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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 20:39 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 21:42 — 2026-11-09 21:42（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 20:39最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 20:38（北京时间）
新论文 · v1arXiv:2610.36082HF 社区推荐

How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning

Johnny Yu, Cyril Gorlla

原文摘要

Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning. On-policy distillation narrows such gaps by supervising a student on its own rollouts, but traditional OPD requires a strong external teacher, and on-policy self-distillation (OPSD) conditions on a full reference solution. We ask how much of that signal is necessary. We present Fin-SD, a localized hindsight self-distillation recipe for multi-step reasoning. Given a problem the student fails, the student itself identifies the first incorrect reasoning step and writes a short critique of that step. We truncate the student's trajectory immediately before the error (aiming to obtain a correct prefix), condition a frozen copy of the student on the same prefix plus the hint, and distill that hint-conditioned teacher into the student over a short rollout under reverse KL. No external model contributes a gradient. We apply Fin-SD to GPT-OSS-20B on a custom multi-step financial reasoning benchmark that requires deriving formula inputs from realistic scenarios via accounting conventions. We find: (i) replacing the critique with a generic-feedback control matches Fin-SD's entire 3.03 pp accuracy gain over the base model on the FinanceReasoning Hard subset, suggesting the gain comes from where supervision is applied, not hint content; (ii) the model writing the hint does not need to be stronger than the model receiving it: hints from same-family GPT-OSS-120B, at roughly 6x the parameters, yield no materially greater benefits than self-written hints; and (iii) Fin-SD matches on-policy self-distillation from full reference solutions on accuracy while generating 9.5% fewer tokens. With Fin-SD, general reasoning on MMLU-Pro and a fourteen-metric compliance audit on FinTrust show no material regression.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.29983

Free-XOR TFHE via Lazy Bootstrapping

Ali Ajorian, Osman Biçer

原文摘要

Gate bootstrapping (GB) is a widely used technique in FHEW-like fully homomorphic encryption schemes, such as TFHE,for evaluating Boolean gates while simultaneously reducing the noise of the resulting ciphertext. However, the computational cost of GB is typically dominated by an expensive blind rotation (BR). [8] proposed a gate bootstrapping framework in which XOR gates can be evaluated simply by adding the two input ciphertexts, resulting in what they call freeXOR. To obtain a functionally complete set of operations, they further designed a GB procedure for evaluating AND gates using two lightweight blind rotations. In this work, we propose a similar gate bootstrapping framework that supports free evaluation of XOR gates while evaluating all symmetric binary Boolean gates, i.e., the 8 gates whose output is identical for the inputs (0,1)and (1,0), using two blind rotations. In addition to providing broader gate support, our construction is substantially simpler than that of [8], both conceptually and in terms of implementation. As a proof of concept, we implemented our approach and compared it with standard TFHE, measuring speedups of about 30% for AES and 34% for SHA.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36079

Closed-Loop Aware Planning via Imitation-Free Speed Scoring for End-to-End Autonomous Driving

Emad Aghajanzadeh, Thomas Schwarzfischer, Marc Kaufeld, Moritz Thoma, Ryan Pégoud, Manoj Rohit Vemparala, Pierpaolo Mori, Nael Fasfous 等 11 位作者

原文摘要

End-to-end autonomous driving has predominantly relied on open-loop imitation learning for training, which presents two limitations. First, expert demonstrations show only one behavior per scenario, so the model cannot learn alternative valid behaviors and, in turn, cannot adapt to user-specified preferences at test time. Second, noise or ambiguity in these demonstrations can produce inconsistent, unreliable supervision for the end-to-end models. Driving is inherently multi-modal: multiple different behaviors can be valid responses to the same scene, and this diversity arises largely from speed rather than path. We introduce a planning paradigm that learns the path through imitation while scoring a set of candidate speeds across multiple criteria with a learned function supervised by physically grounded safety constraints. We realize this paradigm as Closed-Loop Aware Planning for Autonomous Driving (CLAP-AD), a plug-in planning head that integrates with existing end-to-end driving models and, to our knowledge, is the first to enable explicit test-time control over their speed selection without speed-conditioned training. On Bench2Drive-Speed, CLAP-AD sets a new state of the art Speed-Adherence Score of 82.53, topping TFv6, the strongest baseline on this metric, by 12.9 points while retaining strong closed-loop driving performance. On Bench2Drive, it improves driving score by +28.5 and +32.7 over UniAD and VAD, and on NAVSIM v2, built on real-world driving data, EPDMS by +6.1 over its backbone. Project page: https://clap-ad.github.io

cs.RO · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.15830

Ensemble-size-dependence of deep-learning post-processing methods that minimize an (un)fair score: motivating examples and a proof-of-concept solution

