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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 12:58 — 2026-11-22 12:58(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:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v2arXiv:2611.24684

Hi Gemini, Who Should I Vote For? The Benefits (and Problems) of Using LLMs As Voting Advice Applications

William John Atkinson, Paul Saproza

原文摘要

Large language models (LLMs) can provide voters information about political issues, party positions, and even advise on which party to vote for. However, no previous study explores whether off-the-shelf LLMs could be used as voting advice applications (VAAs) to improve voter-party congruence. In this article, we address this gap by examining how Gemini 3 Flash advises a sample of 6,022 German survey respondents on which party to vote for, based on their policy preferences and priorities alone. In brief, we find that for most respondents, following the LLM's advice would benefit voter-party policy alignment (i.e. congruence), with a significantly stronger remedial effect among voters with low levels of political interest and formal education. However, our analysis also reveals concerning biases in the LLM's recommendations. For instance, the LLM suggested voting for the AfD at approximately 1.5 times the frequency of a standard salience-weighted proximity model. In addition, the LLM hardly ever advised voting for either Die Linke or the BSW. We conclude that while LLMs can approximate the behaviour of VAAs, users should be aware that the LLM's recommendations are still biased in ways that are extremely difficult to trace.

cs.CY

新论文 · v1arXiv:2611.25819

SCCV-6D: Sparse Canonical Coordinate Voting for Holistic Multi-View RGB-D 6D Pose Estimation in Robotic Bin Picking

Nico Leuze, Samed Dogan, Maximilian Hoh, Henry Schaub, Alfred Schöttl

原文摘要

Industrial bin picking requires pose estimates that are accurate under clutter, partial occlusion, and the reflective, texture-less nature of manufactured parts. Most recent approaches to 6D pose estimation follow multi-stage pipelines. These achieve high accuracy, but incur memory and runtime footprints that do not cope with the operational constraints of many real-world industrial deployments. Holistic pipelines estimate poses in a single pass, with cost controlled through indiscriminate subsampling or lowered resolution. Continuing this line, we present SCCV-6D, a fully sparse multi-view RGB-D estimator. We reconstruct the 3D space at millimeter precision, prune background via a staged heatmap mechanism, and predict class, translation offset and rotation at highest resolution for an arbitrary number of objects simultaneously. Rotation is formulated as canonical coordinate voting. Points vote for their canonical object coordinates with an associated confidence, enabling closed-form pose recovery with a symmetry-aware weighted Procrustes solve. Along an in-cluster point recovery induced by offset votes, this removes time-consuming post-processing stages. We reuse the task-supervised attention priors from the heatmap formulation for a novel attention-gated distillation objective that reweights teacher-student feature alignment. On the IPD test split we report competitive 0.826 AP at 1.13 s per scene, significantly faster than the leading entries. On MV-YCB our approach reaches 96.1 ADD-S, and remains competitive even on the densely packed bins of ROBI.

cs.CV

新论文 · v1arXiv:2611.25818

Anchor and Check: Deterministic Cross-Prompt, Cross-Model Reconciliation for Auditable LLM Decisions

Sivakameswara Reddy Chejarla

原文摘要

Pipelines that let a large language model (LLM) make discrete decisions need to know which decisions they may act on unattended, and a record that explains each one. We study a small, fully specified reconciliation contract: commit the target model's greedy answer (the anchor), draw one or two greedy checks that reach the answer by a different route (an alternate prompt, or a model from another family), and let a pure function return one of five outcomes, of which only Agree is acted on. On 48,000 model-item evaluations over 6,000 questions, with every method given access to verbalized confidence as a tie-breaker, the main finding concerns where calls come from: pooling another family's samples raises semantic entropy's AUROC by 1.7 to 4.0 points at every budget, and a same-model temperature check is the weakest design. As complete pipelines, the point estimates of the three-call contract and pooled semantic entropy over 3 or 5 samples differ by less than one point, with intervals containing zero. As detectors of the anchor's errors, the contract is ahead of pooled entropy with 3 and 5 samples under both tie-breaker conventions; with 10 samples the point estimates differ by less than one point and the sign depends on the convention. Under the strict Agree gate it automates 70% of items and still acts on 16% of errors. What the contract adds is a fixed committed answer, an explicit outcome and a decision replayable from its record; generation itself was not reproducible on the hosted API.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2611.24913

