跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 05:45 — 2026-11-09 05:45（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 05:07最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 14,661 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
版本更新 · v3arXiv:2610.34507

The Price of Scale in Proactive Memory Recall

Yichuan Chen, Xin Wang

原文摘要

A long-lived assistant that brings up memories without being asked must decide at every turn whether anything in its store is worth an interruption. We show that this decision is a multiple-testing problem whose difficulty grows with the store size N. On replays of LongMemEval, a similarity threshold tuned to 5% false alarms at N=8 reaches 84-100% at N=2048 across embedding models and cue types; LoCoMo and LLM judges show it too. We prove that a gate which thresholds the best of N independent irrelevant scores at false-alarm rate alpha operates at a per-item false-positive rate of about -ln(1-alpha)/N, which pins its hit rate to the far left of the ROC and makes it regularly varying in N under regular variation. Replayed hit rates stay within its bounds for mixed cues up to 0.3 points, and hit rates carry over to held-out questions to within 6.0 points. At matched false alarms the deployed score recalls 14-26 points more than raw cosine. A cue-swap conformal gate, which ranks the current cue among other cues on the same store, has a finite-sample false-alarm guarantee under exchangeability. With a background from the user's unfiltered history it keeps false alarms at 3-6% on LongMemEval at the hit rate of a label-tuned threshold; on LoCoMo it overshoots or turns conservative depending on the source of its reference cues. In a chronological replay with the user's own earlier messages as references, it fires on 5-8% of questions on stores without their answer and on 6-8% of session-opening turns, against 57% for the deployed gate at N=2048, at a median 0.4 s CPU per decision. A cross-encoder pays the same price of scale, and on a prospective-memory benchmark, similarity gates recall at most 9% of constraints at controlled false alarms. One human and two LLM annotators judge most false alarms unhelpful for a response. Code and data: https://github.com/RiverChenStillCompiling/price-of-scale

cs.CL · cs.AI · cs.IR · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.14423

Scaling Laws for Multimodal Data Mixtures

Aditi Khandelwal, Ayush K. Tarun, Yixuan Xu, Imanol Schlag, Golnoosh Farnadi, Siva Reddy, Luke Zettlemoyer, Antoine Bosselut

原文摘要

Frontier AI systems are increasingly natively multimodal, jointly pretrained on multiple modalities, such as text, vision, and audio. However, the scientific understanding of the multimodal data mixtures used to pretrain these systems --- how much of each modality to mix, and at what potential interference cost to the others --- is largely absent or gatekept. In this work, we derive data mixing scaling laws for three modalities: text, vision, and audio. Multimodal Large Language Models (MLLMs) increasingly adopt Mixture-of-Experts (MoE) architectures, as MoEs scale efficiently and partially limit cross-modal interference. We therefore use MoEs to conduct 268 experiments ranging from 457M to 8.3B parameters, on up to 150 billion tokens. Our work leads to multiple actionable insights into multimodal data mixing for training MLLMs. First, compute optima are modality-specific: audio modality is model-heavy, favoring scaling parameters over tokens, while text and vision require balanced scaling of model size and data. Second, repeating vision or audio data beyond 2x yields negligible benefits. Finally, cross-modal interactions are highly asymmetric: vision strongly interferes with audio, whereas audio's interference with learning text and vision is negligible. Overall, we provide a principled foundation for understanding the multimodal data mixtures needed to train frontier MLLMs.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05066

VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models

Junzhe Chen, Tian Qin, Eugenie Shi, Tianshu Zhang, Qiang Ju, Lijie Wen

原文摘要

Multimodal discrete diffusion language models (dLLMs) generate responses through iterative mask prediction and offer a promising alternative to autoregressive large vision-language models. However, they still suffer from hallucination, producing outputs that are plausible under language priors but insufficiently grounded in the image. We argue that hallucination in multimodal dLLMs is not only a token prediction problem, but also a premature commitment problem: during iterative denoising, some masked positions are unmasked too early because their confidence is driven more by language priors than by visual evidence, and these early commitments can bias later generation. To address this issue, we propose Visual Gain Ordering (VIGOR), a training-free and plug-and-play inference strategy that reorders masked positions according to counterfactual visual evidence. At each denoising step, VIGOR compares the confidence of each candidate token under the original image-conditioned pass and an additional visual-ablation pass, and prioritizes positions whose predictions are more strongly supported by the image. Experiments on LLaDA-V and Lumina-DiMOO show that VIGOR consistently reduces hallucination and improves multimodal reasoning performance across benchmarks. Code is available at https://github.com/THU-BPM/Vigor.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2503.19288