Christopher David Roberts

原文摘要

Fair scores reward ensemble forecast members that behave like samples from the same distribution as the verifying observations. They are therefore an attractive choice as loss functions to train data-driven ensemble forecasts or post-processing methods when large training ensembles are either unavailable or computationally prohibitive. The adjusted continuous ranked probability score (aCRPS) is a fair and ensemble-size-unbiased scoring rule when applied to ensembles with forecast members that are interpretable as conditionally independent draws from an underlying predictive distribution. However, distribution-aware post-processing methods that introduce structural dependency between members can violate this assumption, such that aCRPS no longer functions as a fair scoring rule. We demonstrate this effect using two approaches designed to minimize the expected aCRPS of a finite ensemble: (1) a linear member-by-member calibration, which couples members through a common dependency on the sample ensemble mean, and (2) a deep-learning method, which couples members via transformer self-attention across the ensemble dimension. In both cases, the results are sensitive to ensemble size and apparent gains in aCRPS can correspond to systematic unreliability characterized by over-dispersion. We introduce trajectory transformers as a proof-of-concept that ensemble-size independence can be achieved. This approach is an adaptation of the Post-processing Ensembles with Transformers (PoET) framework and applies self-attention over lead time while preserving the conditional independence required by aCRPS. When applied to weekly mean $T_{2m}$ forecasts from the ECMWF subseasonal forecasting system, this approach successfully reduces systematic model biases whilst also improving or maintaining forecast reliability regardless of the ensemble size used in training or real-time forecasts.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.09237

MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics

Neil Janwani, Ellen Novoseller, Vernon J. Lawhern, Maegan Tucker

原文摘要

Multi-objective reinforcement learning (MORL) is a powerful tool to learn Pareto-optimal policy families across conflicting objectives. However, unlike traditional RL algorithms, existing MORL algorithms do not effectively leverage large-scale parallelization to concurrently simulate thousands of environments, thus facing vastly increased computation time. Ultimately, this has limited the application of MORL towards complex multi-objective robotics problems. To address these challenges, we present 1) MORLAX, a new GPU-native, fast MORL algorithm, and 2) MO-Playground, a pip-installable playground of GPU-accelerated multi-objective environments. Together, MORLAX and MO-Playground approximate Pareto sets within minutes, offering 26-271x speed-ups compared to legacy CPU-based approaches and up to 19x speed-ups over prior GPU-based approaches whilst learning superior Pareto front hypervolumes. We demonstrate MO-Playground's versatility by implementing a custom BRUCE humanoid robot environment and learning Pareto-optimal locomotion policies across 6 practical objectives in simulation, such as smoothness, efficiency and arm swinging. Our toolbox is available at https://dynamicmobility.github.io/moplayground/.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36077HF 社区推荐

The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang 等 20 位作者

原文摘要

Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36075

Jaxnasium: Embracing PyTrees For Any-Agent, Cross-Suite Reinforcement Learning

Koen Ponse, Aske Plaat, Thomas M. Moerland

原文摘要

Hardware-accelerated reinforcement learning in JAX has gained rapid popularity in recent years and has proven to be a successful method of scaling online reinforcement learning. The resulting ecosystem, however, is fragmented: environment suites define their own interfaces, and algorithm implementations are typically written for a single suite, a single type of space, and either JAX-native or host-based environments. Here we present Jaxnasium, a library for JAX-based reinforcement learning, aiming to make the field more accessible. Jaxnasium represents observation and action spaces as PyTrees, and uses this structure to build networks and support multi-agent processing. Through this, its near-single-file implementations run on discrete, continuous, image, and composite spaces, as well as in multi-agent environments, without any changes to the algorithm code. The same files serve as readable, research-friendly algorithms, as well as importable algorithms for more applied workloads. Through a minimal Gymnasium-style interface and wrappers for 11 suites, over 300 environments are available on which a small PPO implementation with default hyperparameters is able to run. Additionally, through a simple wrapper, we can run Gymnasium and EnvPool environments with the same algorithm and training loop, with no performance loss compared to architectures specifically built for training JAX algorithms on host-based environments. Jaxnasium further provides tools for multi-seed evaluation, hyperparameter sweeps, and project scaffolding. Jaxnasium is open-sourced at https://github.com/ponseko/jaxnasium

