跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 06:44 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 07:20 — 2026-11-20 07:20(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:2026-11-20 06:44最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

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 23,249 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 06:42(北京时间)
新论文 · v1arXiv:2611.23803

CoT-WAM: Collaborative Training of Vision-Language Models and World-Action Models via Plan Latents

Jinhao Zhang, Yushen Zuo, Ke Rui, Weitao Zhou, Haibao Yu, Honglong Tian, Xiaoheng Ma, Jie Mei 等 10 位作者

原文摘要

General robot manipulation requires both semantic competence and physical foresight. World action models (WAMs) acquire an understanding of and predictive capability over the physical world by jointly modeling visual foresight and action distributions. However, existing WAMs still lack semantic competence: they have limited ability to perform open-world scene understanding, semantic reasoning, and long-horizon planning. Although vision-language models (VLMs) provide these capabilities, effectively integrating their semantic priors into WAM prediction and control remains challenging. To address this challenge, we propose CoT-WAM, a jointly trained WAM-VLM framework. CoT-WAM uses a learnable embedding to exchange information between the VLM and the WAM, which is supervised by textual and goal-image signals during training to encode rich intent information. A tailored two-stage training strategy enables joint optimization and more effective collaboration between the VLM and WAM. We evaluate CoT-WAM on six benchmarks covering control performance, zero-shot generalization, and long-horizon planning. CoT-WAM achieves SOTA performance on LIBERO, CALVIN, and RoboCasa-Kitchen, and demonstrates stronger zero-shot generalization on LIBERO-Plus and LIBERO-Pro without fine-tuning. On RoboCasa365, it further improves long-horizon planning over baselines with and without external planners. Real-world experiments further demonstrate the effectiveness of our method in practical deployments.

cs.RO

新论文 · v1arXiv:2611.23801

Improved Leverage Score Sampling for Constrained Active Linear Regression

Aarshvi Gajjar, Syamantak Kumar, Aditya Makkar, Christopher Musco, Joey Zhou

原文摘要

In this paper we study active learning for constrained linear regression. Given a design matrix $A\in\mathbb{R}^{n\times d}$, a constraint set $C\subseteq\mathbb{R}^d$, and query access to $b\in\mathbb{R}^n$, we seek an approximate solution to $\min_{x\in C}\|Ax-b\|_2^2$ using as few queries as possible. This problem arises in many scientific and engineering applications, and randomized leverage score sampling provides a powerful method to solve it. However, existing leverage score methods ignore the constraint or encode it through ridge regularization, suffering unfavorable query complexity for anisotropic constraint sets. We propose ellipsoid-regularized leverage scores, where we approximate the constraint set by an outer ellipsoid and use its shape matrix to bias sampling toward directions that matter under the constraint geometry. We prove that the query complexity is governed by an anisotropic effective dimension $d_{\text{eff}}(C)\le d$. With appropriate parameters, $O(d_{\text{eff}}(C)\log d/\varepsilon^2)$ queries suffice to return a point in $C$ with objective value at most $(1+\varepsilon)$ times the optimum. This bound can substantially improve on the standard leverage-score bound, since anisotropic constraints can make $d_{\text{eff}}(C)$ much smaller than $d$. For convex constraints, we improve the dependence on $\varepsilon$ from $1/\varepsilon^2$ to $1/\varepsilon$. We also prove two lower bounds: first, the $d/\varepsilon^2$ dependence is unavoidable without convexity assumptions on $C$, and second, in some regimes, the effective dimension dependence $d_{\mathrm{eff}}(C)/\varepsilon$ is necessary for ellipsoidal constraints. Experiments on synthetic regression problems and a parametric heat conduction problem show lower regression error than standard baselines for similar query budget.

stat.ML · cs.LG · math.NA

版本更新 · v2arXiv:2611.15314

AcrossPlace: Do Vision--Language Models Recognize Places Beyond Their Source Views? A Comprehensive Benchmark

Zhenyu Li, Tianyi Shang, Shuhan Dong, Ruotong Xu, Qingyu Zhu

原文摘要

Language-guided place recognition requires recovering geographic identity across visual observations beyond the image from which a description originates. However, aggregate retrieval scores often entangle observation transfer, gallery competition, and linguistic evidence, obscuring the underlying recognition capability. We introduce AcrossPlace, a provenance-aware benchmark establishing a systematic evaluation standard for bidirectional language--vision place recognition. Built upon GSV-Cities, AcrossPlace comprises 56,726 places across 23 cities, 156,800 automatically generated, rule-filtered descriptions, and 113,404 target images. Each description retains its source-image provenance, while retrieval operates on disjoint target observations. Text-to-image (T2I) and image-to-text (I2T) retrieval share a unified place-identity relevance criterion supporting multiple valid matches. Two geographic protocols evaluate unseen places within represented cities (P0) and generalization to held-out cities (P1). Paired observation comparisons, gallery-controlled evaluations, fixed-query scaling, and blinded annotation auditing systematically characterize retrieval performance. Across three training seeds, place-supervised SigLIP2 T2I Recall@1 decreases from 19.69% on source images to 12.31% on independent targets under P0. For fixed P1 queries, expanding the gallery from 500 to 8,425 places reduces Recall@1 from 14.67% to 2.87%. A 240-description audit further reveals discrepancies between automated acceptance and factual evidence. These findings establish AcrossPlace as a reproducible evaluation standard for assessing transferable place identity across visual observations and geographic environments.

