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：2026-11-10 00:52 · 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 2026-11-09 01:19 — 2026-11-10 01:19（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：2026-11-10 00:52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 15,506 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 00:50（北京时间）
新论文 · v1arXiv:2611.01966

Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected?

Yuntong Hu, Hongji Pu, Zimo Li, Ruomeng Li, Xiaotong Liu, Ziyuan Qin, Qiyue Li, Liang Zhao

原文摘要

Coding agents can now rewrite repository-scale codebases while preserving tested behavior, creating a new challenge for plagiarism detection, license auditing, and software provenance. We ask whether such rewrites can still be traced to their source. Existing clone benchmarks emphasize fragments and bounded edits, while repository-transformation benchmarks evaluate functional correctness rather than provenance. Moreover, ranking the most similar source does not establish derivation when independent implementations can be similarly close. We define repository-level agentic code laundering and introduce Launder-Bench, to our knowledge the first repository-level benchmark for provenance under agentic rewriting, constructed from 282 real-world repositories. A source-hidden reconstruction protocol decomposes source behavior, reconstructs modules and repository structure, and retains rewrites only after execution-based verification. We evaluate the same provenance problem in two complementary settings: Launder-Bench-Pair contains 1,128 pairwise instances asking whether two repositories share provenance, while Launder-Bench-Attr contains 229 source-attribution instances asking which candidate is the source, with abstention when evidence is insufficient. Measured same-domain independent repositories establish how much similarity can arise without shared provenance and provide detector-specific reference bands. Existing methods remain far from saturating Launder-Bench: the strongest static method reaches only 0.66 AUROC on pairwise detection, while repository encoders rank the true source first on up to 22% of attribution queries but earn calibrated attribution credit on only 1-2%. These results reveal a systematic gap between relative code similarity and source-specific provenance evidence, providing a reproducible target for provenance detection under agentic rewriting.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01965

OC-OPD: Observation-coordinated Supervision for On-Policy Distillation

Ruoran Xu, Yilun Zhao, Ziyu Chen, Arman Cohan

原文摘要

Reverse and forward Kullback--Leibler (KL) divergences provide complementary supervision in on-policy distillation: reverse KL refines the student's active token rankings, and forward KL allocates mass to teacher-supported candidates. At student-generated prefixes, we form a four-observation matrix by treating the student and teacher as both candidate sources and evaluators. The diagonal self-observations measure uncertainty, while source-centered cross-observations recover the two KL objectives. We establish an exact identity equating the Fisher inverse-metric coupling of their logit gradients with the sum of these contrasts, yielding a common local descent direction for distinct positive distributions. Observation-coordinated on-policy distillation (OC-OPD) uses observations to set preferences, closed-form bargaining to coordinate gradients, and distributional discrepancy to scale the update. Across three heterogeneous student settings (non-thinking generation, thinking generation, and base-model initialization), OC-OPD achieves strong gains in mathematical reasoning and transfers effectively to out-of-distribution scientific question answering and code generation. Our code is publicly available at: https://github.com/RuoranXu/OC-OPD.

cs.LG · cs.AI · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.08869

OntoKG-EQ: Evidence-boundary auditing for analytical knowledge graphs

Furqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf

原文摘要

An analytical knowledge-graph result can be supported in its ambient graph while its delivered explanation omits deciding observations. OntoKG-EQ connects competency-question requirements to an executable audit of ambient observations, declared finding support and delivered evidence. A bounded declarative interpreter distinguishes positive, false and unknown numerical status, with same-witness unit readiness reported separately. A public-data application reconstructs England's August 2026 provider-level referral-to-treatment statistical screen. Independent source recomputation reconciles 532 providers with the publisher workbook: 91 meet the inclusive 92% threshold and 441 do not. One additional roster entry remains unavailable rather than zero-filled. All 533 application frames agree with an independently implemented standards-based validation and availability baseline. Transfer requires a disclosed source adapter and arithmetic compilation, but no change to the core interpreter. Twenty-six constructed analytical cases yield 78 status/readiness agreements. Actual financial release replay reproduces two omitted-volume defects: support and delivery suffice for 19 of 21 original findings and all 21 repaired findings after interface adaptation. A separate replay agrees on 487 overlapping financial records. Source audits expose scaling errors and unresolved comparator and temporal assumptions, so financial examples do not establish authenticated market effects. The contribution is a reproducible analytical audit interface and source-reconciled application, not new sufficiency logic or first evidence-boundary isolation. Historical ratings measure preference only; objective human audit benefits and independent production deployment remain untested.

cs.ET · cs.AI · cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01962

Object-Only Is Not Context-Free: A Counterfactual Diagnostic for Context Removal in Object Retrieval