cs.LG · cs.DL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31809

CuraLoc: Repository-Level Fault Localization via Planned Code Inspection

Sangeeta Warrier, Anush Sankaran, Ryen W. White

原文摘要

A bug report describes what went wrong, but rarely where the code should change. Existing repository-level localization methods often let language models iteratively decide what code to inspect next, requiring repeated model calls and substantial token usage. We investigate whether these inspection decisions can instead be planned before source retrieval. In this research, we introduce CuraLoc, which first selects candidate files and represents their symbols using compact behavioral and structural descriptions. In a single planning decision, the model jointly selects starting symbols, chooses code relationships to inspect from each, and forms hypotheses about likely edits. Deterministic retrieval collects the requested source for a final ranking informed by those hypotheses, concentrating model reasoning on choosing and comparing code rather than directing each retrieval step. We demonstrate the efficacy of our proposed approach on the SWE-Bench Lite and Verified datasets. On SWE Bench Verified with GPT-5.2, CuraLoc raises Func@1 from LocAgent's 53.8% to 59.3% while using 90.3% fewer recorded tokens, and also outperforms RepoSearcher (56.2%) and Agentless (39.6%) on Func@1. On SWE-bench Lite, CuraLoc achieves a high 83.8% Func@5 accuracy improving on Agentless by more than 15% in relative accuracy. Additionally, CuraLoc supports different model backbones, with strong localization accuracy demonstrated using both GPT-5.2 and GPT-6 Astra. These results provide evidence that repository-level code inspection can be planned effectively without iterative model-controlled navigation.

cs.LG · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.00924

When is Fine-Tuning Scalable? Certified Recovery from Noisy Data and Linear-Cost Fine-Tuning on Structured Task Shifts

Anastasis Kratsios, Tin Sum Cheng, Bum Jun Kim, Daniel Roy

原文摘要

Transformers often transfer across related tasks with little fine-tuning; we study this question in noisy nonparametric regression for continuous maps $f,g:[0,1]^d\to\mathbb{R}^D$, representing the source and shifted tasks, using a single-query, single-head transformer $\mathcal{T}(\cdot)=V\operatorname{Softmax}(-α(\cdot,K))$ with $\ell^{\infty}$-based alignment scores $α$. Rather than assume that gradient-based training reaches an empirical risk minimizer, we give a model-specific two-stage procedure \textbf{certifying} source-task recovery and out-of-distribution (OOD) adaptation. With high probability, the resulting attention head recovers $f$ to arbitrary accuracy $\varepsilon>0$ in every fixed $L^p([0,1]^d)$ norm, $1\le p<\infty$, from noisy observations. For Lipschitz targets, its rate is minimax-optimal up to logarithmic factors without assuming oracle access to an asymptotic ERM. If $D=1$ and $f$ is Pfaffian than the values matrix factors into $AC$ with $A$ scaling at-most linearly $\mathcal{O}(\varepsilon^{-1})$ in the reciprocal approximation error $\varepsilon>0$. Importantly, our training procedure encodes all our identified (potentially) shared geometric structure from $f$ only into the values matrix factor $C$ and the keys matrix $K$ allowing for rapid access, and all $f$-specific structure only into $A$. Our main result concerns the OOD phase; where we identify geometric structures, which if shared by the source $f$ and OOD $g$ task; then only only the values matrix factor $A$ needs to be fine-tuned to guarantee an $L^p$-recovery of $g$. Critically, fine-tuning only $A$ is a convex problem which involving an \textit{at-most linear} number of parameters $\mathcal{O}(\varepsilon^{-1})$; dramatically cutting down on the worst-case scaling of $\mathcal{O}(\varepsilon^{-\mathbf{d}})$ unavoidable in the source-training phase.

stat.ML · cs.LG · cs.NE · math.NA · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36068HF 社区推荐

Rollback: Experience Backtracking in World Models for Policy Improvement

Jiayi Luo, Yang Zhang, Liliang Chen, Nan Wang, Chen Gao, Boxiang Qiu, Zhuoxuan Li, Baorui Peng 等 16 位作者

原文摘要

Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as forward-only surrogates of the physical environment, leaving untapped a capability no physical environment affords: rewinding to past decision points to explore counterfactual futures. We introduce Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines: it rolls back to critical decision points, branches into alternative actions, and contrasts their outcomes to attribute success to individual decisions. This concentrates imagination where it matters most and distills counterfactual outcomes into fine-grained, action-level supervision without a separately learned value model. We build a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle: real-world experience continually sharpens the world model, and a sharper world model in turn drives further policy improvement. We term the world-model side of this cycle test-time physics grounding, a capability that hand-built physics simulators lack: while the world model serves as the training environment, real transitions from the policy it trains correct its dynamics through a lightweight LoRA pipeline. Experiments on three challenging real-world tasks show that Rollback improves success rates over the strongest baseline by an absolute 10.67%, 11.11%, and 11.85% on block extraction, ball tossing, and tabletop curling, respectively, while achieving more stable improvement throughout training. Although initialized from teleoperated demonstrations far below human level, Rollback surpasses the average success rate of human players on both ball tossing and tabletop curling within 8 hours of training.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36034