cs.CV

版本更新 · v2arXiv:2607.14256

Disagreement-Guided Agentic Data Curation for Multimodal Safety

Genglin Liu, Muye Zhang, Krishnamurthy Viswanathan, Nichole J. Hansen, Blaž Bratanič, Nathan L Clement, Shalini Ghosh, Ariel Fuxman

原文摘要

Written safety policies in multimodal settings define categories whose visual boundaries span many contexts. We study disagreement as a signal for identifying useful synthetic boundary cases. Our pipeline generates policy-conditioned images, selects cases with target--rater or inter-rater disagreement, conditionally escalates unresolved cases, and retrieves the resulting rater-labeled examples as in-context demonstrations. On a failure-enriched multimodal safety benchmark, policy grounding reduces false negative rate (FNR) from 0.875 to 0.413 and raises F1 from 0.220 to 0.731; retrieval from 50 disagreement-selected examples further reduces FNR to 0.245, compared with 0.297 from a 350-example Regular pool. The selected memory also improves a different target-model family, with a smaller gain on a proprietary benchmark with a refined policy. In a blinded human study, experts disagree on 24% of disagreement-guided images and 17% of baseline-curated images. These findings support traceable, disagreement-guided curation for multimodal safety evaluation and example selection.

cs.AI · cs.MA

新论文 · v1arXiv:2611.23795

A Dual-SOM Learner Model of Instructional Efficiency within Cognitive Load Theory

Spyridon Revithis

原文摘要

This paper presents a novel methodological framework, integrating a dual self-organising map (SOM) neural network architecture with Cognitive Load Theory (CLT), for assessing instructional efficiency within learning environments. By representing curriculum content as a directed acyclic graph of topic dependencies, the proposed model captures collective learning behaviour across two core dimensions: academic performance and subjective/introspective mental effort. During SOM training, representative data sets of successful learner trajectories are compressed into two topologically ordered, identically structured neural networks: PSOM (performance space) and ESOM (mental effort space). By pairing these behavioural maps, the model serves as a decision-support tool that enables instructors to simultaneously pinpoint structural instructional design defects, such as hidden topic prerequisites, and evaluate collective cognitive load profiles. The implementation and performance of the PSOM component (and, by extension, its symmetrical twin, ESOM) is linked to an earlier modelling study employing a SOM with identical structure and encoding semantics situated in the same domain (i.e., a learning environment). This paper combines the study of behavioural phenomena with theoretical work on human cognitive architecture via SOM neurocomputational cognitive behavioural modelling.

q-bio.NC · cs.CY · cs.NE

新论文 · v1arXiv:2611.23793

ROBIN++: Unified Copyright Protection and Tamper Localization for Diffusion Models via Dual-Domain Synergistic Watermarking

Huayang Huang, Siqi Zeng, Qian Wang, Bo Du, Yu Wu

原文摘要

Digital watermarking provides a promising solution for verifying the provenance and integrity of generated content. However, existing methods often suffer from an inherent trade-off between copyright robustness and localization sensitivity due to the entanglement of conflicting signals within a single domain. In this paper, we propose ROBIN++, a paradigm that shifts from single-domain entanglement to a Dual-Domain Synergistic design. Our key insight is to explicitly decouple robustness and fragility during injection by assigning them to distinct domains, while re-coupling them for mutual reinforcement during verification. Specifically, we introduce an Adversarial Optimization Algorithm to inject a frequency-domain copyright watermark during generation, maximizing extraction robustness without visual artifacts. Complementarily, a Content-Aware Perturbation generator is integrated into the latent space to inject the spatial-domain localization watermark, ensuring sensitivity to spatial tampering with minimal interference to the copyright watermark. During verification, we propose a dual-branch synergistic detector that facilitates Frequency-to-Spatial Synergy, where robust spectral priors act as global anchors for local anomaly detection. Conversely, a Spatial-to-Frequency Refinement strategy is employed to rectify corrupted latent features using predicted tamper masks. Extensive experiments show that ROBIN++ significantly outperforms existing approaches in both copyright recovery and tamper localization accuracy, effectively mitigating the long-standing trade-off between the two tasks. Code is available at https://github.com/Hannah1102/ROBIN.

cs.CV

新论文 · v1arXiv:2611.23788

Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT

Sungho Yun, Seungryong Cho

原文摘要

Rigid motion of a patient head during head cone-beam CT (CBCT) scan can degrade image quality and complicate recovery of accurate anatomical structures from the measured projections. We present a 3D flow-matching prior approach that learns the image changes induced by motion. Its geometry-bridge connects motion-corrupted and motion-free Feldkamp-Davis-Kress (FDK) reconstructed images of the same source volume through progressively reduced simulated motion. The forward projector's geometry derivative supplies analytic velocity targets along this path. A plug-and-play loop encompasses the learned image updates together with spline-based pose estimation, conjugate-gradient data consistency, and image total-variation regularization. Both the refined image volume and the FDK reconstructed image volume at the estimated poses are evaluated. On simulated 360-view scans from 30 held-out CQ500 patients with nominal per-component motion amplitudes within 10 mm / 10 degrees, the framework achieved state-of-the-art image reconstruction quality and motion accuracy in comparison with other methos such as learned autofocus and diffusion-based joint reconstruction. Mean peak signal-to-noise ratio (PSNR) reached 37.1 dB and mean detector-plane reprojection error (RPE) was 0.27 mm. With matched endpoints at the inference settings, the geometry bridge improved PSNR by 1.6 dB and reduced RPE by 33% relative to image-linear training. With 50 prior updates and coarse-to-fine motion estimation, total processing time averaged 9.1 minutes per patient on an RTX A6000.

physics.med-ph · cs.CL · cs.CV

版本更新 · v2arXiv:2607.10059

AgentAbstain: Do LLM Agents Know When Not to Act?

Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran

原文摘要

Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain. This gap poses real risks: under ambiguity, conflicting constraints, or tool failures, agents may execute unintended and irreversible actions. To close this gap, we present the first systematic evaluation framework for agentic abstention: the calibrated ability of tool-using LLM agents to recognize when not to act. At its core, AgentAbstain is a paired-task benchmark built on an agent-native taxonomy of 8 abstention scenarios across pre-execution reasoning and runtime discovery. It contains 263 paired tasks across 42 executable sandbox environments, where each pair consists of a should-act task and a should-abstain variant produced through a controlled perturbation to the instruction, tool, or environment state. To scale this paired design and resist data contamination, we propose AbstainGen, a fully automated pipeline that synthesizes sandbox environments and generates paired tasks end-to-end, validated by deterministic replay and semantic LLM judges; fresh task instances can be regenerated on demand, and three independent annotators rate 94-98% of sampled tasks as well-designed. Across 17 frontier LLMs in 4 agent harnesses, the best agent (Gemini 3.1 Pro) achieves only 59.5% paired accuracy (correct on both the act and abstain sides of each paired task). More importantly, abstention capability is largely independent of general task-solving capability, indicating that scaling task-solving alone will not close this gap. We further identify failure modes such as post-hoc abstention, in which agents execute irreversible actions before recognizing abstention triggers. Our code and dataset are open-sourced at agentabstain.github.io.

cs.AI

版本更新 · v2arXiv:2611.22815

Visual Harness Scales General VLMs to Medical Images

Shaowen Wan, Hanqi Jiang, Zihao Wu, Junhao Chen, Weihang You, Ruiyu Yan, Bowen Chen, Tianming Liu 等 9 位作者

原文摘要

We show that an appropriate visual harness can substantially improve the performance of general vision-language models (VLMs) across diverse medical imaging tasks. We introduce VERA, a medical visual harness that equips general VLMs with interactive visual tools and systematic diagnostic evidence management. With VERA, general VLMs interactively explore medical images and progressively acquire diagnostic evidence, which is preserved in a lossless memory for subsequent retrieval and use. After submitting an initial answer, the VLM receives an assessment of potential omissions and the reliability of identified findings. This assessment guides further image inspection and measurement, followed by answer revision in an iterative agentic loop until sufficient evidence is obtained. Across 11 tasks and four imaging modalities, VERA improves performance on all tasks with Qwen3.8-27B, with notable gains in spleen measurement (63.3% to 98.3%), renal search (57.5% to 71.2%), and pulmonary nodule detection (0.0% to 28.2%). High-capability API-based VLMs achieve even higher performance with VERA. For example, GPT-6.1 Sol improves pulmonary nodule detection from 10.8% to 69.2% with VERA, demonstrating the complementary benefits of stronger model capabilities and an effective medical visual harness. Our results highlight the potential of visual harnesses as a new paradigm for scaling general VLMs to medical imaging tasks.

cs.CV

版本更新 · v2arXiv:2606.20937

Learning through Internalization

Nikolaos Tsilivis, Nirmit Joshi, Marko Medvedev, Julia Kempe, Nathan Srebro

原文摘要

We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how they facilitate learning. We investigate how transformers internalize the simulation of semiautomata by internalizing chain-of-thought (CoT) tokens, which classes of semiautomata are harder to internalize, and expose the flip side of internalization, that is, a progressive degradation of out-of-distribution performance. We then provide the first provable analysis of successful internalization: for the task of learning parities, we show that a simplified one-layer transformer provably first learns the target with explicit CoT supervision and then internalizes the autoregressive generation as CoT tokens are progressively removed, learning to directly compute the parity. This task is computationally hard to learn from data without CoT supervision. Finally, we discuss how learning through internalization relates to the \textit{Positive Distribution Shift} phenomenon recently introduced by~\citet{Med+26}.

cs.LG

版本更新 · v2arXiv:2602.08230

Generating Adversarial Events: A Motion-Aware Point Cloud Framework

Hongwei Ren, Lansong Yang, Youxin Jiang, Tuopusen Huang, Xiangqian Wu

原文摘要

Event cameras have been widely adopted in safety-critical domains such as autonomous driving, robotics, and human-computer interaction. A pressing challenge arises from the vulnerability of deep neural networks to adversarial examples, which poses a significant threat to the reliability of event-based systems. Nevertheless, research into adversarial attacks on events is scarce. This is primarily due to the non-differentiable nature of mainstream event representations, which hinders the extension of gradient-based attack methods. In this paper, we propose MA-ADV, a novel \textbf{M}otion-\textbf{A}ware \textbf{Adv}ersarial framework. To the best of our knowledge, this is the first work to generate adversarial events by leveraging point cloud representations. MA-ADV accounts for high-frequency noise in events and employs a diffusion-based approach to smooth perturbations, while fully leveraging the spatial and temporal relationships among events. Finally, MA-ADV identifies the minimal-cost perturbation through a combination of sample-wise Adam optimization, iterative refinement, and binary search. Extensive experimental results validate that MA-ADV ensures a 100\% attack success rate with minimal perturbation cost, and also demonstrate enhanced robustness against defenses, underscoring the critical security challenges facing future event-based perception systems.