Design of an Underwater Vehicle With Orientation-Adjustable Thrusters and Adaptive Tracking Control

Yifei Wang, Shihan Kong, Zhanhua Xin, Kaiwei Zhu, Junzhi Yu

原文摘要

Unmanned underwater vehicles (UUVs) are essential for marine exploration and research. However, conventional designs often struggle with limited maneuverability in complex and dynamic underwater environments. This paper presents an orientation-adjustable thruster UUV (OAT-UUV) with vector thrusters, enabling full six-degree-of-freedom (6-DOF) motion. and composite maneuvers. To overcome challenges associated with uncertain model parameters and environmental disturbances, a vision-based tracking control system based on a novel feedforward adaptive model predictive controller (FF-AMPC) is proposed to achieve robust object tracking, which integrates realtime state feedback with adaptive parameter updating. Extensive experiments, including closed-loop tracking and composite motion tests in real-world environment, have been conducted. The obtained results demonstrate that the orientation-adjustable propulsion design significantly improves the underwater maneuverability, while the FF-AMPC controller achieves a 49.1% hovering improvement compared to conventional controller.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05058

Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action

Yihang Liu, Yiming Chen, Mingzhe Zheng

原文摘要

Recent multimodal language models can reason directly about robot scenes, but it is unclear whether they need to repeatedly reinterpret raw visual observations at every step of an interaction. We propose shifting routine spatial reasoning from images to text and symbols through a 3D geometric abstraction that is refreshed locally from observations and read directly by the language models. Specifically, our interface represents scene geometry via typed, evidence-aware symbolic references to object parts, grounds them from calibrated RGB-D, and returns compact textual checkpoints with metric residuals after each action. Symbolic task structure can thus be reused across decisions while metric values are rebound to the current scene, with direct visual reasoning invoked only on demand. Across offline policy synthesis and continuous online execution, reasoning over grounded text and symbols improves multi-step manipulation completion while substantially reducing repeated multimodal queries, positioning explicit geometric state as an effective substrate for agentic robot policies.

cs.RO · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16351

PALM: Physically-Anchored Latent-timescale Mamba for Stable Representations under Distribution Shift

Sangyoon Bae, Shinjae Yoo, Jiook Cha

原文摘要

Scientific foundation models are built to reuse representations across datasets and acquisition protocols, yet their representations degrade under distribution shift. We trace one source of this failure to selective state-space models (SSMs). Their memory depends on the step Delta and the state matrix A only through their product, so data do not identify the physical timescale of memory, and under a shift the resulting memory no longer matches the signal's timescales. We call this failure memory-timescale misalignment. To resolve it, the split between Delta and A must be tied to physical units. We therefore propose Physically-Anchored Latent-timescale Mamba (PALM), which disentangles A from Delta by anchoring both to acquisition units: Delta through spectrum-estimated knee frequencies and A through a physical memory range. We evaluate PALM against parameter-matched baselines in two domains, under temporal-context truncation, low-resource transfer, and brain-state shift on fMRI and under held-out-station forecasting on Weather-5K. Under fMRI context truncation with run-level spectral calibration, PALM keeps its latent timescales in physical units and retains 11% higher representation similarity than Mamba2. At geographically isolated weather stations never seen during training, PALM achieves the lowest error on every variable and horizon, 15.2% below the best baseline on average, and outperforms zero-shot forecasting foundation models. Across both domains, the gains come from where the backbone places memory in physical time rather than from model size. We therefore argue that physically anchored latent timescales are a design requirement for scientific foundation models that must transfer across acquisition conditions.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05055

Ablating Design Choices for Protein Ensemble Generators Across Structural Regimes

Eoin Quinn, Oliver Bent

原文摘要

Generative models of protein conformational ensembles inherit much of their design from structure prediction for folded proteins. Ordered and disordered proteins, however, occupy distinct structural regimes, and we investigate how design choices hold up across them. Using a minimal C$α$ flow-matching model, we ablate choices of architecture, sequence conditioning, rigid-body alignment and training source, and evaluate each variant against experimental SAXS and NMR chemical-shift data partitioned into ordered, disordered, multi-domain and transitional proteins. Mixture-of-experts routing, a static pair representation and a disorder probe have no detectable effect, a smaller protein language model performs worse on ordered proteins but not on disordered ones, and alignment in the loss degrades agreement with SAXS. Replacing coarse-grained simulations of disordered proteins with fragment-assembled ensembles improves agreement with chemical shifts at a cost to SAXS, while an equal mixture of the two keeps most of the gain at a smaller cost. This points to the training data, rather than the architecture, as the main constraint.