The proton structure one mode at a time: a Neural Tangent Kernel analysis of a DIS fit

Amedeo Chiefa, Luigi Del Debbio, Richard Kenway

原文摘要

We study the training dynamics of a feed-forward neural network (NN) through the analysis of the neural tangent kernel (NTK) in a phenomenologically relevant fit of parton distribution functions (PDFs) from deep inelastic scattering (DIS) data. The exact integration of the gradient flow derived in a previous single-flavour analysis is generalised to the multi-flavour case, yielding an analytical perspective on the relationship between data and methodology during training. The Shapley value recently used in the context of PDFs is derived within our statistical framework for observables that depend linearly on the PDFs, and we outline a geometric interpretation of training. We expose the role of gradient-based optimisation algorithms and of the parametrisation in the regularisation of the ill-posed inverse problem that affects the determination of PDFs from experimental data, demonstrating that the regularisation amounts to the incremental inclusion of NTK modes, each learned at the timescale set by the corresponding eigenvalue. We find that only a few leading modes of the NTK are necessary to reconstruct the target PDFs, while the noise of the data is carried by the sub-leading ones learned at later stages of training. Finally, we consider the impact of the initialisation on the training dynamics, and recover a transient behaviour observed in the previous analysis and in the machine learning (ML) literature. Beyond sharpening our understanding of the training dynamics, our framework can be applied to other parametrisations (such as fixed functional forms) and ML applications in physics, as well as to stress tests in the presence of inconsistent data.

hep-ph · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35868

Retriever-Free Retrieval: Navigating Documents with Decision Models

Chao Wan, Paul Jünger, Beixi Du, Bodong Liu, Navaneetha Krishnan, Kilian Q. Weinberger

原文摘要

While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35865

Center-of-Mass Interpretation of Evolution Strategies

Akshat Gupta

原文摘要

Evolution strategies (ES) update a model by sampling a population of perturbed copies, scoring each one, and moving in the reward-weighted direction of the perturbations. This update is usually presented as an estimate of a smoothed gradient. We present a geometrical interpretation of this update instead. Treat each perturbed model as a particle and its reward as the particle's mass. Before scoring, every particle has the same mass and the population balances at its centroid. Once rewards are assigned, it balances at its reward-weighted center of mass instead. We show that the mean-subtracted ES update is exactly this displacement, scaled by a scalar factor that depends on the mean reward, for any finite population. The physical reading needs nonnegative rewards, which can always be arranged by adding a constant to every reward without changing the update. In the limit of a large population or under antithetic sampling, the centroid sits on the model itself, so ES has an even simpler geometric interpretation: from its current location, the model moves towards the reward-weighted center of mass of its own population. The same picture explains what subtracting the mean reward does: it changes the point from which the displacement is measured, from the model to the sampled centroid. Our contribution is an intuitive, geometric way to visualize an ES update, exact for any finite population.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35862

Learning Force-Reactive Humanoid Loco-Manipulation

Sihang Li, Xiaofeng Guo, Jinkun Cao, Charlie Cheng, Ruihan Yang, Chen Feng, Guanya Shi, Haozhi Qi

原文摘要

Many everyday tasks require controlling contact force as well as motion. On a humanoid, this force must often be coordinated across both hands and the whole body, and cannot be specified by kinematic trajectories alone. Therefore, we present FLORE, a framework for learning force-reactive humanoid loco-manipulation. We collect robot-free demonstrations using two force-sensing UMI-style handheld grippers for hand motion and contact wrenches, and wearable trackers for body motion. A force-reactive diffusion policy takes vision, proprioception, and measured wrenches as input, then predicts actions and per-hand force commands. A hybrid compliance whole-body controller with force tracking executes these commands while maintaining balance: an integral of the force error measured by real force/torque (F/T) sensors lets each hand track force accurately along the commanded direction and remain compliant along the others. In simulation, the controller tracks per-hand force commands of varied magnitude and direction, with little loss in whole-body motion accuracy. Across three contact-rich tasks on the robot, the force-reactive policy succeeds in 80% of rollouts, compared with 26.7% for a position-only policy trained on the same demonstrations and executed by the same controller. For more details, please visit our website: https://louis-leee.github.io/FLoRe/.