Boaz Meivar, Shai Avidan

原文摘要

Object-centric retrieval pipelines often mask the background before pooling backbone features, aiming for a descriptor that reflects the object rather than its scene. Whether this truly yields an object-only descriptor, however, is rarely tested. We introduce the Keyhole Aperture Probe (KAP), a counterfactual diagnostic that repurposes the ground-truth masks of existing panoptic segmentation datasets (COCO, ADE20K) for retrieval: it holds the pooled object region fixed and varies only the pixels outside it, summarizing a backbone's context dependence in a single number. We find that the pooled object region has already integrated its surround. Replacing the context, with a neutral fill or even a different real scene, changes the descriptor, and when retrieval fails under a blank fill, the descriptor matches plain-background images rather than its own object. Object-only is not context-free. Across ten modern backbones, object-only descriptors retain only about a quarter to two-thirds of their full-image accuracy, and the effect is not unique to Transformer self-attention: a convolutional backbone shows it too. The dependence is also reducible: a lightweight adapter that encourages the descriptor to stay stable as context is removed lowers it and improves full-image instance retrieval on INSTRE, transferring to ILIAS with accuracy improved or preserved. A matched contrastive-fine-tuning control does not reproduce those gains. We release KAP as a simple, backbone-agnostic evaluation protocol to measure and reduce this dependence before deployment.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:1903.07745

Attention-Based Multiple Instance Regression for Remote Sensing

Thomas Uriot

原文摘要

In this paper, we propose a novel approach to tackle the multiple instance regression (MIR) problem. This problem arises when the data is a collection of bags, where each bag is made of multiple instances corresponding to the same unique real-valued label. Our goal is to train a regression model which maps the instances of an unseen bag to its unique label. This MIR setting is common to remote sensing applications where there is high variability in the measurements and low geographical variability in the quantity being estimated. Our approach, in contrast to most competing methods, does not make the assumption that there exists a prime instance responsible for the label in each bag. Instead, we treat each bag as a set (i.e, an unordered sequence) of instances and learn to map each bag to its unique label by using all the instances in each bag. This is done by implementing an order-invariant operation characterized by a particular type of attention mechanism. This method is very flexible as it does not require domain knowledge nor does it make any assumptions about the distribution of the instances within each bag. We test our algorithm on five real world datasets and outperform previous state-of-the-art on three of the datasets. In addition, we augment our feature space by adding the moments of each feature for each bag, as extra features, and show that while the first moments lead to higher accuracy, there is a diminishing return.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01960

Event-Based Optical Flow Constraint via Time-Sliced Plane Fitting

Masaki Koike, Yusuke Kameda, Shunichi Sato, Takayuki Hamamoto

原文摘要

Event-based optical flow estimation using spatiotemporal planar approximation inherently assumes constant velocity and tends to average out temporal velocity variations. In this paper, we propose a flow estimation method that extends this planar approximation along the temporal axis. The resulting event-based optical flow constraint allows existing variational optical flow formulations to model temporal motion variation. Specifically, we partition the space-time volume into sub-intervals and apply a two-step planar approximation to track object edges consistently. Moreover, a spatial compensation mechanism and a temporal regularization term are incorporated to compensate for edge displacements and temporally stabilize the flow estimation, respectively. The experimental results show that modeling temporal motion variation improves flow estimation accuracy over conventional methods.

cs.CV · eess.IV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01958

Answering Without Arriving: An Evidence Audit for Embodied Question Answering

Shubh Garg, Divyansh Pandey, Niyati Rawal, Vedant Khandelwal, Amit Sheth

原文摘要

Embodied question answering asks an agent to navigate, observe, and then answer questions about what it saw, yet answer accuracy alone cannot tell whether any of this happened. A plausible answer can come from the question, the room label, or the answer choices, and a correct answer does not show that the supporting observation was ever made. We present a multi-room benchmark whose 200 test episodes and 800 questions are stratified by route extent, with an evaluation ladder that holds the questions fixed while varying only the evidence supplied to the answerer, from text-only probes through closed-loop agents to replay of the reference trajectory. Questions are generated from symbolic records of rooms, visible objects, and frames, so every answer can be traced to the observations that support it. A closed-loop vision-language agent reaches no target in 200 episodes yet answers 45.5% of questions, within 0.1 points of the same model given no images; replaying the reference trajectory raises the same model to 57.4%, so the evidence exists along the route but is not gathered. A family-level audit then shows that access to evidence is not the same as use of it. Four of eight families are largely answerable from text, one cites frames that cannot establish its own answer, and the oracle conditions reach 59.5% on Rooms-visited by counting the supplied images. Evidence acquisition, answer coverage, and shortcut sensitivity must therefore be established before an accuracy gain can be credited to memory.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.20812

B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet

Jaedong Hwang, Kathleen Zhang, Wei Dai, Konstantinos Kontras, Maarten Vanmarcke, Maarten De Vos, Ila Fiete, Paul Pu Liang