cs.CV · cs.AI

新论文 · v1arXiv:2611.23781

When accuracy hides risk: risk-controlled confirmation of the critical view of safety under expert disagreement

Bowen Xiang, Xiao Yu, Mingze Xu

原文摘要

Automated assessment of the critical view of safety (CVS) in laparoscopic cholecystectomy has advanced rapidly, but a deployed check must decide, before the first clip, whether to confirm CVS. The standard rule calibrates a threshold so that false confirmations are rare on average. We show that this rule concentrates its errors on disputed videos, which one of three expert raters judged sufficient, and that the failure is structural. When reference labels are votes of a panel sampled from a larger expert pool, the rule that maximizes sensitivity at a fixed average false-confirmation rate also maximizes false confirmation of disputed videos, and for recognizers that recover expert judgement with less noise this rate rises with accuracy. We propose certified confirmation, a risk-controlled monitoring rule whose threshold is selected by multiple testing so that, with probability at least 1 - δ, false confirmation is at most α overall, among disputed videos, within vendor and country groups, and before CVS is visible, using disputed labels only to calibrate. In a pre-specified, hash-locked evaluation on the 300 test videos (18 countries) of the SAGES CVS Challenge, standard calibration falsely confirmed 8 of 39 disputed videos (0.21; one-sided p = 0.037 against α = 0.10), whereas certified confirmation confirmed 2 (one-sided 95% upper bound 0.15). On development data, protection held for vendor and country groups left out of calibration. The cost was confirming 10% rather than 35% of sufficient videos on time. Average accuracy hides this risk; disputed cases must be protected explicitly.

cs.CV

新论文 · v1arXiv:2611.23779

TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning

Pau Mateo-Bernadó, Saivenkata Nagavyjayanthi Polapragada, David Bonet, Pol Arbiol Rakuljic, Laia Mogas Pladevall, Marçal Comajoan Cara, Jesus Gonzalez-Ferrer, Jordi Abante 等 11 位作者

原文摘要

Recent advances in machine learning have accelerated biomedical prediction, but evaluation on structured biomedical data remains fragmented, especially for datasets with high dimensionality, large sample size, missingness, and class imbalance. We introduce TabBioMed, a large-scale benchmark of 94 curated public biomedical tabular datasets spanning electronic health records, drug discovery, genomics, transcriptomics, proteomics, metabolomics, single-cell omics, and systems biology. TabBioMed unifies these datasets through a standardized, dataset-aware preprocessing and evaluation framework, enabling reproducible comparison across classification, regression, and multi-target tasks. We benchmark 23 models across classical baselines, gradient-boosted trees, neural tabular architectures, and tabular foundation models. Foundation models deliver the strongest family-level predictive performance. However, their gains are regime-dependent: tree-based models and tuned multilayer perceptrons remain highly competitive, often dominating under inference-time or training-cost constraints. Overall, TabBioMed shows that biomedical tabular learning is strongly context-dependent, with optimal model choice depending on data regime, task type, and computational budget. We release TabBioMed with curated datasets and splits, preprocessing code, baselines, and results, providing a reproducible benchmark for practical model selection and future methods development in biomedical machine learning, available at https://github.com/AI-sandbox/TabBioMed.

cs.LG

新论文 · v1arXiv:2611.23777

STORM: A Lightweight Structure-Free Model for Binding Affinity Prediction

Ayush Pandit, Rohan V. Koodli, Wei Deng, Roxana Daneshjou, Ron O. Dror

原文摘要

Accurately predicting a small molecule's binding affinity to a protein, a critical task in drug discovery, remains challenging. Physics-based approaches like free-energy perturbation (FEP) have very high computational costs and require expert setup. Recent machine learning--based cofolding models have reported accuracy approaching that of FEP---and at least one of them, Boltz-2, has already been widely adopted for affinity prediction---but they remain expensive for large computational screens and even more expensive for retraining on newly collected experimental data. To address these challenges, we introduce STORM: Similarity Transfer from Observed Reference Molecules. STORM is a fast, simple machine learning model that ensembles many small model fusions of diverse protein and molecule representations for binding affinity prediction. Trained on the same data, STORM matches or exceeds the accuracy of Boltz-2 on multiple evaluation datasets, while delivering a speed improvement of over five orders of magnitude for both inference and training. Our results also suggest opportunities to substantially improve affinity prediction accuracy by integrating historical experimental affinity data with structural and biophysical information.

q-bio.QM · cs.LG

新论文 · v1arXiv:2611.23774

Improve How You Improve: Recursive Policy Self-Improvement for Zero-Shot Open-Vocabulary Multi-Object Navigation

Yang Li, Ziju Han, Aming WU, Zihao Zhang, Sijia Zhang, Yahong Han, Qinghua Hu

原文摘要

To advance the development of embodied general navigation, zero-shot open-vocabulary multi-object navigation has attracted increasing attention, aiming to enable robots to efficiently search multiple objects in unseen environments without training. For this task, the key lies in improving navigation policies from earlier searches to locate subsequent goals more efficiently. Recent methods automate this process through trajectory reflection and rule revision, enabling policy self-improvement. However, the mechanisms for diagnosing problems and generating revisions are typically designed by humans and remain fixed across iterations. Consequently, the system's capacity for continued self-improvement remains constrained, even as its navigation policy evolves. To this end, we propose RPSI-Nav, a Recursive Policy Self-Improvement framework for zero-shot multi-object navigation that revises both the navigation program and its revision mechanism. RPSI-Nav diagnoses search behavior, requests diagnostic views when existing observations cannot distinguish competing causes, and generates targeted navigation revisions. Feedback from subsequent goal searches is linked to the rules that produced these revisions, guiding changes to diagnosis, observation acquisition, and revision planning. The updated improver governs subsequent navigation improvements, forming a recursive loop in which RPSI-Nav revises its own improvement process. Across goals, the robot conditionally inherits accepted program updates and spatial memory, enabling search experience to improve both future navigation and adaptation. Benchmark experiments and qualitative real-robot evaluations validate RPSI-Nav's effectiveness.

