. This framing offers a clean way to connect ideas across otherwise separate research threads. We trace how communication approaches have evolved across three major paradigms. In Multi-Agent Reinforcement Learning (MARL), early methods used hand-designed or implicit protocols, followed by end-to-end learned communication optimized for reward and control. While successful, these protocols are frequently task-specific and hard to interpret, motivating work on Emergent Language (EL), where agents can develop more structured or symbolic communication through interaction. EL methods, however, still struggle with grounding, generalization, and scalability, which has fueled recent interest in large language models (LLMs) that bring natural language priors for reasoning, planning, and collaboration in more open-ended settings. Across MARL, EL, and LLM-based systems, we highlight how different choices shape communication design, where the main trade-offs lie, and what remains unsolved. We distill practical design patterns and open challenges to support future hybrid systems that combine learning, language, and control for scalable and interpretable multi-agent collaboration.
Read the full abstract

All authors Jingdi Chen, Hanqing Yang, Zongjun Liu, Carlee Joe-Wong

Machine Learning

Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal

Brain foundation models (BFMs) are advancing neurotechnology by learning transferable representations from neural signals, with broad potential in clinical diagnosis and neuroscience research. Their development relies on large-scale pretraining corpora of electrical brain signals, including scalp electroencephalography (EEG) and intracranial EEG (iEEG). However, existing BFM benchmarks primarily focus on EEG, cover only a limited subset of models, and provide limited analysis beyond downstream performance. We introduce Brain4FMs, the first unified benchmark, to our knowledge, for jointly evaluating BFMs on EEG and iEEG. It integrates 17 representative models and 21 public datasets across clinical diagnosis, sleep staging, communication, and affective computing. Brain4FMs is open and plug-and-play, with dataset-aware preprocessing, cross-subject evaluation, heterogeneous multichannel handling, and standardized downstream adaptation workflows. The benchmark reveals performance variation across tasks, signal modalities, and adaptation protocols, with no single BFM consistently dominating all evaluation scenarios. % To better understand these heterogeneous transfer behaviors, we further conduct exploratory analyses of model-specific properties. To better understand these behaviors, we further conduct exploratory analyses of model-specific properties of spatial, spectral, and discrete representations. The code is available at https://github.com/wajtsq/Brain4FMs.
Read the full abstract

All authors Fanqi Shen, Enhong Yang, Jiahe Li, Junru Hong, Xiaoran Pan, Zhizhang Yuan, Meng Li, Yang Yang

Machine Learning

The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient

A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we study the implicit bias of mini-batch stochastic steepest descent in multi-class classification, characterizing how batch size, momentum, and variance reduction shape the limiting max-margin behavior and convergence rates under general entry-wise and Schatten-$p$ norms. We show that, without momentum, worst-case convergence and successful classification can only be guaranteed with full-batch gradient. In contrast, momentum enables small-batch convergence to an approximate max-margin solution through a batch-momentum trade-off, though it slows convergence. This approach provides fully explicit, dimension-free rates that improve upon prior results. Moreover, we prove that variance reduction can recover the exact full-batch implicit bias for any batch size, albeit at a slower convergence rate. Finally, we further investigate the batch-size-one steepest descent without momentum, and reveal its convergence to a fundamentally different bias via a concrete data example, which reveals a key limitation of purely stochastic updates. Overall, our unified analysis clarifies when stochastic optimization aligns with full-batch behavior, and paves the way for perform deeper explorations of the training behavior of stochastic gradient steepest descent algorithms.
Read the full abstract

Machine Learning · Cross-listed from cs.RO

HyperDet: 3D Object Detection with Hyper 4D Radar Point Clouds

How far can 3D object detection go using 4D radar alone? Despite offering weather-robust and velocity- aware sensing for autonomous perception, modern 4D radar still yields sparse, noisy, and unstable point clouds, limiting radar-only 3D detection. We present HyperDet, a detector- agnostic input enhancement pipeline that constructs task- aware hyper 4D radar point clouds by combining measured observations with completed foreground geometry. HyperDet first refines short-window surround-view radar observations through spatio-temporal accumulation and cross-sensor val- idation, while Doppler-guided motion compensation reduces dynamic object trails when motion can be estimated reliably. It then performs foreground generative enhancement using LiDAR-guided pseudo-radar supervision available only during training, enriching object geometry while preserving measured radar background and radar-native attributes. During detec- tor training, radar-aware object-level augmentation maintains Doppler consistency under geometric relocation. At inference, HyperDet requires radar input alone and can be directly paired with standard 3D detectors. Experiments on two public surround-view 4D radar datasets demonstrate consistent im- provements over matched temporal accumulation across stan- dard 3D detectors, validating input-level radar enhancement as an effective approach to radar-only 3D detection.
Read the full abstract