原文摘要

EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical and brain-computer interface tasks. Existing models typically discretize the continuous multi-channel EEG waveform into patches or codebook tokens and train a transformer with masked self-supervision. Recognizing that this discretization fragments continuous brain rhythms and obscures fine-grained temporal dynamics, we present B[FM]$^2$(Brain Foundation Model via Flow Matching), whose inductive bias aligns with the data by pretraining directly on the raw signal using continuous-time flow matching without patches, tokenization, or masking. However, multi-channel EEG signals pose an architectural challenge for flow matching: time is densely sampled and highly autocorrelated (thousands of timepoints), while the electrode axis is short (tens of channels) at distinct scalp positions. To address this time-electrode asymmetry, we introduce SplitUNet, a velocity network that factorizes each block into separate 1D temporal and 1D electrode convolutions and downsamples only along time, preserving electrode topology throughout the hierarchy. B[FM]$^2$ sets a new state of the art on $7$ of $9$ standard downstream EEG classification tasks, using a pretraining budget of only $36{,}895$ segments ($\approx$ 307h), 1-2 orders of magnitude ($\approx$ 30x) less than required by existing EEG foundation models. Further, it generates synthetic EEGs that two board-certified neurologists cannot distinguish from brain data (Cohen's $κ= -0.096$). https://jd730.github.io/projects/BFM2

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01954

Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs

Ruisheng Sun, Jiaqi Shao, Weijia Han, Linxi Ju, Yunzhen Zhang, Binyan Sun, Rong Chen, Benjamin Blas Maristany 等 12 位作者

原文摘要

Traditional interactive narrative systems offer strong authorial control and structural coherence but often restrict player agency. In contrast, LLM-driven narratives enable open-ended generation and greater flexibility, yet frequently suffer from inconsistency and diminished narrative control. To navigate this trade-off, we propose a hybrid narrative framework that dynamically balances pre-authored content with real-time LLM generation via semantic similarity alignment. Additionally, sustaining narrative quality over extended gameplay remains a core challenge in LLM-based storytelling. To address this, we introduce a self-evolving, feedback-driven optimization framework that leverages in-context learning to iteratively refine prompts, eliminating the need for manual prompt engineering. Through a case study and participant-based evaluation, we show that our framework enhances narrative coherence while preserving player agency, effectively aligning generated content with both authorial intent and evolving player behavior.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01953

Step-Zero Attack: Agent Safety Before Observability

Tian Qin, Yuhang Jiang, Junzhe Chen, Lit Sin Tan, Lijie Wen

原文摘要

Existing attacks and defenses for coding agents act once content enters the model context: injected text persuades the model, and guards inspect what the model reads. Yet to judge whether processing an unknown archive, network response, or image is safe, an agent often must process it first, and that step can do harm before any content reaches the model. We call this first processing Step Zero, and harm done by it a Step-Zero attack. Across seven harnesses and six models, each agent received only a path or URL to a crafted input, paired with a benign twin showing the same visible fields. Step Zero is where most agents are already unsafe: 32/42 harness-model pairs overran a 4 MiB disk budget, 26/42 before the model saw any member, and four of the six models did so in every round (84/84), so the damage precedes any model-side defense. Every twin stayed within budget, so the attacker's bytes alone cause the harm. On network and image inputs the risk moves to what the agent writes: agents stored the body under the name the input declared, letting the input decide what is written, and their checks faded once cues were removed. Model-free tests trace the harm to the processing primitive, so we defend it there: a gate that counts the bytes each call produces held every routed extraction within budget while agents completed 25/28 tasks. Vendors should pair such gates with safety-alignment training that teaches agents to inspect an input before processing it.

cs.CR · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01952

Hippocampal consolidation without replay in fully fine-tuned networks

Keuntae Kim, Yong Suk Choi

原文摘要

Networks that keep learning overwrite what they know. Prevailing remedies replay stored data, distil from old models or freeze the backbone. The brain suggests a different division of labour: the hippocampus indexes where experience lies in cortex while the cortex keeps learning. We show that this division lets a fully trainable network keep learning without cross-task replay, a teacher or inference-time memory. After each task, a training-only hippocampal memory indexes the input geometry of every group of synapses sharing an input, residual energy included, and limits each synapse's movement per direction before and after the optimizer. This class-free geometry carries most of the protection; with conflict detection on top, the method cuts absorption of established classes by near-duplicates several-fold against every compared method. To our knowledge, this is the first demonstration of one principle keeping whole networks learning across four architecture families and models up to 8 billion parameters. Methods that freeze the backbone hold up only as far as its representation already separates the classes; here the whole network keeps learning to tell near-duplicates apart, leading the frozen-backbone baseline by 17.5 points on TACRED. Without the memory, much old knowledge stays decodable but beyond the network's reach.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.25441

Stepwise Reasoning Verification: Don't Generate, Classify!