Sharp Bounds for Selector Advice and Oblivious Equilibrium Search

Sebastian Ben Daniel

原文摘要

Ko's tournament argument recognizes a P-selective language with quadratic advice. We determine the leading coefficient in the selector-query model. On $n$-bit inputs, $n^2/4+O(n)$ ordinary advice bits and $n$ nonadaptive comparisons suffice. Some cuts require $n^2/4-O(n\log n)$ bits even for randomized decoders with adaptive access to individual-degree-two extensions. At degree one the exact fixed advice width is $n+1$. Assuming exponential hardness in $\mathrm E$ against SAT-gate circuits, the quarter bound holds in deterministic polynomial time for every P-selective language. The same fixed point determines the cost of searching for an approximate equilibrium before seeing the payoffs. In an $N$-action symmetric constant-sum game with payoffs in $[0,1]$, let $P$ be the best worst-case probability that one game-independent proposal is an additive $ε$-Nash equilibrium. For each fixed $0<ε<1/2$, \[ -\log_2 P=(1+o(1))\, \frac{(\log_2 N)^2}{4[1-H_2(1/2+ε)]}. \] The algorithm draws uniform actions and proposes their empirical distribution for both players. The lower bound allows arbitrary mixed profiles and $N^{o(1)}$ adaptive payoff inspections before the proposal. For all symmetric two-player games, including general-sum games, the sharp exponent is $(\ln 2/8+o(1))(\log_2 N)^2/ε^2$ when $ε\to0$ and $\log(1/ε)=o(\log N)$. For security strategies in arbitrary zero-sum games the exponent is four times larger, and sampling an optimal strategy attains it. The common mechanism counts successful tuples. A fixed point makes them capture constant sampling probability while controlling a power moment of their distribution.

cs.CC

新论文 · v1arXiv:2611.25815

What Places an Action Boundary? Structure-Aware Attribution for Temporal Action Localization

Ruoshan Lan, Zongru Shao, Chieh Tsai, Mihai Surdeanu

原文摘要

Temporal action localization (TAL) detectors must identify actions and estimate their temporal boundaries, but localization remains a major source of detection errors. While understanding what determines boundary placement requires faithful attribution of temporal evidence, existing attribution methods have not sufficiently addressed the temporal structure of TAL or the need to tailor attribution to boundary localization. We introduce a structure-aware attribution framework that averages contributions across random evidence-restoration orders following the Shapley-Shubik principle. We make it tractable by using the detector's receptive field to limit which time steps are ordered individually, and by approximating each order with a soft gradient path. For boundary predictions, we further introduce cell-structured restoration orders and boundary-anchored references that selectively remove adjacent evidence. We also adapt faithfulness evaluation to assess the joint effects of contiguous temporal evidence and the direction of boundary displacement. Experiments on THUMOS14 and EPIC-KITCHENS-100 with TriDet and ActionFormer demonstrate improved attribution faithfulness over existing methods. Attribution analysis and controlled interventions further reveal that class-score changes do not reliably track boundary displacement, providing input-level evidence that classification relies on content less informative about boundary placement. Code and evaluation artifacts will be publicly released.

cs.CV

新论文 · v1arXiv:2611.25814

What Does Anti-Hallucination Training Buy? Saying Less, Cheap Pruning, and the Rest