cs.RO · cs.AI · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35859

An $O(n^{0.1537})$-Coloring Algorithm for 3-Colorable Graphs

Kaisei Deguchi, Ken-ichi Kawarabayashi, Hirotaka Yoneda, Masataka Yoneda

原文摘要

We present a polynomial-time randomized algorithm that colors every $n$-vertex $3$-colorable graph with $O(n^{0.1537})$ colors. This improves upon the previous bound of $O(n^{0.1954})$ colors by Bansal, Huang, and Lee (SODA '27). To achieve this result, we introduce a new algorithmic framework for finding a large independent set from a solution to the vector coloring SDP. Combined with the (combinatorial) dense-progress algorithm of Kawarabayashi, Thorup, and Yoneda (STOC '24), this framework yields an $n^{1/6 + o(1)}$-coloring algorithm. Furthermore, we strengthen the SDP-based algorithm specifically for 3-colorable graphs to achieve $O(n^{0.1537})$ colors.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.15198

SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings

Shuai Wang, Zihan Qian, Ke Zhang, Jiangyu Han, Zikai Liu, Xiaoyang Yu, Haoyu Li, Marc Delcroix 等 12 位作者

原文摘要

We introduce the REAL-TSE Challenge, an IEEE SLT 2026 satellite challenge on target speaker extraction~(TSE) from real conversational recordings. Given a multi-speaker mixture and one or more enrollment utterances from a target speaker, participating systems must recover only the target speech. Unlike simulated read-speech benchmarks, REAL-TSE evaluates Mandarin and English recordings that contain natural overlap, reverberation, noise, channel mismatch, and conversational dynamics. The challenge defines two complementary tracks: an Online track for low-latency streaming extraction and an Offline track for full-context processing. Systems are evaluated with Token Error Rate (TER), Speaker Similarity (SpkSim), DNSMOS, and target-speaker activity F1. This overview paper describes the task definition, datasets, baselines, evaluation protocol, submitted systems, condition-wise findings, and lessons for future real-world TSE benchmarks.

eess.AS · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.22678

BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering

Jinghong Chen, Jingbiao Mei, Guangyu Yang, Bill Byrne

原文摘要

A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a language model to generate an answer. While simple, this strategy can obscure the contribution of individual documents, making attribution difficult and contributing to the ``lost-in-the-middle'' effect, where relevant information in long contexts is overlooked. Concatenation also scales poorly: computational cost grows quadratically with context length, a problem that becomes especially severe when the context includes visual data, as in visual question answering. Attempts to mitigate these issues by limiting context length can further restrict performance by preventing models from benefiting from the improved recall offered by deeper retrieval. We propose Bayesian Ensemble Retrieval-Augmented Generation (BERAG), along with Bayesian Ensemble Fine-Tuning (BEFT), as a RAG framework in which language models are conditioned on individual retrieved documents rather than a single combined context. BERAG treats document posterior probabilities as ensemble weights and updates them token by token using Bayes' rule during generation. This approach enables probabilistic re-ranking, parallel memory usage, and clear attribution of document contribution, making it well-suited for large document collections. We evaluate BERAG and BEFT primarily on knowledge-based visual question answering tasks, where models must reason over long, imperfect retrieval lists. The results show substantial improvements over standard RAG, including strong gains on Document Visual Question Answering and multimodal needle-in-a-haystack benchmarks. We also demonstrate that BERAG mitigates the ``lost-in-the-middle'' effect. The document posterior can be used to detect insufficient grounding and trigger deflection, while document pruning enables faster decoding than standard RAG.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35857

Do vision models know that three is three?

Ankit Sonthalia, Arnas Uselis, Seong Joon Oh

原文摘要

Do vision models encode the transition $2{\to}3$ the same way whether it appears in handwritten digits or in hand gestures, and do they "understand" that clean${\to}$dirty is the same transformation regardless of whether it is applied to a kitchen or a carpet? The linear representation hypothesis (LRH) answers this for language models: concept changes correspond to directions in (language) embedding space. In vision, the same concept can manifest in visually unrelated "regimes" that rarely co-occur: images of digits and hands do not share much in common in pixel space. To understand whether vision models still encode the underlying abstract concepts, we study 46 vision encoders across architectures, training objectives, and scales, on 10 concept families including numerosity, age, object identity, and MIT-States attributes. Within each regime, we find statistically significant concept directions near-universally across our tested models. However, two distinct regimes do not always share the same concept direction. Several models learn multiple linear structures for the same concept transition, split across regimes. We call this phenomenon "fragmented linearity": strong local linearity coexisting with near-absent global linearity. Fragmentation is, however, not fixed: models with stronger local linearity progressively escape it (local-global linearity correlated with $τ\in [0.38, 0.89]$ across all concepts), and where global linearity does emerge, concept directions can transfer as linear probes across regimes.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35856