cs.RO

新论文 · v1arXiv:2611.23773

A Systematic Analysis of a Small Optimal Subspace for Physics-Informed Neural Networks: $n$-DAS $\subset \mathbb{R}^p$

Ahmad AliAhmad, Khemraj Shukla

原文摘要

The search for a low-dimensional subspace that governs neural network training has been a persistent goal in optimization. Yet subspaces defined by Hessian eigenvalue magnitude, such as the dominant/bulk decomposition underlying Dom-SGD and Bulk-SGD, have repeatedly failed to capture where optimization takes place, and adaptive Krylov-based alternatives built on energy-fraction thresholds show promise but still struggle at lower eigenmodes. We argue this failure is structural: the directions of highest curvature are not, in general, the directions along which training moves. We introduce the dominant aligned subspace (DAS), constructed from a full eigendecomposition of the Hessian but selected by gradient alignment rather than eigenvalue magnitude, as a tool for understanding optimization dynamics and a foundation for designing methods that exploit them. To expose this structure under the hardest conditions, we use physics-informed neural networks (PINNs) as a testbed: differential operators from the parabolic, elliptic, and hyperbolic classes induce severely ill-conditioned, anisotropic loss landscapes. Across Poisson, heat, wave, and viscous Burgers benchmarks DAS-restricted training with a line search matches full-space training even where the projected Hessian remains ill-conditioned, showing empirically that convergence does not require all Hessian eigendirections but only a low-dimensional, gradient-aligned subset. We extend the analysis to Gauss-Newton within the DAS and discuss what this structure implies for future subspace-aware optimizers.

cs.LG · math.AP · math.OC

新论文 · v1arXiv:2611.23770

DetectViT: Test-time Backdoor Detection for Vision Transformers via Inter-Head Attention Discrepancy

Siquan Huang, Yijiang Li, Xingfu Yan, Ningzhi Gao, Leyu Shi, Ying Gao

原文摘要

Vision Transformers (ViTs) now underpin the visual encoders of most multimodal models, but this success comes at a cost: relying on third-party pretrained checkpoints leaves these systems open to backdoor attacks. Existing test-time detection methods rely on either the predicted label or intermediate embeddings, limiting their applicability across diverse tasks and incurring substantial computational overhead. In this work, we study how backdoor triggers affect the multi-head attention mechanism of ViTs and identify two distinct anomalous patterns: $\textit{complete attention hijacking}$, causing the attention to exhibit abnormally high inter-head spatial overlap, and $\textit{partial attention hijacking}$, causing an abnormally large variance in the concentration of the attention distribution. Motivated by these findings, we propose $\textbf{DetectViT}$, a test-time backdoor detection method that requires neither training data, model outputs, nor any prior knowledge of the trigger. DetectViT quantifies the two hijacking phenomena via an inter-head consistency score and an inter-head entropy variance score, with thresholds estimated from a small out-of-distribution (OOD) calibration set drawn from an arbitrary source. Across four representative attacks, diverse architectures (DeiT, CLIP, and LLaVA), and downstream tasks (image classification and captioning), DetectViT substantially outperforms all baselines with as few as 64--128 OOD calibration samples, achieving a true positive rate of $100\%$ and a false positive rate of $0.17\%$ on BadCLIP. Notably, it introduces negligible additional overhead by relying solely on attention weights already computed during inference. Code is available at: https://github.com/siquanhuang/DetectViT.

cs.CV · cs.CR

版本更新 · v4arXiv:2603.12408

Imitation Learning from Human Motion Alone Does Not Guarantee Biomechanically Plausible Gait Kinetics

Xinyi Liu, Jangwhan Ahn, Edgar Lobaton, Jennie Si, He Huang

原文摘要

Imitation learning (IL) via motion data is increasingly used in robotics and character animation, yet its ability to be applied to human biomechanics to estimate physiologically plausible joint moments without explicit kinetic information remains unclear. In this study, we examined whether motion imitation alone can estimate reasonable biological joint moments in human walking. We compared motion-only IL (MOIL) against a kinetics-aware IL (KAIL) framework, which incorporates additional ground reaction forces (GRFs) and center of pressure (CoP) in imitation rewards. A progressive kinetic reward shaping approach was used to examine the contribution of each kinetic term. Experiments were conducted using walking data from two non-disabled participants at three speeds (0.9, 1.2, and 1.5 m/s). While both MOIL and KAIL achieved comparable kinematic tracking accuracy, KAIL produced kinetics more closely aligned with biomechanical values across participants and walking speeds, reducing the root mean square errors (RMSEs) of vertical GRF and CoP by 40% and 48%, and of hip, knee, and ankle moments by 19%, 18%, and 35%, respectively, relative to MOIL. These findings highlight a fundamental limitation of MOIL approaches, as their failure to accurately estimate human-like gait kinetics may lead to erroneous interpretations of gait biomechanics and adversely affect downstream applications such as wearable robot design and the diagnosis of pathological gait.