Yifei Shi, Michalis Korakakis, Rami Aly, Eric Chamoun, Lukasz Szpruch, Andreas Vlachos

原文摘要

Verifying the reasoning of large language models is increasingly important as they are applied to complex mathematical and scientific problems. Existing work focuses on large decoder models and reports mixed results for generative and discriminative verifiers, leaving unclear which paradigm is more effective and whether large models are necessary. In this work, we cast stepwise verification as a natural language inference task: the problem and partial solution prefix form the premise, while the next reasoning step serves as the hypothesis to be classified as entailed or non-entailed. This formulation enables error localisation at individual reasoning steps and direct comparison of encoder classification, decoder classification, and decoder verdict generation across model scales and annotation budgets. Across five reasoning datasets, a 0.15B encoder classifier outperforms most generative verifiers with up to 4B parameters. On identical decoder backbones, classification outperforms generation from 0.5B to 4B parameters and matches it on the strongest 7B backbone---reaching comparable performance with roughly one tenth as many annotated problems. Our findings establish classification as a parameter- and data-efficient approach to stepwise verification and show that strong verification does not require large generative decoders.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01945

Tracing How Language Models Integrate Temporal Anchors into Factual Recall

Ayana Niwa, Masahiro Kaneko, Kentaro Inui

原文摘要

Factual recall in language models is typically framed as retrieving a factual association: a subject--relation pair maps to a single object. However, many facts are context-dependent: the same pair maps to different objects depending on a condition such as time. We introduce anchored factual recall, in which the model receives an explicit conditioning expression, an anchor, and must select the object valid under it. This raises questions that single-object recall does not: where the anchor enters the computation, what it changes, and how that change selects the answer. Focusing on temporal anchors, we answer them with causal interventions on four open-weight models on English prompts and identify two routes. In a subject-mediated route, the anchor resolves the final subject-token representation to the queried year, and the relation redistributes the readout of this state across attention heads. In a direct route] the final position attends to the anchor, and upper-layer MLPs turn this signal into a preference for the time-appropriate object. The two routes are parallel channels: their contributions add up, most queries use both, and their balance depends on the query, e.g., on the relation, consistently across models. This reframes mechanistic accounts of factual recall from retrieving a single stored object to selecting among context-dependent alternatives.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01943

Beyond Multimodal Emotion Conflict: Temporal Context-Aware Hidden Emotion Detection with Multimodal Large Language Models

Yonghao Wang, Jiaxin Zhou

原文摘要

Multimodal emotion recognition commonly combines textual, acoustic, and visual signals to infer affective states. Recent work has begun to study conflicts among modalities, but a conflict does not necessarily indicate that a person is concealing an emotion. It may also result from mixed emotions, individual expressive styles, or contextual factors. This proposal aims to distinguish ordinary emotional inconsistency from emotion concealment and to infer the underlying emotion when supported by evidence. We plan to construct a multimodal benchmark with explicit annotations of expressed emotion, internal emotion, and concealment conditions, and to develop an MLLM-based framework that integrates fine-grained facial Action Units (AUs), cross-modal features, and temporal context.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.10092

RAP: Research Attention Prediction in Language Agents

Yingqian Wu, Jingcong Liang, Shengbin Yue, Siyuan Wang, Zhenfei Yin, Junchi Yu, Zhongyu Wei

原文摘要

LLM agents increasingly support research planning and execution, where judgments about current and anticipated research activity inform decisions. Yet whether they can infer changes across a whole field from the partial evidence they retrieve through online scholarly search remains unclear. We introduce Research Attention Prediction (RAP), a literature search benchmark for evaluating this ability. We build a local search environment from 356,357 dated arXiv papers and construct two complementary evaluation tasks. The benchmark comprises a Core set of 2,160 questions across 54 AI/ML fields and an Extended set covering 269 fields. Our evaluation and analysis of LLM agents show that search substantially improves stronger agents' recognition of recent changes, while forecasting gains remain limited or negative. Agents update forecasts across dates and adjust their investigations to forecasting goals, but these adaptations do not reliably yield accurate predictions of future shifts. Even for recent changes, final judgments can diverge from what the retrieved papers indicate. These findings show that agents can recognise some recent changes, yet reliably anticipating future research activity remains difficult despite changes in their answers and investigations.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01942

Direct Knowledge Transfer for Offline Q-Learning

Zhanye Luo, Guangyan Gan, Lin William Cong

原文摘要

Data-driven sequential decision making in marketing and healthcare can benefit from observations collected in related environments, particularly when data in the environment of interest are limited. Transferring such information requires accounting for differences in rewards and transition dynamics across environments. We study knowledge transfer for offline reinforcement learning through a joint estimation framework that directly integrates source information into target value-function learning. We propose Direct Transfer Fitted Q-Iteration (DFQI), which updates the target Q-function while simultaneously borrowing the source information through an L1 penalty that links the target coefficients to a weighted aggregate of source coefficients, with both determined jointly within each Bellman update. Using sieve approximation, we establish statistical guarantees for target estimation and policy learning in stationary discounted environments with common or heterogeneous transition kernels. Empirical studies further demonstrate the effectiveness of the proposed DFQI framework in transferring source information to improve policy learning with limited target data.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v9arXiv:2606.08343

GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators

Jason Sulskis, Sathya Ravi

原文摘要

We propose GENERIC-FNO, a neural operator that embeds the metriplectic (GENERIC) degeneracy structure of nonequilibrium thermodynamics in function space, coupling reversible, energy-conserving dynamics to irreversible, entropy-producing dynamics via the degeneracy conditions. Prior structure-preserving neural operators enforce at most one conservation law or a Hamiltonian form, and thermodynamically consistent learning has been confined to finite-dimensional, graph, or particle systems. GENERIC-FNO learns the energy and entropy functionals as neural operators and builds the reversible and irreversible operators as diagonal Fourier multipliers flanked by rank-one projections that enforce both degeneracy conditions exactly, by construction, with no penalty, update projection, or residual; the Jacobi identity is not enforced. The identities hold to machine precision (~10^-13) for any initialization, dimension, or resolution, so the continuous-time dynamics conserve the learned energy and produce the learned entropy exactly, with explicit time stepping adding only an O(dt^2) drift. These are guarantees about the learned functionals within GENERIC's scope of closed conservative-dissipative dynamics, not a certificate of physical accuracy, and the (E,S,L,M) decomposition is not unique; we make this gauge freedom explicit and propose a gauge-invariant dissipation diagnostic independent of the learned functionals. Across three backbones (1D/2D FNO, DeepONet) and four canonical scalar PDEs, the guarantees transfer zero-shot over a 4x super-resolution range and hold in 3D; the diagnostic identifies the reversible and the most dissipative system in every backbone; and over 200-step rollouts, where every unconstrained model we test diverges or collapses, GENERIC-FNO stays bounded, at half the parameters but 4-10x the compute, while losing accuracy on pure transport and on the smallest 1D backbone.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01939

VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph

Yuntae Jeon, Younho Jeon, Sujin Jin, Sungho Jo, Seunghee Park

原文摘要

Learning semantic representations for 3D Gaussian Splatting has recently emerged as a promising direction for 3D scene understanding. However, existing 2D-to-3D semantic lifting approaches rely primarily on 2D segmentation supervision and lack object-level priors, causing the learned representation to be driven by local mask evidence rather than holistic object structure. In this paper, we present VLSplat, a vision-language guided approach for object-centric semantic lifting in 3D Gaussian Splatting. Our method augments mask-based lifting with object-level semantic priors derived from vision-language models and refines Gaussian representations using an object-group scene graph. The refinement is performed through two language-guided modules: intra-group refinement suppresses semantic noise within object groups, while inter-group acquisition expands object support regions by incorporating structurally relevant candidates from neighboring groups. Extensive experiments on indoor scene datasets demonstrate that VLSplat improves the semantic consistency and structural completeness of object-level categories. Our code and models are available at https://vlsplat.github.io/.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01937

Spade-SLAM: Sparse Correspondence Anchors for Dense Self-Supervised Visual SLAM

Julian Philipp Schmitt, Weirong Chen, Ganlin Zhang, Felix Wimbauer, Daniel Cremers

原文摘要

We introduce Spade-SLAM, a self-supervised dense visual SLAM framework that substantially narrows the long-standing performance gap to supervised methods in a zero-shot setting. By demonstrating that high-fidelity tracking can be achieved without explicit ground-truth pose and depth labels, our approach offers a highly effective and label-efficient alternative to fully supervised pretraining. Our core contribution is a complementary sparse-to-dense training regime: While a warping-based photometric loss provides a dense training signal, we stabilize the optimization and suppress drift in ambiguous regions using a sparse correspondence loss derived from image feature matches. Extensive experiments demonstrate that Spade-SLAM significantly improves robustness and accuracy compared to existing self-supervised baselines, closely rivaling SLAM systems trained with explicit pose and depth supervision. The code will be made publicly available at https://github.com/JulianPSchmitt/Spade-SLAM.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2607.26998

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents

Ruoyu Wang, Heng Zhao, Renjie Wu, Tianhang Zheng, Mengnan Zhao, Wanyu Lin, Kui Ren

原文摘要

Large language model agents automate web penetration testing through observation-action loops, enabling defenders to influence decisions with deceptive decoy observations. Advanced agents can recognize and bypass static decoys, then refocus on real targets. We propose AgentSnare, a trajectory-adaptive deception system that expands a decoy environment alongside exploration. For online deployment, ShadowOS combines an LLM-driven decoy constructor with a virtual kernel. Conditioned on exploration, it generates decoy artifacts that the kernel materializes and handles consistently across interactions, sustaining long-horizon exploration. Because deploying a powerful LLM for decoy construction is costly and slow, we train a small LLM using an offline adversarial interaction-simulation framework. It synthesizes multi-round trajectories by generating candidates and retaining those that sustain simulated interactions. Across 15 CVE-Bench web applications and four attacker models, AgentSnare absorbs 49.9% of tool calls to delay attacks, retains 57.2% of post-entry actions in the decoy to divert trajectories, and grounds 89.5% of completion reports in decoy evidence to defuse threats; across 60 attacker-CVE pairs, no real target is exploited at pass@3.