On the stability of learning

John J. Vastola

原文摘要

Learning algorithms are usually analyzed under the assumption that informative gradients are continuously available. But this is not always true---learning signals in biological neural networks, for example, may be sparse, local, and only intermittently available at any given synapse. In this work, we show that if gradient information is noisy and only intermittently available, learning may be unstable. In particular, even if average learning dynamics converge to the correct optimum, variance in learning may be asymptotically infinite. We explore this point in a number of analytically tractable settings, including single-layer and multi-layer linear networks, and derive explicit conditions under which learning is stable. These conditions complement, but are conceptually distinct from, existing conditions related to the stability of stochastic gradient descent. Our work demonstrates that unbiased credit assignment is not enough for reliable learning; sufficiently frequent and informative feedback is also required, which yields an additional constraint on models of biologically plausible learning.

q-bio.NC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35854

FL4N: Feed-forward Latent Model for 4D Novel View Synthesis

Eunbeen Hong, Hyeonseo Yu, Honggyu An, Jooho Son, Hyunah Ko, Soowon Son, Chaehyun Kim, Jahyeok Koo 等 11 位作者

原文摘要

4D novel view synthesis (NVS) aims to render dynamic scenes across viewpoints and timestamps, which requires jointly inferring 3D structure and temporal dynamics. Existing monocular feed-forward methods often rely on explicit 4D Gaussian representations, which are prone to temporal inconsistency and severe rendering artifacts. We present FL4N, the first feed-forward latent 4D NVS model. Instead of relying on explicit 4D primitives, FL4N encodes a 4D scene prior into a unified latent representation across space and time. Our core insight is that learning temporal dynamics as residuals on top of a pretrained static latent prior enables effective 4D modeling with limited dynamic training data. To this end, we introduce a lightweight dynamic encoder that leverages static scene features to disentangle object motion from camera-induced parallax. Trained solely with an image synthesis objective, FL4N achieves state-of-the-art 4D NVS quality while rendering in real time. Its learned latent representation generalizes to real-world videos and disentangles viewpoint from time.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35851

Nonprehensile Robotic Catching Using Virtual Constraints

Aakash Khandelwal, Ranjan Mukherjee

原文摘要

The problem of nonprehensile robotic catching is addressed using virtual nonholonomic constraints (VNHCs); the motion of the robot end-effector is designed and controlled directly in terms of the states of the object before it is caught on the surface of the end-effector. In contrast to contemporary approaches, our approach avoids the need for object trajectory prediction, and consequent time-varying robot trajectory generation. With a focus on the planar case, we demonstrate that our VNHC approach can be used to catch an object on an end-effector at a desired height, with minimal relative normal velocity at the contact instant. Moreover, the VNHC function depends only on the desired catching height, and the same VNHC can be used for a range of initial conditions. We use model predictive control (MPC) to bring the object and end-effector to rest at a desired location after contact is made. The approach is validated in simulation.

eess.SY · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35850

OSWAM: An Effective World Action Model with One-Step Action Generation

Guowen Zhang, Liyi Chen, Xu Hu, Pengfei Wang, Jingfan Chen, Chenhang He, Lei Zhang

原文摘要

Direct-policy World Action Models (WAM) have demonstrated the benefits of decoupling action generation from explicit future visual prediction for efficient inference in autonomous driving and embodied control. However, they still require tens of denoising steps to achieve competitive action quality, incurring substantial latency and hindering real-time deployment. Simply reducing the number of denoising steps will collapse the nonlinear multi-step denoising trajectory into coarse updates, substantially degrading action quality. To reduce the denoising steps while enabling real-time action generation, we present an effective world action model with one-step action generation, namely OSWAM, for autonomous driving and embodied control. We argue that it is the absence of structured action priors in random noise initialization that forces direct-policy WAMs to recover coherent action sequences through iterative denoising. Hence, we construct imagination tokens to initialize the diffusion process, providing physical priors and action-conditioned representations. We further introduce privileged information distillation with future conditioning to enhance future-aware action generation. As a result, OSWAM can efficiently and effectively generate high quality actions in just one diffusion step. Our experiments demonstrate that OSWAM achieves comparable or even better results in both autonomous driving and embodied control than direct-policy WAM and Joint-WAM that require tens of steps. It obtains approximately $3\times$ speedup over direct-policy WAM baselines and supports real-time compiled inference with latency as low as 40ms on an NVIDIA RTX 5090 GPU. The project page is available at https://gwenzhang.github.io/OSWAM/

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35847

Patient-specific rubric-based evaluation of large language models across longitudinal cancer care