cs.RO · cs.LG

新论文 · v1arXiv:2611.23769

Keep the Reasoning, Read the Image: On-Demand Visual KV for Multi-Turn Reasoning VLMs

Ziyi Wang, Xiyue Zhang, Bing Hu, Guangmin Song, Chenyi Zhang, Li Wang

原文摘要

Reasoning vision-language models (VLMs) think for thousands of tokens before they answer, and retention policies keep the KV cache affordable by pruning it as the reasoning grows. We find that this pruning sacrifices the image in multi-turn conversations: the image and the reasoning share one budget, so the growing reasoning crowds the visual entries out. A chart question that loses 8 points to the full cache when asked first loses 24 points when asked after a round of reasoning. Protecting a small visual reserve from eviction recovers most of this loss, while adding the same slots to the shared budget recovers considerably less. The image therefore lacks protection, not capacity. Based on this finding, we propose ShelfKV, a training-free method that works on top of existing retention policies. It keeps every visual entry in CPU memory and, at each decoding step, swaps the visual entries that the current query scores highest into the attention slots of the text entries it scores lowest. The image is never evicted, yet it occupies attention slots only while it is read. We evaluate ShelfKV on four benchmarks, three of them conversational, with two retention policies and two reasoning VLMs. In conversations, it improves the strongest existing policy, DBTrimKV, by up to 20.3 points at matched GPU memory, and still leads by 8.7 points when DBTrimKV uses twice the memory. It also consistently outperforms a fixed visual reserve of matched GPU memory in these settings, without hurting accuracy on standalone questions. These results show that the image should be protected from the reasoning but read only on demand.

cs.CV

版本更新 · v3arXiv:2510.10731

Controllable Generative Trajectory Prediction via Weak Preference Alignment

Yongxi Cao, Julian F. Schumann, Jens Kober, Joni Pajarinen, Arkady Zgonnikov

原文摘要

Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy in such prediction tasks. Besides accuracy, diversity is also crucial for safe planning because human behaviors are inherently uncertain and multimodal. However, existing methods generally lack a scheme to generate controllably diverse trajectories, which is arguably more useful than randomly diversified trajectories, to the end of safe planning. To address this, we propose PrefCVAE, an augmented CVAE framework that uses weakly labeled preference pairs to imbue latent variables with semantic attributes. Using average velocity as an example attribute, we demonstrate that PrefCVAE enables controllable, semantically meaningful predictions without degrading baseline accuracy. Our results show the effectiveness of preference supervision as a cost-effective way to enhance sampling-based generative models.

cs.RO · cs.LG

版本更新 · v3arXiv:2602.06475

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning

Jingyao Wang, Xingyu Zhang, Peizheng Guo, Jiahuan Zhou, Zhenghao Zhang, Changwen Zheng, Chuxiong Sun, Wenwen Qiang

原文摘要

Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coupled to final correctness and pay little attention to the underlying reasoning process: trajectories with sound reasoning but wrong answers receive low credit, while lucky guesses with flawed logic may be highly rewarded, affecting reasoning generalization. From a causal perspective, we interpret multi-candidate reasoning for a fixed question as a family of counterfactual experiments. Building on this, we propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns. It proposes an episodic causal counterfactual reward that jointly captures (i) robustness, encouraging the answer distribution induced by a reasoning step to remain stable under counterfactual perturbations; and (ii) effectiveness, enforcing sufficient variability so that the learned reasoning strategy can transfer across questions. We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust. Extensive experiments on diverse benchmarks demonstrate its advantages.

cs.LG

新论文 · v1arXiv:2611.23765

Mean Curvature Minimizing Foliations Of A Vector Field

Tabish A. Syed, Marc Theveneau, Benedikt Wirth, Rustum Choksi, Kaleem Siddiqi

原文摘要

Streamline patterns are ubiquitous in nature. Prominent examples include white matter fibre tracts in the mammalian brain and arrangements of elongated cells, such as cardiomyocytes in the heart wall. It has been posited that such organisations foliate into locally smooth surfaces to optimise function. However, the recovery of these foliations from a single vector field aligned with the local orientation of the underlying sheets remains an open problem. We address this challenge by introducing a mathematical model of a sheet and developing an algorithm for sheet inference, from measurements of the oriented structures. Given an input vector field, our model estimates a second vector field that is orthonormal to it, while also requiring the Lie bracket of the two to vanish. To balance sheet likelihood against low surface area, we also reduce the mean curvature of the recovered local surface. We compute the first variation of an associated energy and provide a numerical method which admits an efficient, parallel implementation for sheet estimation. We demonstrate our approach on both synthetic and biological examples, motivated by applications to medical imaging. These include white matter fibre tracts from a brain atlas and confocal microscopy images of cleared heart wall tissue. For the latter we are able to reconstruct sheets aligned with local cardiomyocyte directions at unprecedented (micrometre) scale.