cs.CR · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01934

TriPhysBench: Evaluating Physical Intelligence for Embodied Agents

Zhongxiang Sun, Chenghao Yang, Haojie Ding, Boheng Zhang, Fan Yang, Qingsong Wen, Kun Wang

原文摘要

Embodied agents need physical intelligence to understand their surroundings through physical perception, physical knowledge retrieval, and physical reasoning. These capabilities must work together to interpret events and make quantitative judgments. Existing benchmarks advance physical understanding and general-purpose tool use, yet the coordination of these capabilities in physical scenarios remains insufficiently characterized. Inspired by Popper's Three Worlds, we introduce TriPhysBench, a benchmark of 410 questions from 200 videos that brings physical perception, physical knowledge retrieval, and physical reasoning into a shared evaluation setting. Its measurement-grounded and knowledge-grounded subtasks impose complementary demands on obtaining observations and acquiring external specifications, then applying them to quantitative problems. Among six representative vision-language models, the best achieves an answer accuracy of only 50.38%, revealing limited performance on tasks that require these capabilities to work together. We further introduce TriPhys, a framework that learns a unified policy for physical perception, knowledge retrieval, and quantitative reasoning from complete tool-integrated trajectories. The policy uses intermediate reasoning to guide retrieval and computation, then incorporates tool feedback into subsequent physical inference. On 110 questions from videos excluded from training, TriPhys improves answer and solution scores across three Qwen configurations, with a 17.7% relative gain in answer accuracy for TriPhys-27B over its Qwen3.6-27B backbone. This work provides a benchmark and a learning pathway toward embodied agents that move beyond recognizing events to understanding and reasoning about the physical processes behind them.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01932

Geometric Morphology Learning: Empowering Foundation Models from Structure to Spacetime Intelligence

Li Sun, Philip S. Yu

原文摘要

Geometry is the very form that connects space, time, and matter, serving as the fundamental fabric of the physical world, from continuous fields to discrete structures. Despite its importance, deep learning is inherently blind to geometry. Riemannian geometry stands as a well-established mathematical foundation for studying geometry, yet it remains largely incompatible with deep learning architectures. To bridge this gap, we establish a new learning framework--Geometric Morphology Learning--that learns geometric or topological structures, shapes or conformations for representation learning, reasoning and action modeling. Moving beyond early attempts limited to specific geometric priors, this theory centers on modeling the intrinsic geometry of objects and learning from such geometric or topological knowledge. Specifically, we construct a neural bundle, a unified scaffolding linking local and global structures, and formulate differentiable operators, including connection and curvature, thereby enabling the study of geometry with advanced geometric concepts such as holonomy and cohomology. Consequently, Geometric Morphology Learning opens new horizons in foundation models, reasoning and planning, graph modeling, physical simulation, PDE systems, and dynamics, marking a fundamental shift toward instilling systematic geometry in artificial intelligence.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.13686

IndicDBBench - Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages

Aviral Dawar, Roshan Karanth, Vikram Goyal, Rakhee Kulshrestha, Sumanta Pasari, Dhruv Kumar

原文摘要

While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks largely focus on Western contexts leaving a gap in real-world, non-Western applications. We introduce IndicDBBench, a comprehensive multilingual Text-to-SQL benchmark designed to evaluate cross-lingual semantic parsing across diverse Indic language families. The underlying schemas are derived from real-world open-data platforms (NDAP and IDP), ensuring realistic structural complexity. IndicDBBench comprises 20 databases spanning 237 tables. To construct complex relational structures from denormalized government data, we employ a three-agent pipeline (Architect, Auditor, Refiner), achieving high relational density (11.85 tables per database) and join depths of up to six. We generate 15,612 tasks spanning seven languages: English and six Indic languages, ensuring that queries are grounded in real database values and require multi-table reasoning. We evaluate state-of-the-art models, including DeepSeek V3.2, MiniMax M2.7, Llama 3.3, and Qwen3, across seven linguistic variants. Our results reveal a 9.0-point drop in execution accuracy from English to Indic languages, exposing an "Indic Gap" that, for the two models tested, persists even when gold tables and literal values are supplied, since this grounding raises accuracy in every language by similar amounts. The dataset and code are publicly available at https://anonymous.4open.science/r/multilingualText2Sql-Indic--DDCC/

cs.CL · cs.AI · cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01930

RECEIPT: Measuring and Repairing the Return Assumption of LLM Agents in Web Service Operations