q-bio.BM · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.34527

LLM4Robot-Bench: How Far Can GPT-6 Astra Go in Robotic Manipulation? A Hierarchical, Paired Sim-Real Benchmark

Haibao Yu, Jiaqi Meng, Zijian Zhang, Bowen Jing, Lei Yang, Yue Hu, Chenchen Ge, Yiming Hou 等 19 位作者

原文摘要

We introduce LLM4Robot-Bench, a hierarchical, paired Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometric alignment (L1), force regulation within sustained contact (L2), and coordinated contact reconfiguration and force regulation (L3). Each task is instantiated in physically and visually matched simulated and real-world environments, with shared task definitions and success criteria. We evaluate GPT-6 Astra zero-shot with three trials per task in each environment. Real-world success rates decline from 80.0% at L1 to 47.6% at L2 and 0.0% at L3, with corresponding simulation rates of 66.7%, 47.6%, and 0.0%. Ten of the 16 tasks have identical success counts across environments; the remaining six differ by one success out of three trials. Across both environments, recurring difficulties in spatial reasoning, contact selection, force regulation, and coordination often prevent local physical progress from accumulating into task completion. These findings characterize Astra's observed capability boundary across increasing interaction demands and, for this model, support matched simulation as a repeatable, scalable testbed for studying the sustained, coordinated physical interactions that limit reliable manipulation.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17864

TStruct: Learning Shared Temporal Structures for Long-Term Time Series Forecasting

Yangze Li, Zhengyang Zhou, Qihe Huang, Pengkun Wang, Binwu Wang, Yang Wang

原文摘要

Long-term time series forecasting requires learning temporal dependencies that remain stable and generalizable under temporal distribution shifts. However, real-world time series are often noisy, non-stationary, and heterogeneous, making deep learning models prone to overfitting incidental temporal interactions in the training data. This raises a question: when observations are difficult to align, could temporal relationships be easier to reuse? To investigate this possibility, we analyze patch-level temporal relationship matrices across commonly used time series datasets, revealing dominant patterns shared across different temporal windows and variables. Comparisons with patch-shuffled and IID Gaussian controls further support the presence of reusable temporal relationship structures. Motivated by these findings, we propose \textbf{T}emporal \textbf{Struct}ure Network (\textbf{TStruct}), a simple yet effective network that learns reusable temporal dependency structures and adaptively combines them for each sample and variable. Specifically, TStruct directly parameterizes a set of shared temporal dependency matrices and generates normalized combination weights using dynamic sample information and static variable priors. These weights represent a soft allocation of each sample-variable pair over shared temporal dependency structures, enabling the model to generate adaptive temporal dependency matrices under shared structural constraints, rather than fitting incidental interactions in a fully unconstrained manner. Notably, TStruct consistently outperforms several strong baselines across all evaluated datasets, achieving superior accuracy while maintaining high computational efficiency. Our code is available at https://github.com/yangzeli/TStruct.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05049

On the Learnability of Footwear Robustness: Footstep Recognition Under Unseen Conditions

Robyn Larracy, Erik Scheme

原文摘要

Footstep patterns, captured using pressure or force-sensitive walkways during natural walking, offer a convenient and passive approach to biometric recognition. However, footwear variability poses a major challenge to practical deployment, as it impacts both the foot-sensor interface and the user's underlying gait mechanics. This study considers the particularly difficult scenario where users enroll under one fixed footwear condition but must later be recognized in arbitrary, unseen footwear. Using the StepUP-P150 dataset, we show that footwear-induced shift, while substantial and heterogeneous across individuals, contains shared structure that can be learned from a training population and transferred, zero-shot, to previously unseen users and footwear styles. We do this using BiStepNet, a novel architecture that decomposes spatial and temporal identity cues into independently trainable streams and outperforms compact 3D spatiotemporal baselines for cross-footwear recognition. We demonstrate that cross-footwear recognition performance scales systematically with the volume and diversity of footwear representation in the training set, with gains transferring to footwear styles not directly observed during training. Moreover, we show that auxiliary gait datasets with only partial modality overlap (incorporated through the architecture's decomposed design) can be leveraged to further improve robustness to unseen footwear conditions.