cs.CV

版本更新 · v2arXiv:2610.00262

Risk-Calibrated Intent Routing for Conversational AI via Signed Lexical Evidence

Yezhou Cheng, Zehua Yang, Bojun Lin

原文摘要

Conversational AI has become widely used as advances in language models let people find information, get writing help, and ask for practical guidance in their own words. When an assistant handles specific tasks, it must infer what the user wants and decide whether to act on that prediction. A sentence classifier's confidence can miss clues in the wording. We combine the gap between the classifier's two highest scores with signed lexical evidence, a score based on words and short character patterns. The score is positive when those patterns favor the predicted intent and negative when they favor another. We use separate calibration data and a statistical upper bound on the error rate to set the minimum confidence required to accept a request. Across ten runs per dataset, our method reduces the area under the risk-coverage curve, which summarizes error as more requests are accepted, by 15.8%, 15.1%, and 11.8% on BANKING77, CLINC150, and HWU64, respectively, compared with a confidence model that uses only sentence classifier scores. At a 5% error target, the share of accepted requests rises by 1.83 percentage points on BANKING77 and 5.14 points on HWU64. CLINC150 already has near-full coverage at that target. At a 2% target, calibration finds a rule that accepts some requests in all 30 runs. Our contribution is a two-feature confidence model that improves routing by measuring how strongly the wording supports or challenges the original intent prediction.

cs.CL · cs.AI

版本更新 · v2arXiv:2606.07179

Lifting 3D Gaussians: A Wavelet Multiresolution Representation for Scalable Gaussian Splatting Streaming

Yuang Shi, Géraldine Morin, Simone Gasparini, Wei Tsang Ooi

原文摘要

3D Gaussian Splatting (3DGS) represents a scene as an unstructured set of primitives optimized at a single scale, offering no native support for progressive delivery to heterogeneous devices. Existing scalable approaches organize these primitives into independent quality layers or spatial hierarchies. However, maintaining separate splat representations across scales introduces redundancy, while independent layers have limited ability to correct coarse geometry as finer detail arrives. We present LiftGS, a multiresolution representation that organizes a scene into a coarse Gaussian set and a tree of refinements. Each refinement replaces one coarse Gaussian with two finer children whose attributes are learned relative to their parent. Inspired by wavelet lifting, we encode these changes using a shared detail vector and per-attribute factors that allow the two children to differ asymmetrically from the parent. A client first receives the coarse set, then reconstructs and substitutes children as refinement data arrives. This construction reuses previously transmitted attributes to encode finer detail and removes replaced parents from the active rendering set, reducing both refinement payload and rendering memory. Extensive experiments on four benchmark datasets show LiftGS cuts splat redundancy from over 65% to under 25%, reduces transmission payload and GPU memory by up to 2.4x and 5.5x over state-of-the-art scalable-3DGS baselines, achieves smooth quality transitions in simulated progressive delivery, and compresses a further 8.7x with standard coding at negligible quality loss. Project website: https://yuang-ian.github.io/liftgs/

cs.CV · cs.MM · eess.IV

新论文 · v1arXiv:2611.23761

When Normal-Only Updates Are Not Enough: Test-Time Adaptation in Reconstruction-Based Time-Series Anomaly Detection

Jianhuan Mao, Mengxiao Zhu, Yue Pei, Lei Li, Haogang Zhu

原文摘要

Normal operating conditions can evolve after deployment, motivating test-time adaptation (TTA) of time-series anomaly detectors using incoming data. Yet the same stream may contain anomalies, so TTA with online updates must decide which test samples should be used for adaptation. This leaves a more basic question: even if updates are restricted to samples labeled as normal in the benchmark, does TTA reliably improve anomaly detection? We study this question with a controlled intervention that replaces the practical update selector with a rule that uses only samples labeled as normal in the benchmark, while keeping the rest of the online adaptation procedure unchanged. Across nine benchmark families, four optimizer configurations, and five random seeds, we obtain three main findings: (1) using only samples labeled as normal in the benchmark does not reliably improve detection; (2) practical TTA failures exhibit two distinct responses to this intervention, with 63 of 180 settings recovering a clear detection gain while 90 still show no clear detection gain; and (3) the updates reduce their immediate reconstruction objective across the evaluated settings, yet these reductions do not consistently lead to better anomaly ranking. Both failure patterns persist across alternative practical adaptation variants and modest perturbations of the benchmark labels. Together, these findings show that improving sample selection alone is not a complete solution to reconstruction-based TSAD TTA.

cs.LG

新论文 · v1arXiv:2611.23755

GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-Synthesis

Vasha DuTell, Zuyu Yun, Anne Harrington, Michael Y-S Fang, Mark Hamilton, Christian Kövesdi, Edward H. Adelson, William T. Freeman 等 9 位作者

原文摘要

Deep networks achieve high realism in texture synthesis but often rely on opaque, over-parameterized representations that have limited direct connection to biological vision. Neuroscience-informed pyramid models are interpretable, compact, and biologically inspired, but rely on small, hand-curated statistics sets that are difficult to generalize or extend. We introduce GramStatTexNet, a hybrid analysis-by-synthesis framework that combines the multi-scale Gabor filter structure of classical models with the flexibility of Gramian-based correlations, organized into structured filter families. This structured representation enables analyses that are challenging for deep-feature methods: each statistic carries a named filter-family identity, allowing us to decompose synthesis fidelity into per-family contributions and to learn an interpretable, low-dimensional embedding that preserves perceptual texture content. We compare our framework to classical and deep texture-synthesis baselines across diverse texture categories, and on multiple perceptual metrics, highlighting the compactness and interpretability advantages of this hybrid representation, alongside competitive synthesis quality. This same framework extends naturally to peripheral textures via spatial pooling, and to dynamic textures using a spatiotemporal filter bank. GramStatTexNet provides a unified, interpretable framework for analyzing and modeling visual information with natural extensions across space, time, and eccentricity. Project page: https://vdutell.github.io/gstn