All authors Yichun Xiao, Jin Jin, Runwei Guan, Fangqiang Ding

Machine Learning

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a trade-off: Parametric Adaptation can cause catastrophic forgetting and requires costly multi-domain maintenance, while Non-Parametric Retrieval improves forecasts but incurs high inference latency due to datastore search. We propose Parametric Memory Distillation and implement it as TS-Memory, a lightweight memory adapter that augments frozen TSFMs. TS-Memory is trained in two stages. First, we construct an offline, retrieval-leakage-safe kNN teacher that synthesizes confidence-aware quantile targets from retrieved futures. Second, we distill this retrieval-induced distributional correction into a lightweight memory adapter via confidence-gated supervision. During inference, TS-Memory fuses memory and backbone predictions with constant-time overhead, enabling retrieval-free deployment. Experiments across diverse TSFMs and benchmarks demonstrate consistent improvements in both point and probabilistic forecasting over representative adaptation methods, with efficiency comparable to the frozen backbone. Code: https://github.com/sisuolv/TS-Memory.
Read the full abstract

All authors Sisuo Lyu, Siru Zhong, Tiegang Chen, Weilin Ruan, Qingxiang Liu, Taiqiang Lv, Qingsong Wen, Raymond Chi-Wing Wong, Yuxuan Liang

Machine Learning

Native Reasoning Models: Training Language Models to Reason on Unverifiable Data

The prevailing paradigm for training large reasoning models–combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)–is fundamentally constrained by its reliance on high-quality, human-annotated reasoning data and external verifiers. This dependency incurs significant data-collection costs, risks embedding human cognitive biases, and confines the reinforcement learning stage to objectively assessable domains like mathematics and coding, leaving a wide range of unverifiable tasks beyond its scope. To overcome these limitations, we introduce NRT (Native Reasoning Training), a novel framework that cultivates complex reasoning by having the model generate its own reasoning traces using only standard question-answer pairs, thereby obviating the need for expert-written demonstrations. NRT reframes the training problem by treating the reasoning process as a latent variable. It employs a unified training objective that models reasoning as an optimization problem, intrinsically rewarding paths that increase the model's likelihood of producing the ground-truth answer. This unified perspective allows us to analyze intrinsic failure modes of prior methods, such as policy collapse, and systematically design more robust reward aggregation functions, creating a self-reinforcing feedback loop where the model learns to think in ways that resolve its own uncertainty. Empirical evaluation on Llama and Mistral model families demonstrates that NRT achieves state-of-the-art performance among verifier-free methods, significantly outperforming standard SFT baselines and prior verifier-free RL methods. Our approach yields particularly strong performance gains in complex reasoning domains and exhibits high robustness to policy collapse, offering a general, scalable path toward building more powerful and broadly applicable reasoning systems.
Read the full abstract

All authors Yuanfu Wang, Zhixuan Liu, Xiangtian Li, Chaochao Lu, Chao Yang

Machine Learning · Cross-listed from cs.AI

Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use

We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize this setting as sequential decision making in context space with priced and stochastic tool executions, making direct planning intractable due to massive state-action spaces, high variance of outcomes and prohibitive exploration cost. To address these challenges, we propose INTENT, an inference-time planning framework that leverages an intention-aware hierarchical world model to anticipate future tool usage, risk-calibrated cost, and guide decisions online. Across cost-augmented StableToolBench, INTENT strictly enforces hard budget feasibility while substantially improving task success over baselines, and remains robust under dynamic market shifts such as tool price changes and varying budgets.
Read the full abstract

All authors Hanbing Liu, Chunhao Tian, Nan An, Ziyuan Wang, Pinyan Lu, Changyuan Yu, Qi Qi