cs.CV · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30192

SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

Xinyue Zeng, Jiawei Zhang, Yujun Yan, Dawei Zhou

原文摘要

Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure Analysis (SCA) as a theoretical lens characterizing how branching structures and sparse rewards induce these biases in long-horizon reasoning with local admissibility, and as a design principle for structural priors in less formal reasoning tasks. Motivated by this analysis, we propose SAGE (Structural Admissibility-Guided Exploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horizon reasoning. SAGE combines two complementary structural guidance: algebraic sparsification, which projects locally admissible candidates onto operator-indexed algebraic subspaces to suppress spurious branching and mitigate exploration bias, and hyperbolic structural guidance, which embeds reasoning states into a negatively curved space to provide dense depth-wise signals and mitigate compounding bias. Across 12 benchmarks and 7 model families, SAGE outperforms competitive baselines. In particular, SAGE achieves up to an 8-fold improvement on the Andrews-Curtis problem, an open real-world long-horizon task. Code is available at: https://github.com/Susan571/SAGE-NeurIPS2026.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2610.05366

The ÌròyìnSpeech Text Corpus: 24,905 Curated Yorùbá Sentences for Speech and Language Technology

Kola Tubosun, Anuoluwapo Aremu, Tolulope Ogunremi, Iroro Orife, David Ifeoluwa Adelani

原文摘要

ÌròyìnSpeech is a 42-hour, 80-speaker Yorùbá read-speech corpus whose audio has been distributed by ELRA since 2024. This paper describes the release of its text component: 24,905 unique, hand-verified, tone-marked Yorùbá sentences (275,897 tokens; 15,687 types), curated in 2022 as recording prompts. Roughly 11,000 sentences were adapted from openly licensed news material; the remainder were written in-house to broaden coverage beyond the religious translation that dominates existing Yorùbá corpora. Every sentence was checked by hand for tone-mark accuracy, edited for read-aloud clarity and a neutral register, and localised so that non-Yorùbá personal and place names appear in Yorùbá form. Preparing the text for release surfaced systematic Unicode normalisation failures affecting more than 60% of lines (with precomposed and decomposed forms of the same letter co-occurring within single sentences) which we document and correct. The corpus supports diacritic restoration, grapheme-to-phoneme conversion, TTS front-end development and orthographic research, and serves as a validated prompt set for new recording.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05042

Effects of Parton Pair Correlations on Direct-Photon Yields and Elliptic Flow in Heavy-Ion Collisions

Xingjian Lu, Shuzhe Shi

原文摘要

Direct photons escape heavy-ion collisions with little rescattering, carrying information from the full emission history. Yet describing the measured direct-photon yield and the sizable elliptic flow $v_2$ together remains a long-standing challenge. Here we explore how correlations between emitting partons may affect both observables. The local $2\to2$ photon rate depends on the joint distribution of incoming partons, so a connected correlation between them can change photon emission without changing the one-particle distribution of medium particles. Once folded over the evolving medium in Au+Au and Pb+Pb collisions, the correlation raises the photon yield toward the fitted PHENIX and ALICE data and increases $v_2$ mainly at intermediate $p_T$. The fitted temperature dependence accounts for most of the net flow increase in this region, suggesting that the correlation changes the relative contributions between hotter and cooler regions.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05041

Positional Encoding is All You Need for Scalable Equivariance Constraint Relaxation

Hagay Michaeli, Haggai Maron, Daniel Soudry

原文摘要

Equivariant neural networks incorporate known symmetries of the data, such as permutations, rotations, or translations, directly into their architecture, often improving sample efficiency and generalization. However, strict equivariance can make optimization difficult, for example, when the data only approximately satisfy the assumed symmetry, or when the equivariance constraints induce a challenging loss landscape. Recent studies have shown that relaxing equivariance during training by introducing non-equivariant dense linear layers can ease optimization in such cases and improve the performance of the resulting strictly equivariant model, after removing the relaxation layers at test time. While effective, this approach incurs a significant computational overhead, limiting its applicability in scalable architectures. In this work, we propose a more efficient constraint-relaxation method based on positional encoding (PE). Our framework injects a positional encoding with learnable scale that breaks the model's original symmetry. This positional signal is gradually annealed to zero, recovering the original equivariant model by the end of training. Empirically, we demonstrate significant improvements for translational and rotational equivariant models with only marginal compute and memory overhead.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2602.16346