Wei-Wei Zhang, Pengkai Wang, Yan Li, Zhijie Sang, Guan-Qun Zhou, Jun-Yan Li, Shu-Han Zhou, Pei-Wen Liu 等 16 位作者

原文摘要

Large language models (LLMs) show promise in specialty medicine, yet existing evaluations largely focus on isolated clinical encounters rather than tracking how clinical responsibilities evolve across a longitudinal care pathway. Here we introduce NPC-RubricBench, a phase-aware benchmark for evaluating multistage clinical reasoning across the cancer care continuum, using nasopharyngeal carcinoma as a defined disease context. Curated from longitudinal records of 405 patients across two cancer centers, the benchmark comprises 941 patient-phase units across six sequential care phases and 17,688 patient-specific atomic criteria spanning five evaluation dimensions, with each assessment strictly restricted to decision-time clinical evidence. Evaluating 30 general-purpose and medical LLMs revealed that strong diagnostic performance does not carry over to downstream care. We evaluated 30 general-purpose and medical LLMs, showing that high diagnostic performance did not translate into improved downstream care. Instead, the dominant failure modes reversed across phases. Explicit decision errors dominated anatomical staging at 48.2%, whereas decision omissions dominated initial work-up and post-treatment follow-up at 33.4% and 30.4%, respectively. In the evaluated model set, medically adapted models showed higher omission rates than general-purpose models. Moreover, varying query granularity exposes a critical specification trade-off: broad open-ended requests degrade Decision Quality across all 30 models, while more detailed, checklist-like prompts raise Decision Quality but reduce Evidence Faithfulness and Safety Adherence. Furthermore, NPC-RubricBench demonstrates that static diagnostic benchmarks are insufficient to ensure consistent clinical reliability over time, highlighting the importance of phase-adaptive safeguards in multistage medical AI.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35846

Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR

Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar

原文摘要

Expanding multilingual ASR systems to new languages is challenging when adaptation must preserve previously supported languages without replaying source-language training data. We study this problem in connector-based Speech LLMs, where a trainable connector maps speech representations into a frozen large language model. We evaluate target-update construction and merging strategies for adapting the connector while preserving source-language performance. In single-target expansion, target-only fine-tuning and standard TIES merging learn new languages but cause severe source-language forgetting, while SSU-Wanda+TIES gives the best source-preserving trade-off. In multi-target expansion, update merging provides stable source retention, whereas recursive expansion can improve target adaptation under favorable orders but is highly order-sensitive. These results show that multilingual ASR expansion requires balancing target acquisition, source retention, and interactions among target-language updates.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35845

Work Agents: Systems, Capabilities, and Optimization

Zishan Xu, Enjun Du, Mingqi Gao, Cheng Yang, Junhao Shen, Zirong Chen, Zhiyuan Yao, Yifu Guo 等 16 位作者

原文摘要

As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows. However, existing research lacks a unified perspective on how agents reliably accomplish delegated work. To address this gap, we present a work-centric, system-level perspective that views work agents as systems combining foundation models and runtime harnesses to execute tasks in stateful workspaces and deliver verifiable outcomes. We introduce two complementary dimensions, work persistence and work openness, to characterize working conditions, and classify digital work into five forms according to task scope and organization. Building on this framework, we identify five core capability families required for reliable work execution and examine approaches to model optimization, harness optimization, and their joint optimization. We further analyze existing evaluation methods and metrics from the perspective of work outcomes. Finally, we discuss future research directions, including sustained work delegation, adaptation to open environments, and the interaction between work execution and capability improvement. This paper provides a unified framework for understanding, optimizing, and evaluating work agents, supporting the development of systems capable of delivering reliable, verifiable, and practically valuable work outcomes.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35842

MedVTok: A General-Purpose Medical Visual Tokenizer

Chenglong Ma, Yuanfeng Ji, Junzhi Ning, Jiyao Liu, Yujie Wei, Shaohao Rui, Chaoyang Zhang, Wenjie Li 等 21 位作者

原文摘要

Multimodal medical AI requires a common visual interface for encoding heterogeneous imaging evidence for patient condition modeling. However, existing medical visual tokenizers are often tied to a specific dimension and imaging modality, forcing multimodal systems to rely on fragmented and poorly reusable representations. We introduce MedVTok, a general-purpose visual tokenizer that maps 2D images and 3D volumes from diverse imaging modalities into a unified token space. Building such a tokenizer poses two key challenges: preserving anatomical structure across dimensions and capturing clinical semantics across modalities. To this end, MedVTok introduces (i) slice differential regularization, which explicitly models inter-slice anatomical coherence missing in previous per-pixel/per-voxel supervision, and (ii) multi-expert representation alignment, which integrates knowledge from multiple medical expert encoders while retaining modality-specific complementary knowledge. Trained on 28M images and 70K volumes across 9 imaging modalities, MedVTok supports classification, retrieval, segmentation, synthesis, visual question answering, and medical report generation through a single tokenizer. Across 24 benchmarks, MedVTok achieves state-of-the-art performance, demonstrating a scalable token interface that unifies medical image dimension, modality, and task usage.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35840