Lingkai Bu, Qian Gao

原文摘要

Preference training is the standard recipe for reducing object hallucination in vision-language models, and each new method reports a lower CHAIR score. We ask what that reduction consists of. Every trained system is compared with its base model's caption truncated to the same object recall, which removes the part of the gain that comes from saying less; the remainder is compared with what a deliberately weak, frozen, eleven-feature post-hoc probe fitted on 500 annotated images can reproduce. All criteria were specified in the analysis code and frozen before the outputs they judge existed. For eight public methods on LLaVA-1.5-7B, the probe reproduces at least two thirds of what training removes beyond saying less for 7 of 8 methods on COCO, 8 of 8 on AMBER and 6 of 8 on Object HalBench, with RLAIF-V the consistent exception; a later public method released for both LLaVA-1.5 and Qwen2.5-VL (SENTINEL) meets the same bar on both. On our own DPO checkpoints the accounting holds on Qwen2.5-VL but fails on InternVL2.5 on COCO (2 of 4 training designs). At matched recall, the base model plus the probe beats truncation for 8 of 9 LLaVA-1.5 systems on COCO and 9 of 9 on AMBER, on the two newer backbones, and when realized as actual sentence deletion. The same measure prices training signals: DPO on the model's own samples labelled by the probe or by an object-level CLIP score recovers 0.70 and 0.87 of the beyond-brevity gain of ground-truth-labelled DPO on Qwen2.5-VL (the probe 0.73 on InternVL2.5), both beat length-matched random labels, and CLIP labels buy more than probe labels on COCO. Human judgements show that the sentences the probe deletes are wrong more often than those truncation would delete; a human check of the CHAIR evaluator's precision falls below our pre-set bar, which we report as a limitation.

cs.CV · cs.CL

版本更新 · v2arXiv:2605.07419

Incentivizing User Data Contributions for LLM Improvement under Withdrawal Rights

Di Feng, Runyuan Zhao, Chenhao Zhang, Zhanzhan Zhao

原文摘要

As large language models (LLMs) become a common source of information, users may contribute less original knowledge to the public communities on which model development depends. Platforms seeking user contributions must account for privacy and effort costs and the incentive to rely on contributions from others. We study this dilemma in a threshold public-goods model with heterogeneous user costs. Under uniform per-unit subsidies, users can be paid even when aggregate contributions fall short of the improvement threshold. To address this subsidy leakage, we develop a mechanism that combines verifiable cost disclosure, personalized contribution assignments, and voluntary withdrawal. We show that rational assignment leads either to profitable provision or to no collection. Simultaneous withdrawal minimizes contribution costs when both protocols succeed, while small-first sequential withdrawal can sustain provision under a wider range of cost conditions. Numerical experiments quantify the effects on provision probability and social welfare. In an exploratory dialogue experiment, we evaluate LLM agents based on 50 anonymized American Community Survey profiles under all three mechanisms, generating 150 trajectories to compare contribution and withdrawal decisions under matched conditions. These findings clarify how assignment rules and withdrawal timing can support collective data provision while preserving user control.

cs.GT

新论文 · v1arXiv:2611.25813

Efficient and Robust Drafting with Multi-Token Prediction

Filippo Galgani, Ziwei Ji, Omri Homburger, Ganesh Jawahar, Michelle Ramanovich, Ivan Korotkov, Luciano Martins, Utku Evci 等 12 位作者

原文摘要

Speculative decoding has emerged as a critical technique for accelerating Large Language Model (LLM) inference by decoupling generation into a drafting phase and a parallel verification phase. A crucial challenge is therefore designing a drafter that is both lightweight and accurate enough to approximate the predictions of the target model. We present a highly optimized Multi-Token Prediction (MTP) architecture that extends existing backbone LLMs to efficiently produce high-quality drafts. Built around a single shared drafting head, our approach features three core architectural optimizations: target activation injection to anchor semantic planning, zero-copy KV-cache cross-attention to bypass prefill compute and reduce memory overhead, and an efficient clustered vocabulary projection to reduce the cost of full-vocabulary decoding. Testing these improvements with the Gemma 4 model family, our G-MTP shows out-of-the-box speedups for both large server-side setups (up to 3.1$\times$) and smaller models targeting memory-constrained on-device environments (up to 2.3$\times$ on H100 and up to 2.2$\times$ on a smartphone GPU). In addition, we present parameter-efficient fine-tuning recipes for G-MTP that keep the drafter aligned with the backbone LLM under domain shift, requiring up to 1.83$\times$ fewer target forward passes than tuning only the backbone.