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut

原文摘要

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test single-prompt instructions, leaving a gap in measuring how agents end up helping with harmful or illegal tasks over multiple turns. We introduce STING (Sequential Testing of Illicit N-step Goal execution), an automated red-teaming framework that constructs a step-by-step illicit plan grounded in a benign persona and iteratively probes a target agent with adaptive follow-ups, using judge agents to track phase completion. We further introduce an analysis framework that models multi-turn red-teaming as a time-to-first-jailbreak random variable, enabling analysis tools like discovery curves, hazard-ratio attribution by attack language, and a new metric: Restricted Mean Jailbreak Discovery. Across AgentHarm scenarios, STING yields substantially higher illicit-task completion than single-turn prompting and chat-oriented multi-turn baselines adapted to tool-using agents. In multilingual evaluations across six non-English settings, we find that attack success and illicit-task completion do not consistently increase in lower-resource languages, diverging from common chatbot findings. Overall, STING provides a practical way to evaluate and stress-test agent misuse in realistic deployment settings, where interactions are inherently multi-turn and often multilingual.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05039

ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refineme

Aboubaker Seddiq Benterki, Jüri Vain, Gert Kanter, Leelo Aino Jürgenstein

原文摘要

We introduce ALBI (Agent for Learning By Induction), a neuro-symbolic ILP framework that replaces the ASP-based hypothesis generator in the Learning from Failures (LFF) paradigm with a Large Language Model (LLM), while retaining SWI-Prolog as a formal verifier. ALBI implements an iterative generate-test-constrain loop: the LLM proposes candidate hypotheses from structured prompts; Prolog tests each candidate; and diagnostic feedback drives refinement. We further introduce semantic anonymization, a metamorphic testing methodology, to distinguish structural symbolic induction from surface-level pattern matching on predicate names. Experiments on 30 standard ILP benchmarks show that ALBI achieves 100% success across three frontier LLMs (Gemini 3.1 Pro, GPT 5.4 Pro, Claude Opus 4.6), matching Popper while requiring only 1.4-1.7 iterations on average. Under anonymization, all models maintain 100% success with a moderate iteration increase (1.36-1.67 times), providing evidence of robust symbolic reasoning.

cs.AI · cs.SC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05036

ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents

Guanting Dong, Zhichao Sun, Xinyu Yang, Rui Wang, Xin Deng, Jiajie Jin, Zhixiong Yang, Junhao Huang 等 25 位作者

原文摘要

Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As a result, tool interfaces may not match real ones, tool compositions are not grounded in execution, and tasks rarely span more than one environment. We propose ToolSpace, a tool-centric framework that reverses this order. ToolSpace mines data, state, and retry dependencies from adjacent calls in execution traces of real MCP services and open agent corpora, using deterministic rules rather than LLM judgment, and clusters the resulting weighted tool-composition graph into environments. Databases are synthesized only for state-mutating environments, while query and stateless tools replay recorded returns. ToolSpace then performs state-aware random walks with rollback and decompiles each chain into a natural-language task with assertion-based checks, keeping only samples that replay successfully from the initial state. Applied to AutomationBench and tau3-Bench Banking, the pipeline produces harder Pro versions on which 7 frontier models drop by up to 38.2 points. Across seven long-horizon tool-use benchmarks, ToolSpace raises Qwen3.6-35B-A3B from 23.0 to 41.0 average score (43.2 with RL) and GLM-5.2 from 44.6 to 56.6, on par with Claude Opus 5. Ablations show that execution-witnessed edges clearly outperform LLM-judged ones, and performance keeps improving with data and environment scale.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.21961

FlowDrive: moderated flow matching with data balancing for trajectory planning

Lingguang Wang, Ömer Şahin Taş, Marlon Steiner, Christoph Stiller

原文摘要

Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade performance on critical scenarios. To tackle this problem, we compare balancing strategies for sampling training data and find reweighting by trajectory pattern an effective approach. We then present FlowDrive, a flow-matching trajectory planner that learns a conditional rectified flow to map noise directly to trajectory distributions with few flow-matching steps. We further introduce moderated, in-the-loop guidance that injects small perturbation between flow steps to systematically increase trajectory diversity while remaining scene-consistent. On nuPlan and the interaction-focused interPlan benchmarks, FlowDrive achieves state-of-the-art results among learning-based planners and approaches methods with rule-based refinements. After adding moderated guidance and light post-processing (FlowDrive*), it achieves overall state-of-the-art performance across nearly all benchmark splits. Our code is available at https://github.com/einsteinguang/flow_drive_planner.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05035