ACARE: Agent-Context-Aware Reranker for Iterative Search

Sahel Sharifymoghaddam, Yauhen Babakhin, Reza Esfandiarpoor, Oliver Holworthy, Jimmy Lin, Bo Liu

原文摘要

In agentic search, a document can match an agent-generated sub-query without helping answer the user's original question. Conventional rerankers score documents against the sub-query alone, overlooking the broader task and the agent's reasoning. We introduce the Agent-Context-Aware Reranker (ACARe), a compact 4B LLM trained to rerank documents using this context when available. Across multiple benchmarks and agent families, ACARe improves retrieval quality over its base reranker while reducing search effort. These benefits extend to answer generation: ACARe improves accuracy and reduces searches over no reranking, while matching or exceeding the base reranker's mean accuracy with more precise evidence. It also helps smaller agents narrow the retrieval-quality gap to larger agents, showing how better retrieval tools can make smaller agents more effective. The model, training data, and code will be released soon.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.20967

Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization

Jung-Hoon Cho, Heling Zhang, Siqi Du, Roy Dong, Cathy Wu

原文摘要

Generalization is crucial for modern control, but learning across tasks can be costly. Recent work shows that zero-shot transfer, in which a controller designed for a source task is directly deployed to a target task, can achieve strong performance. We formalize task-space complexity, which characterizes the difficulty of achieving sufficiently good performance across a collection of tasks, by casting source selection as a covering problem. We provide bounds on the complexity and demonstrate its applicability.

cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35833

Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization

Shreya Meel, Sennur Ulukus, Itzhak Tamo

原文摘要

In federated learning (FL), secure aggregation enables a server to compute the sum of local model updates of $N$ clients, without revealing any information on the individual model updates to the server, beyond their sum. Different clients may be subject to heterogeneous bandwidth constraints, and consequently may choose different numbers of quantization levels to represent the information they send. Most secure aggregation works require the clients to project the values of their update parameters to a common finite group (or field), which does not directly accommodate heterogeneous precision constraints on their transmitted masked updates. Existing approaches of secure aggregation with heterogeneous quantization levels reveal partial aggregates of model-updates, and can reveal segments of individual model updates, under certain dropout and client-server collusion patterns. To prevent this privacy breach, we propose an information-theoretic secure aggregation scheme that tolerates client drop-outs, and up to $T$ semi-honest clients that collude with each other and with the server, under heterogeneous quantization at clients. Our protocol utilizes the $(T+1, N)$ threshold black-box secret sharing construction, where secret shares of the client updates, despite belonging to distinct algebraic groups owing to different quantization, are generated from identical linear integer systems.

cs.IT · cs.CR · cs.LG · cs.NI · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35832

Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy

Yifei Yao, Yude Zou, Guanbo Jiao, Xing Gao, Ning Gao, Yukai Wang, Jiantong Chen, Zihou Zhu 等 15 位作者

原文摘要

Frontier multimodal large language models (MLLMs) can control robots without robot-specific training, but how their capabilities compare and interact with post-trained vision-language-action (VLA) and world action model (WAM) policies across manipulation demands remains to be thoroughly evaluated. In this report, we evaluate GPT-6-Astra on EBench as the core of an agent that controls a robot through an agent harness under the same visual and proprioceptive observation protocol as post-trained policies. We study two agent configurations: direct control, in which the agent generates waypoint commands directly, and harness with policy, in which it can also invoke a post-trained VLA or WAM policy for action execution. Under direct control, the agent achieves competitive overall performance relative to post-trained policies. It leads on short-horizon tasks and exhibits the least performance variation across generalization dimensions, whereas it underperforms post-trained policies on long-horizon tasks, tabletop manipulation, and high-precision contact-rich tasks. In the harness with policy, invoking a post-trained VLA or WAM combines the complementary strengths of both components, raising overall task success to the level of the strongest compared post-trained policies while substantially reducing token cost. However, performance remains below the per-task upper bound of the standalone components due to suboptimal policy invocation, fixed-instruction execution without subgoals, and grasp disruption when the agent resumes control. Overall, our study characterizes the capability boundary of a frontier MLLM agent and suggests directions for improving future agent harness design. Project page: https://internrobotics.github.io/EBench-Astra-Tech-Report/

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