cs.CV · cs.GR · q-bio.NC

新论文 · v1arXiv:2611.23754

Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding

Zihao Zhang, Aming Wu, Yang Li, Yahong Han

原文摘要

Accurately matching human intentions in 3D space is an important goal of artificial intelligence. Recently, 3D Intention Grounding (3D-IG) has emerged, aiming to localize target 3D objects given a natural-language intent. Unlike conventional visual grounding with descriptive referring expressions, 3D-IG intents are abstract and non-descriptive, making object localization substantially more challenging. This requires inferring latent functional requirements from non-descriptive intents and aligning them with object-level 3D representations. However, existing methods largely rely on implicit intent-object matching, leading to logical gaps and limited interpretability, robustness, and generalization. To address these challenges, we propose Chain-of-Causal Reasoning (CoCR), a causality-inspired functional dependency reasoning framework that explicitly bridges abstract intentions and candidate objects through intermediate functional requirements. Specifically, CoCR progressively decomposes complex intents into ordered functional requirements, thereby forming an explicit intent-function-object reasoning chain that links abstract intentions to object suitability. Building on this chain, we construct a causality-inspired functional dependency graph to model requirement-attribute relationships and introduce a causal-visual alignment module that aligns function-aware representations with the geometric-semantic features of 3D point clouds, enabling bidirectional verification between structured functional reasoning and visual evidence. Extensive experiments on 3D Intention Grounding and 3D Visual Grounding demonstrate that our method enhances intent-aware object localization. Our code is available at https://2490o.github.io/CoCR.

cs.CV

新论文 · v1arXiv:2611.23753

Interpreting Timestamp Permutations in Dynamic Link Prediction

Ilia Karpov, Kirill Koloskov, Valeriy Kuleshov, Dmitry Ilvovsky

原文摘要

Timestamp permutations are used to test whether dynamic link predictors exploit temporal information, but a performance gap can reflect changes in training, evaluation history, or both. We separate these effects with a crossed diagnostic and measure input exposure: whether altered histories actually change the predictor's inputs. On MOOC, TCL trained with binary cross-entropy gains approximately eight pairwise-accuracy points from original-chronology training under either evaluation history, while changing history at fixed weights gives only 0.03 points. The small history contrast reflects unchanged inputs for 68.37% of queries, stable rankings for most others, and cancellation of gains and losses. Under original evaluation history, suppressing explicit time encoding reduces the training contrast from 8.03 to 3.64 points, a paired reduction of 4.39 points (95% interval [3.68, 5.09]) across six seeds. DyGFormer shows corresponding training and history contrasts of 22.34 and 0.38 points across two seeds, despite greater exposure. Partial history permutations further separate nominal intervention strength, input changes, and aggregate accuracy. These comparisons turn a single permutation gap into interpretable statements about training conditions and model responses, while leaving the internal mechanisms of temporal learning open.

cs.LG · cs.AI · cs.LO · cs.SI

新论文 · v1arXiv:2611.23752

ACUS: An Angular Calibrated Uncertainty Score for Incomplete-View CT

Zihan Deng, Chuanzhi Xu, Quankeng Huang, Yujie Liu, Zhenzhen Gong, Junjie Huang, Tianye Niu, Lequan Yu

原文摘要

Sparse-view and limited-arc computed tomography (CT) are commonly treated as projection completion: a network fills an unmeasured view, and the result is ranked by similarity to one ground-truth image. That score can be high even when the query angle is far from every acquired measurement, because a learned prior may invent anatomy the scan never constrained. Existing protocols therefore leave a basic question unanswered: how does predictive reliability change with distance from the acquired views? We propose the Angular Calibrated Uncertainty Score (ACUS) to answer that question. ACUS is the Winkler interval score of a nominal 90% predictive interval on held-out projections, binned by distance to the nearest acquired view. It charges interval width and adds a large miss penalty when a held-out pixel falls outside the interval, so a narrow band helps only when coverage holds. We use collapse on acquired angles as a necessary consistency check on the predictor. On chest and dental cone-beam orbits, interval width grows with the angular gap. Empirical coverage ranges from 77% to 92%, and the peak signal-to-noise ratio (PSNR) of the point estimate falls as the width rises. Nearest-neighbor, interpolation, and point completion, each given one residual scale, have zero reported far coverage and incur outside-distance penalties. ACUS exposes gap-dependent overconfidence that a point-estimate PSNR alone does not measure.

cs.CV

新论文 · v1arXiv:2611.23751

Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow

Rui Li, Liyang He, Zheng Zhang, Zhenya Huang, Qi Liu

原文摘要

Autonomous LLM agents incur substantial cost and latency by invoking a large model (System-2) at every step, even when many intermediate actions choose among a small set of known candidates. Existing dual-system agents offload such decisions to a lightweight System-1 model, but rely on workflow-specific hooks authored per environment. We present AnyS1, a framework that turns human-authored procedural skills, whose instructions naturally specify where choices arise and which options apply, into a shared, domain-general source of decision points. Offline, AnyS1 mines grounded enumerable decisions across over 1,000 public skills, gathers execution-grounded trajectory states inside isolated containers to construct Any-DP, and trains a single calibrated 4B pointer System-1 with label smoothing. At run time, compiled workflows resolve routine decisions in one forward pass and fall back to System-2 when confidence falls below a calibrated threshold. Across three unseen benchmarks and distinct System-2 model families, AnyS1 preserves task reliability while cutting episode cost by 75-91% and model-call time by 63-92% relative to an uncompiled System-2 agent, and maintains performance under zero-shot threshold transfer.

cs.AI · cs.CL · cs.LG