Federated Transfer Learning for Medical Image Classification under Mixed Skew

Alexandre G. Leclercq, Sébastien Bougleux, Aurélien Corroyer-Dulmont, Romain Hérault

原文摘要

Deep learning in medical imaging is constrained by data scarcity and by privacy regulations that make centralizing patient data across institutions impractical. Federated Learning (FL) addresses these constraints by keeping data local, but its distributed nature exposes training to strong statistical heterogeneity. Multicentric medical data is particularly affected, exhibiting a mixed skew that combines feature, label, concept, and quantity shifts across centers. Personalized FL mitigates heterogeneity by tailoring a model to each client, yet most methods assume training from scratch, which is unrealistic given the high dimensionality of medical features relative to the limited data available. We propose the Personalized Aligner Federated Pretrained (PAFP) framework, a personalized FL approach built on a pre-trained backbone. PAFP inserts client-specific Feature Alignment modules before the fine-tuned blocks to realign hidden feature distributions toward a server-aggregated target. On the FedISIC benchmark, PAFP attains the highest unweighted balanced accuracy while reducing inter-client performance variance roughly six-fold relative to the strongest baseline, yielding accuracy and cross-client equity jointly. Our code is publicly available at https://github.com/Alexandre-Leclercq/PAFP.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.02194

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters

原文摘要

Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more expert demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for typical sparse reward tasks, RL algorithms can struggle to optimize the behavior in a sample-efficient manner. We explore inverse reinforcement learning, where a dense reward function is learned from expert demonstrations, potentially reducing the challenge of RL finetuning. We specifically consider coherent imitation learning, an IRL method that facilitates improvement of the BC policy by using a specific learned reward formulation with theoretical guarantees for imitation learning. We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a $\geq 90\%$ success rate on five out of six complex manipulation tasks, outperforming RL-based baselines using sparse rewards. We also demonstrate real-world learning on a robot manipulation task, finetuning pi-0.5 to success with less than 30 minutes of environment interaction time. By ensuring our initial pretrained finetuning policy is optimal for our initial reward and critic, our method circumvents the initial drop commonly seen in RL finetuning and enables faster improvement.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05033

Whose Effect Is It? How Objectives Inflate Learned Subspace Interventions

Toygar Tanyel, Serkan Ayvaz

原文摘要

Interpretability often locates concepts by copying part of a language model's state from one input into another (activation patching). A larger output change counts as stronger evidence that this part carries the concept. Methods that learn which part to copy often change the output more than the whole state does. By that reading, learned parts isolate the concept more cleanly. Yet the whole contains the part. So whose effect is this excess, the network's or the method's? Copying the whole state learns nothing, so it shows what the network produces. We prove that, to first order, the effects of orthogonal parts add up to that of the whole. A part therefore exceeds the whole exactly when the rest moves the output back, which does not require isolating the concept more cleanly. Objectives that reward a larger effect select such parts. Distributed alignment search with cross-entropy, for example, exceeds the whole-state copy just before the output on almost all tasks, and inside the network at most sites. In both, changing only its objective to target what the network produces removes most of the excess. It therefore comes largely from the objective, so a larger learned effect alone is not stronger evidence.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.27777

Exploring Student Perception on Gen AI Adoption in Higher Education: A Descriptive Study

Harpreet Singh, Jaspreet Singh, Satwant Singh, Rupinder Singh, Shamim Ibne Shahid, Mohammad Hassan, Tayarani Najaran

原文摘要

The rapid proliferation of Generative Artificial Intelligence (GenAI) is reshaping pedagogical practices and assessment models in higher education. While institutional and educator perspectives on GenAI integration are increasingly documented, the student perspective remains comparatively underexplored. This study examines how students perceive, use, and evaluate GenAI within their academic practices, focusing on usage patterns, perceived benefits, and expectations for institutional support. Data were collected through a questionnaire administered to 436 postgraduate Computer Science students at the University of Hertfordshire and analysed using descriptive methods. The findings reveal a Confidence-Competence Paradox: although more than 60% of students report high familiarity with tools such as ChatGPT, daily academic use remains limited and confidence in effective application is only moderate. Students primarily employ GenAI for cognitive scaffolding tasks, including concept clarification and brainstorming, rather than fully automated content generation. At the same time, respondents express concerns regarding data privacy, reliability of AI-generated information, and the potential erosion of critical thinking skills. The results also indicate strong student support for integrating AI literacy into curricula and programme Knowledge, Skills, and Behaviours (KSBs). Overall, the study suggests that universities should move beyond a policing approach to GenAI and adopt a pedagogical framework that emphasises AI literacy, ethical guidance, and equitable access to AI tools.