cs.CL

新论文 · v1arXiv:2611.25809

ALIoTh: Orchestrating Multi-Agent LLMs for Autonomous IoT Penetration Testing

Pironti Francesco Aurelio, Arena Luigi, Blefari Francesco, Lupinacci Matteo, Romeo Francesco, Maresca Alessio

原文摘要

Penetration testing in Internet of Things (IoT) environments, especially those composed of various different devices, e.g., smart plugs, smart cameras, and smart doors, presents great challenges across the phases of information gathering, attack surface enumeration, privilege escalation, and lateral movement. This paper introduces ALIoTh, a multi-agent, workflow-driven penetration testing framework that integrates Large Language Models agents within a Self-Retrieval-Augmented Generation (Self-RAG) architecture to autonomously identify and exploit vulnerabilities in IoT and Industrial-IoT (IIoT) environments. By leveraging state-of-the-art language models and orchestrating specialized agents via the LangGraph framework, ALIoTh dynamically plans and executes a full-spectrum offensive pipeline. This includes network, devices, and service enumeration, vulnerability assessment, payload generation, reverse shell deployment, and privilege escalation on each device. The Self-RAG mechanism equips expert agents with contextual access to IoT security knowledge, e.g., related documentation, tool manuals, and known attack techniques, enhancing their reasoning capabilities in scenarios involving multiple device exploitation and group policy manipulation.

cs.CR

版本更新 · v2arXiv:2609.40119

Function Contracts and Beyond: Machine-Checked Assurance Cases for Conformance of C Libraries to Their Requirements

Haokun Li, Zhongyi Wang, Mingshuai Chen, Ling Zhang, Guanyan Li, Depeng Liu, Xiao Yi, Shengchao Qin 等 9 位作者

原文摘要

Large language models (LLMs) have shown promise in automating interactive theorem proving, yet verification of real-world C codebases requires more than discharging individual proof goals. The task involves jointly constructing expressive function specifications and their proofs, and ensuring that library interfaces compose along intended call sequences even without a designated client. We present Accord, an LLM-assisted framework for building machine-checked assurance cases: structured, auditable artifacts supporting the claim that a C codebase meets its intended requirements. To model intended cross-interface use in open libraries, Accord constructs an interface protocol that exposes permitted call sequences and resource assumptions for review, with a conditional safety guarantee under verified contracts and caller obligations. Accord coordinates two complementary phases: (i) requirement-guided analysis and bottom-up construction of candidate specifications and protocols; and (ii) modular proof construction with feedback that revises the specifications and proofs. Implemented using VST in Rocq, Accord establishes memory safety for 259 function definitions across seven implementation cases from six benchmark families, including industrial cryptographic modules, and additional functional correctness for red--black trees and ML-DSA. Human review took an estimated 0.17--8.00 hours per case. The guarantees depend on disclosed contracts and assumptions; human review supplies the conformance judgments connecting the formal artifacts to the intended requirements.

cs.PL · cs.SE

新论文 · v1arXiv:2611.25802

World-delta: Continually Integrating Observations for Incremental 3D Scene Generation

Haonan Wang, Hanyu Zhou, Xiaobin Hu, Luxin Yan

原文摘要

Existing 3D generation methods synthesize visually compelling scenes from fixed inputs, yet struggle to continually expand and revise a 3D world as new observations arrive. Iterative approaches often fuse real observations and generated content into a single representation, treating generated content as established structure rather than revisable predictions. Consequently, early generation errors can persist and accumulate despite new evidence. We propose World-delta, an incremental 3D scene generation framework combining uncertainty-aware persistent world modeling with delta-guided diffusion for continual scene expansion and correction. Our framework comprises three components: 1) Visual Evidence Encoding integrates geometric and semantic cues from incoming images into unified world tokens. 2) Observation-Calibrated World Modeling maintains a persistent latent world state that distinguishes observation-supported content from provisional completion hypotheses. New evidence drives selective world deltas to revise conflicting hypotheses while preserving well-supported content. 3) Incremental World Diffusion Generation uses delta-derived masks to restrict diffusion to regions requiring updates, freezing unchanged regions. Only affected 3D chunks are decoded and integrated into the existing scene. Together, these components enable continual world expansion and revision while reducing redundant generation and preserving scene consistency. Experiments demonstrate the effectiveness of World-delta in incremental 3D scene generation, observation-driven correction, scene consistency, and update efficiency over successive scene updates.