Boyang Yang, Ziyao Yang, Yu Zhang, Duo Chai, Xiaoming Chen, Haoye Tian

原文摘要

LLM agents operate Web infrastructure from the command line and rely on a return assumption, namely that each tool call returns within a bounded time and with its requested action finished. Many commands, however, ask a question before they act, and the agent's harness either closes the program's input or keeps it open as a terminal at which nobody types. With closed input, the program can return status 0 without the requested action. With open input, it waits until a time limit, and the agent pays in time and tokens. To the best of our knowledge, this paper is the first to measure and repair the return assumption. We collect 91,469 production tool calls and 89,047 public agent trajectories, test how 8 widely used harnesses launch commands, and build Litmus, a catalog of 158 checked command-line invocations, and Tripwire, a benchmark of 25 task pairs that differ only in whether a question guards the requested action. We then propose RECEIPT, which keeps the input open, reads what each process waits for from system calls, and returns this state to an unmodified agent through a model-checked protocol. On Litmus, closed input causes 11.5% of tested invocations to return status 0 without performing the requested action, and 7 of 8 harnesses close input when no terminal is attached. An unanswered question at a plain terminal multiplies a task's token use by 2.9, and the input connection moves an LLM from 7th to 3rd place among 8. Across 5 LLMs, RECEIPT reduces false claims of success by 73.5% and completes all 25 guarded tasks on a second harness. An agent's reliability therefore depends on what its harness lets it observe as well as on its LLM. Agent builders should report what each tool call did, not only how it ended, and benchmark maintainers should fix and report the input connection before they rank LLMs.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01929

Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule

Eitan Gronich, Gal Vardi

原文摘要

We study the implicit bias of Adam and its similarity to sign gradient descent on homogeneous models in binary classification tasks. Perhaps surprisingly, we uncover that these depend on the learning rate schedule. While previous works studied strongly decaying learning rate schedules $η(t)=\mathrm o \left(t^{1/L-1}\right)$, where $L$ is the homogeneity degree, and showed $\ell_\infty$-margin-maximization biases, we focus on the more common complementary regime, including constant and weakly decaying schedules. For a polynomial schedule $t^α$ and homogeneity degree $L$, we show that when $α> \frac 1L - \frac12$, Adam has no trajectory-independent margin-maximization bias for deep linear networks (in the KKT sense): first, there is no non-trivial, locally Lipschitz, convex implicit regularizer in this setting, including any squared norm. Second, on width-$1$ networks, the result holds without requiring convexity, implying that any implicit regularizer for wide networks must be trivial when restricted to a width-$1$ network. Nevertheless, we positively characterize the implicit bias in this regime as maximizing a trajectory-dependent weighted-$\ell_2$ margin for any $L$-homogeneous model. The fundamental mechanism behind our results is convergence of Adam's preconditioner to a trajectory-dependent vector, which also allows showing that the limiting parameter direction depends on initialization. In the intermediate regime $\frac 1L - 1 \leq α\leq \frac1L - \frac12$ we prove an $\ell_\infty$ bias, conditional on gradient directional convergence to a full-support vector. Of independent interest, we establish a loss decay rate for full batch Adam on general homogeneous models, whose leading order depends only on the second-moment parameter.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.37297

TRUCO: A Scalable Lock-Free Algorithm for Parallel Contour Extraction

Rafael Munoz-Salinas, Francisco J. Romero-Ramirez, Manuel J. Marin-Jimenez

原文摘要

Extracting closed pixel contours from a binary image, together with the hierarchy that records which contours enclose which, is a basic step in many computer vision pipelines, from fiducial marker detection to the vectorization of segmentation masks. The reference algorithm, by Suzuki and Abe, is inherently sequential: each contour is found by a raster scan that depends on the labels left by all previous contours, and its parent is obtained from the last contour met by the scan. This paper presents TRUCO (Threaded Raster Unrestricted Contour Ownership), a multi-core algorithm that returns exactly the output of Suzuki--Abe (the same contours, in the same order, with the same hierarchy) without locks, read-modify-write operations or a stitching phase. The method rests on two ideas. First, the image is divided into horizontal stripes, one per thread, and two rules, row-local writes and geometric contour ownership, let each thread trace complete contours independently of the others. Second, the tracing of the contours is separated from the computation of the hierarchy, which is recovered afterwards from one reference per contour; the trace therefore stores no contour numbers in the label image, which also makes it more efficient than that of the original algorithm when a single thread is used. We prove that the output is deterministic and identical to that of Suzuki--Abe, and that the algorithm is free of data races. Experiments on synthetic images, high-resolution photographs and segmentation masks, on a desktop and a server CPU, show that TRUCO scales with the number of threads and is several times faster than the fastest sequential methods, with and without the hierarchy. With a single thread, it is already faster than Suzuki--Abe.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01927

Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks

Yu Jiang, Yue Huang, Hang Hua, Yuyang Wu, Zixuan Weng, Olexandr Isayev, Yue Zhao, Zinan Lin 等 9 位作者