cs.CY · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05031

Comparing model representations and fitting methods for port-Hamiltonian system identification

Sølve Eidnes, Håkon Noren Myhr

原文摘要

Port-Hamiltonian models describe physical systems by separating stored energy, dissipation and external inputs. Learning such models from data requires a choice of representation and fitting method. We compare using neural networks, analytic expressions and combinations of the two for representing the different components of the port-Hamiltonian system, and compare fitting the models with gradient-based optimisation or sparse regression. Testing on simulations of mechanical and electrical systems, with and without added noise, we present prediction accuracy and computational cost of the different approaches.

eess.SY · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05029

DRAP: Dynamics-Risk Adaptive Plasticity for Continual Learning in Physical AI

Oswaldo Ludwig

原文摘要

Continual learning in physical AI differs from conventional continual learning because small per-step policy errors can accumulate over a trajectory. Each deviation may move the agent outside the training distribution, increase subsequent prediction errors, and ultimately cause closed-loop task failure. This work introduces Dynamics-Risk Adaptive Plasticity (DRAP), a replay-free method that estimates the historical importance of adaptable model tensors from sample-level action gradients weighted by local trajectory-amplification risk. A ridge-regularized local linear model is fitted to expert state-action transitions, and the largest singular value of its state-transition matrix provides a policy-independent, Lyapunov-inspired estimate of one-step perturbation amplification. After each task, risk-weighted squared gradients are accumulated in a tensor-level importance memory. During subsequent tasks, DRAP uses normalized cumulative importance to scale the effective AdamW learning rate of each tensor, immediately reducing the plasticity of components that supported previous behavior at dynamically sensitive trajectory points. We instantiate DRAP on a fixed KappaTune-selected subnetwork of OpenVLA and evaluate replay-free sequential adaptation across the LIBERO Spatial, Object, and Goal suites. Compared with standard AdamW fine-tuning and EWC, the results show substantially improved retention of previously learned behaviors while preserving strong new-suite acquisition.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.27613

AMGenC: Generating Charge Balanced Amorphous Materials

Yan Lin, Jilin Hu, N. M. Anoop Krishnan, Morten M. Smedskjaer

原文摘要

Amorphous (disordered) materials require simulation cells with at least hundreds to thousands of atoms to accurately capture their diverse local atomic environments, compared to crystalline materials that can be described by unit cells containing a few to hundreds of atoms. To advance the design of amorphous materials with desired properties and facilitate the exploration of their vast design space, generative inverse design has emerged as a promising approach. It aims to directly output materials with properties closely aligned with the desired ones using probabilistic generative models conditioned on desired properties, which can be more resource efficient than the traditional trial-and-error approach. However, due to the inherent stochasticity of probabilistic generative models, when element assignments are unconstrained, a large portion of generated materials may be charge unbalanced, and existing methods either fix the composition in advance or discard charge unbalanced samples after generation. In this work, we propose AMGenC, a new generative inverse design method for amorphous materials that can guarantee the generation of formally charge balanced samples, with minimal additional computational overhead and without sacrificing inverse design accuracy. AMGenC achieves this through an element noise that gives the generation process a starting point centered around charge balance, and the combination of a per-step soft projection and a final discrete projection for steering the elements toward exact charge balance throughout the generation. We perform extensive experiments on two amorphous materials datasets. Experimental results provide evidence that AMGenC achieves its design goal.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.06109

Low-Degree Learning from Localization Schemes

Gautam Chandrasekaran, Jason Gaitonde, Ankur Moitra, Arsen Vasilyan

原文摘要

The low-degree algorithm is a cornerstone in computational learning theory. For product or Gaussian distributions, it shows that efficiently learnability follows from Fourier concentration. However, a longstanding obstacle towards building such a theory over nonproduct distributions is that we can no longer rely on having closed-form expressions for a good basis of orthogonal functions. This hints that the analysis of the low-degree algorithm might be brittle to the underlying distributional assumptions. We refute this intuition by showing that the low-degree algorithm provably succeeds for a large class of graphical models under mild high-temperature conditions. As an application, for nearly every Ising model that is known to rapidly mix, we obtain learning algorithms for every function class for which the Fourier approach succeeds for product distributions (e.g. low-depth circuits, halfspaces, intersections, monotone, among others) with no significant loss. Our framework is based on a strikingly clean connection with the coordinate-by-coordinate localization scheme of Chen and Eldan introduced for establishing rapid mixing in high-temperature models, as well as other analytical transference principles to product distributions.