cs.CV

版本更新 · v3arXiv:2610.36888

Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learning

Martín de Frutos, Baptiste Corban, Claire Bizon Monroc, Ana Bušić, Donatien Dubuc, Jiamin Zhu, Esteban Ferrer

原文摘要

Existing noise mitigation strategies for wind farms usually consist in reducing turbines power output, without accounting for the wake interactions between them and the noise emission directivity. This leads to over-conservative policies and unexploited wind power. Yet, turbine yaw can simultaneously affect wake interactions and the direction of noise emission, offering an additional degree of freedom for farm-level noise control. We therefore propose Noise Steering, a model-free reinforcement learning (RL) strategy that jointly controls turbine yaw angles and power setpoints to maximise farm power while satisfying a local noise constraint in a defined region. To enable training at a reduced computational cost, a low-fidelity acoustic model is coupled with the steady-state FLORIS simulator. The RL agent effectively learns how to redirect wakes and noise directivity away from the protected region while redistributing power across the farm. On a six-turbine test farm, the policy satisfies the 40 dB noise constraint throughout the full range of turbulent winds, with an average power deficit of only 2% relative to greedy unimpeded control, and up to 7.7% at high wind speeds. In comparison, the industry-standard noise-reduced operation (NRO) baseline here generates an average power loss of 17%. When deployed in the higher-fidelity FASTFarm simulator, the policy largely retains its performance under steady and turbulent inflow, despite differences in simulation fidelity. These results demonstrate the potential of combining yaw control and power derating through RL to improve the power-noise trade-off in wind farm operation.

cs.AI · eess.SY · physics.ao-ph · physics.flu-dyn

新论文 · v1arXiv:2611.25799

Computational trust as intuitionistic knowledge

Ivo Pezlar

原文摘要

In this paper, we will argue that the notion of computational trust can be understood as a form of fallible intuitionistic knowledge grounded in verification. This approach naturally captures a key aspect of trust: it involves vulnerability. Specifically, it validates the principle that verification leads to trust but does not validate the opposite principle that trust leads to verification. Thus, we can trust on good grounds that some program will perform according to its specification but the program might still fail. We present a simple logic for capturing this notion of computational trust based on constructive modal propositional logic extended with a trust modality, which will be specified in an inferential fashion and by utilizing the proofs-as-programs correspondence.

cs.LO · math.LO

新论文 · v1arXiv:2611.25798

Design and Validation of a Telescopic Chassis-Assisted Stair-Climbing Mechanism for Powered Wheelchairs

Yasuhiro Fukuoka, Haruya Shirado, Yuto Nakamura, Haruto Okabe, Ahmad Najmuddin Ibrahim, Takahiro Fukui

原文摘要

We propose a simple stair traversal mechanism that augments a four-wheel wheelchair with an auxiliary telescopic chassis actuator. The proposed mechanism provides the following key contributions during stair ascent: (A) enhanced safety by ensuring that either the front or rear wheels remain stationary at all times; (B) primary reliance of the required force and mechanical work on the telescopic chassis rather than the wheels; (C) insensitivity of the required force and mechanical work to stair inclination; and (D) reduced risk of wheel slip on steeper stairs. In addition, the telescopic chassis is expected to improve level-ground mobility by enabling tight turning with the shortest wheelbase and enhancing stability with the longest wheelbase.

cs.RO

版本更新 · v2arXiv:2608.00608

From field-scale to large-scale spectral libraries: Tabular foundation models in soil spectroscopy