原文摘要

Long-horizon terminal tasks are used to evaluate and train agents. Human-curated datasets are scarce, so many synthesis methods have emerged. They usually measure the length of a task by the turns a model needs to pass it, and its difficulty by labels the LLM sets during generation. We find, however, that the turn count largely reflects the habits of the model, not only the demands of the task, and that the labels barely track how often models pass. We describe a terminal task by its work, the number of operations it requires, and its depth, the number of turns that must happen in sequence because the commands of each turn can only be chosen after reading the output of the previous one. Estimating depth as the smallest turn cap, stated to the agent, under which the task passes, we audit 734 tasks from six existing datasets. Synthesis has mostly added work, not depth: 94% of the solved synthetic tasks pass within three turns, yet depth, unlike the turn count, predicts difficulty beyond work. We propose DEPTH, in which a generation agent writes each task one segment at a time in a real software environment, carrying out each segment before writing it and starting the next from the state it leaves. Our 105 tasks exceed every audited dataset in depth and work, and none of six current models passes half of them. Fine-tuning Qwen3-8B on runs from these tasks improves it on two terminal benchmarks.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01926

TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens

Juseon Do, Sangmin Bae, Jeesu Jung, Hwanjun Song

原文摘要

LLM-based agentic systems are increasingly combined with CoT reasoning to solve tasks that require accurate reasoning, external knowledge, and multi-step deliberation. Yet, explicit CoT incurs substantial generation overhead, while implicit CoT, which replaces textual rationales with compact continuous tokens, does not naturally support the explicit communication interface required for agentic tool-use. We propose TAC-CoT, a tool-empowered adaptive implicit CoT framework that replaces explicit reasoning traces with compact latent reasoning segments while retaining textual tokens only for tool calls, observations, and final answers. This interleaved design enables agentic tool-use without verbalizing every intermediate reasoning step. Experiments on agentic math and QA benchmarks show that TAC-CoT improves accuracy by up to 8.8 points while reducing model forward passes by up to 6.8x. Furthermore, analyses show that TAC-CoT improves tool-use quality in both single- and multi-tool settings.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01921

Vision-language classification of Torsades de Pointes risk from pseudo-coloured ECG images: do T-wave morphology and colour context help or hinder?

Dario Labrador Alonso, Alaa Alahmadi

原文摘要

Contextual prompting is widely presented as a cheap route to better performance from vision models, but the evidence comes largely from benchmarks in which an attribute named in a prompt is also present in the image, confounding the two channels. We investigate the significance of context for a semantically complex biomedical signal classification task using a domain-adapted vision-language model, BiomedCLIP. Building on our previous work that renders electrocardiogram (ECG) signals as colour-enhanced images to flag Torsades de Pointes risk using the QT-nomogram and pseudo-colouring technique, we cross four context strategies with four T-wave morphology label sets, evaluated zero-shot and with a class-balanced linear probe, under five-fold stratified cross-validation on 9,789 images. Zero-shot inference is unusable. Once trained, the colour-enhanced images outperform the colourless ones on every metric: balanced accuracy 0.903 versus 0.825, sensitivity 0.914 versus 0.827, specificity 0.892 versus 0.823, ROC-AUC 0.955 versus 0.888 and Matthews correlation coefficient (MCC) 0.437 versus 0.311. Crossing colour-in-image with colour-in-prompt separates the confounded channels: the image contributes +0.126 MCC (+0.078 balanced accuracy, +0.067 ROC-AUC) whether or not the prompt names colour, whereas naming it changes nothing under any metric. Context is two-sided: the best prompt set gains 0.008 MCC where colour is present and 0.016 where it is not, while the worst loses 0.017 and 0.013. For a signal rendered as an image, the leverage lies in how the signal is drawn rather than in how it is described - and where the endpoint is an interval measurement, prompts naming T-wave morphology describe the wrong quantity.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v8arXiv:2508.02833

TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback

Lei Pang, Jun Luo, Ruinan Jin

原文摘要

Group Relative Policy Optimization (GRPO) trains language models without a value critic using rewards centered within sampled response groups. We study how importance weighting, clipping, and length normalization affect its stochastic updates and propose Trajectory-level Importance-Corrected GRPO (TIC-GRPO), combining an upper importance-ratio cap with a full-trajectory likelihood ratio. Under common maximum-length normalization, a trajectory change of measure gives a score second moment proportional to the response horizon. We propagate this estimate through the actual empirical baseline and all inner updates. With separately optimized constant steps, the sampling term in TIC's stationarity bound has a linear horizon coefficient, versus order three halves for token-level GRPO$_2$. Matching upper and lower bounds separate the capped methods' worst-case response-level variances by a factor $T$. The bounds track prompt count, response-group size, vocabulary size, reward scale, and score regularity; per-response-normalized GRPO also retains a length-covariance term. Experiments at two Qwen3 scales on four reasoning and coding benchmarks evaluate both mechanisms in sampled-token-normalized training.

cs.LG

查看论文
arXiv ↗PDF ↗