cs.LG · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05027

Haptic Shared Control for Multi-Robot Systems

Maxime Bernard

原文摘要

Multi-agent systems offer significant advantages in terms of flexibility and redundancy, enabling the efficient distribution of complex tasks among multiple robots. However, their deployment requires advanced control strategies to ensure optimal cooperation between autonomous agents and human operators. We propose a modification of the global connectivity maintenance algorithm to incorporate measurements taken in agent's local frame, using sensors with limited fields of view. This algorithm, responsible for the autonomous behavior of the multi-robot system, is combined with different adaptive supervision strategies, allowing the user to exert control at varying scales over the entire group. (i) Single Agent Control (S): The operator directly controls a single robot, (ii) Pinning Control (P): The operator imposes constraints on multiple robots to influence the group, (iii) Centroid Control (C): The operator acts on the system's center of mass to steer the entire fleet. In conjunction with the connectivity maintenance algorithm, these methods ensure compliance with inter-agent constraints while providing haptic feedback to the user regarding the system's connectivity state. The effectiveness of these approaches was evaluated through a user study, comparing performance with and without haptic feedback across multiple scenarios tailored to the different control modes.

cs.RO · cs.HC · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.02867

Training with Subword Variants Delays Overfitting in Repeated-Data Language Modeling

Adrian Cosma, Stefan Ruseti, Emilian Radoi, Mihai Dascalu

原文摘要

Subword tokenization introduces a computational layer in language models, where many distinct token sequences decode to the same surface form while preserving meaning, yet induce different internal computations. Despite this non-uniqueness, language models are typically trained using a single canonical deterministic tokenization. In this work, we use non-canonical subword variants as a strictly meaning-preserving form of data augmentation. We introduce a lightweight training architecture that conditions canonical next-token prediction on sampled subword variants via an auxiliary causal encoder and block-causal cross-attention, without modifying the training objective or token interface. In data-constrained pretraining, augmentations with subword variants consistently delay overfitting under repeated data exposure and reduce held-out next-token loss across evaluation datasets. In multilingual fine-tuning, we find that the effectiveness of training with auxiliary subwords depends on tokenizer quality: gains are strongest when canonical tokens are highly compressed and diminish when the tokenizer already over-fragments the input.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05024

RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report

Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Dong Zhang, Zhao Ran, Yang Zhang, Xiaochen Li, Shichang Ju 等 24 位作者

原文摘要

On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast solutions that can perform comprehensive enhancement of RGB photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale DPED dataset consisting of RGB image pairs captured with an old iPhone 3GS smartphone and a professional Canon 70D DSLR camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to enhance Full HD resolution RGB images on both platforms under 300 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05023

HiLo-WAM: Decoupling Long-Horizon Task Evolution and Local Dynamics in World Action Models

Xingyu Wang, Yanjiang Guo, Zhijing Ding, Jiaxin Fang, Zeyu Lai, Jiayu Dong, Weikang Wan, Jianyu Chen 等 10 位作者

原文摘要

World Action Models (WAMs) improve robotic manipulation by jointly modeling visual dynamics and robot actions. However, most existing WAMs model dense short-horizon visual dynamics, capturing local interactions but providing limited long-range task context. Extending prediction horizons increases uncertainty and computation while entangling task-level evolution with fine-grained local dynamics, obscuring their dependencies and distinct roles in action generation. We propose HiLo-WAM, which decouples long-horizon task evolution from local visual dynamics while jointly modeling their interaction with robot actions. A sparse long-horizon visual stream captures historical task context and future evolution, while a dense local dynamics visual stream models short-horizon robot-object interactions. The two streams operate at different temporal scales within a unified dual-DiT architecture and guide actions through structured cross-stream attention. Progressive inference further reduces unnecessary computation through stream-wise partial denoising, joint denoising, and dynamic skipping. Experiments demonstrate strong long-horizon manipulation performance: HiLo-WAM achieves a 93.70% average success rate on RoboTwin 2.0 and a 17.43 progress score on RoboDojo long-horizon tasks, with robust in-domain and OOD performance on the Fourier GR-3 robot. Ablations confirm the complementary contributions of long-horizon task evolution and local interaction dynamics, while temporal-scale analyses highlight the importance of balancing temporal coverage and resolution. Progressive inference further achieves a 2.93x speedup while improving performance.

cs.RO

查看论文
arXiv ↗PDF ↗