Machine Learning

Real-Time Proactive Anomaly Detection via Forward and Backward Forecast Modeling

Reactive anomaly detection methods, which are commonly deployed to identify anomalies after they occur based on observed deviations, often fall short in applications that demand timely intervention, such as industrial monitoring, finance, and cybersecurity. Proactive anomaly detection, by contrast, aims to detect early warning signals before failures fully manifest, but existing methods struggle with handling heterogeneous multivariate data and maintaining precision under noisy or unpredictable conditions. In this work, we introduce two proactive anomaly detection frameworks: the Forward Forecasting Model (FFM) and the Backward Reconstruction Model (BRM). Both models leverage a hybrid architecture combining Temporal Convolutional Networks (TCNs), Gated Recurrent Units (GRUs), and Transformer encoders to model directional temporal dynamics. FFM forecasts future sequences to anticipate disruptions, while BRM reconstructs recent history from future context to uncover early precursors. Anomalies are flagged based on forecasting error magnitudes and directional embedding discrepancies. Our models support both continuous and discrete multivariate features, enabling robust performance in real-world settings. Extensive experiments on four benchmark datasets, MSL, SMAP, SMD, and PSM, demonstrate that FFM and BRM outperform state-of-the-art baselines across detection metrics and significantly improve the timeliness of anomaly anticipation. These properties make our approach well-suited for deployment in time-sensitive domains requiring proactive monitoring.
Read the full abstract

Machine Learning

Krause Synchronization Transformers

Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that favor convergence toward a dominant mode, a behavior associated with representation collapse and attention sink phenomena. We introduce Krause Attention, a principled attention mechanism inspired by bounded-confidence consensus dynamics. Krause Attention replaces similarity-based global aggregation with distance-based, localized, and selectively sparse interactions, promoting structured local synchronization instead of global mixing. We relate this behavior to recent theory modeling Transformer dynamics as interacting particle systems, and show how bounded-confidence interactions naturally moderate attention concentration and alleviate attention sinks. Restricting interactions to local neighborhoods also reduces runtime complexity from quadratic to linear in sequence length. Empirically, we validate Krause Attention across diverse settings, including vision (ViT on CIFAR/ImageNet), autoregressive image generation (MNIST/CIFAR-10), large language models (Llama/Qwen), and language models trained from scratch at multiple scales (100M/200M). Across these domains, Krause Attention achieves consistent performance gains while improving computational efficiency, highlighting bounded-confidence dynamics as a scalable and effective inductive bias for attention.
Read the full abstract

All authors Jingkun Liu, Yisong Yue, Max Welling, Yue Song

Machine Learning

AltTS: A Dual-Path Framework with Alternating Optimization for Multivariate Time Series Forecasting

Multivariate time series forecasting involves two qualitatively distinct factors: (i) stable within-series autoregressive (AR) dynamics, and (ii) intermittent cross-dimension interactions that can become spurious over long horizons. We argue that fitting a single model to capture both effects creates an optimization conflict: the high-variance updates needed for cross-dimension modeling can corrupt the gradients that support autoregression, resulting in brittle training and degraded long-horizon accuracy. To address this, we propose ALTTS, a dual-path framework that explicitly decouples autoregression and cross-relation (CR) modeling. In ALTTS, the AR path is instantiated with a linear predictor, while the CR path uses a Transformer equipped with Cross-Relation Self-Attention (CRSA); the two branches are coordinated via alternating optimization to isolate gradient noise and reduce cross-block interference. Extensive experiments on multiple benchmarks show that ALTTS consistently outperforms prior methods, with the most pronounced improvements on long-horizon forecasting. Overall, our results suggest that carefully designed optimization strategies, rather than ever more complex architectures, can be a key driver of progress in multivariate time series forecasting.
Read the full abstract

Machine Learning

PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models

The emergence of reasoning-based LLMs leveraging Chain-of-Thought (CoT) inference introduces new serving challenges, as their extended reasoning phases delay user-visible output and inflate Time-To-First-Token (TTFT). Existing LLM serving frameworks fail to distinguish between reasoning and answering phases, leading to performance degradation under GPU memory constraints. We present PASCAL, a phase-aware scheduling algorithm that prioritizes reasoning to reduce TTFT while using controlled preemption and token pacing during answering to preserve Quality-of-Experience (QoE). Our hierarchical scheduler combines instance-level placement with intra-instance execution and enables dynamic migration at phase boundaries to balance load and reduce interference. Across benchmarks using DeepSeek-R1-Distill-Qwen-32B, PASCAL reduces tail TTFT by up to 72% while maintaining answering phase SLO attainment, demonstrating the importance of phase-aware scheduling for reasoning-based LLM deployment.
Read the full abstract

All authors Eunyeong Cho, Jehyeon Bang, Ranggi Hwang, Minsoo Rhu