Viacheslav Barkov, Jonas Schmidinger, Robin Gebbers, Martin Atzmueller

原文摘要

Visible and near-infrared (vis-NIR) and mid-infrared (MIR) spectroscopy enable rapid, cost-effective prediction of soil properties. Yet, translating high-dimensional, highly collinear spectra into accurate soil property predictions remains challenging, particularly when employing machine learning. We systematically investigated regression models and dimensionality reduction approaches for spectroscopic modeling across 85 soil property prediction tasks from open benchmark datasets in pedometrics, spanning field-scale digital soil mapping and a global soil spectral library. We compared an in-context learning tabular foundation model (TabPFN), a convolutional neural network (CNN), rule-based regression (Cubist), Random Forest, and partial least squares regression (PLSR) using full spectra as well as features derived from principal component analysis (PCA) and partial least squares (PLS) latent variables. TabPFN consistently delivered the best overall performance across spectral regions, properties, and scales, including large spectral library tasks with tens of thousands of soil samples. Notably, TabPFN applied directly to full spectra already surpassed all classical baselines, showing that explicit dimensionality reduction is not strictly required for strong performance. Further improvements were achieved through PLS, which proved to be an effective dimensionality reduction strategy for all models. Combining PLS latent variables with TabPFN yielded the best predictions overall, lowering the root mean squared error (RMSE) relative to the strongest classical baseline on 44 of the 46 large-scale spectral library tasks, by a median of 14%. Our findings provide evidence-based guidance for spectroscopic calibration model selection across operational scales, demonstrating that the long-standing advantages of PLSR and modern tabular foundation models complement each other in chemometrics.

cs.LG

版本更新 · v2arXiv:2611.24917

Unified Law for Visual Tasks (The Four Laws of Computer Vision)

Sen Fang, Yalin Feng, Yancheng Zhang, Yanxin Zhang, Zonglin Lyu, Hongbin Zhong, Liwei Che, Rui Wu 等 10 位作者

原文摘要

In this paper, we propose a Unified Law for Visual Tasks, which could be further divided into Four Laws of Computer Vision, with the goal of enabling a single framework or method to uniformly train on and perform nearly all visual tasks. Our starting point is an inspiration and hypothesis: if the world information is encoded into image, which we call World Snapshots, then image processing is world processing, and image generation is World Snapshot generation. Furthermore, if all visual and visualization tasks can be reformulated as generation tasks, then a unified method, World Snapshot Models (WSMs), can perform the vast majority of visual tasks, much as large language models have largely unified natural language processing. This paper validates these laws across more than 1,000 trained and evaluated visual tasks (defined by distinct input-output mappings) and presents a unified training framework for future visual-task research and applications.

cs.CV

版本更新 · v2arXiv:2611.18639

SynthDCB: World Distillation for Scalable Device Control Benchmarking

Zichen Zhu, Dingye Liu, Nan Jiang, Danyang Zhang, Hang Zheng, Shijie Zheng, Situo Zhang, Kunyao Lan 等 12 位作者

原文摘要

Scaling device-control evaluation requires scaling both interactive worlds and the tasks agents must solve. We introduce SynthDCB, a benchmark for environment awareness and device control built through world distillation (WD). World distillation transforms knowledge of device behaviors, constraints, and environmental effects into modular executable components. A unified capability representation connects tool discovery, world execution, and task synthesis. SynthDCB instantiates Home, Car, and Phone with 114 device classes, 1,166 functions, and 95 events, supporting five task families with 32 subtypes. Explicit states and tool-call traces support task validation and agent evaluation. We evaluate 22 models on 2,560 test tasks; the best achieves 88.8% mean Pass@1. Construction experiments demonstrate token efficiency and expansion of task coverage. At the richest knowledge level, WD fully covers 22/23 properties, 19/29 functionalities, and 30/39 event requirements specified in a real RobotVacuum protocol. Furthermore, the 1,000 sampled tasks semantically cover 81.6% of the 854 reference instructions in the real-world corpus. SynthDCB connects an expanding space of real-to-sim executable capabilities to verifiable agent evaluation.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.25793

When Safety Rationales Hallucinate: Diagnosing and Grounding Multimodal Safety Guards

Yingshuo Wang, Weixiang Zhao, Guancheng Li, Jiahe Guo, Yu Zhang, Yanyan Zhao

原文摘要

Multimodal safety guards increasingly generate rationales alongside safety predictions, yet whether these rationales are reliable remains largely unexplored. We systematically study *rationale hallucination* from two perspectives: visual rationale hallucination, where rationales contain unsupported visual facts, and safety attribution hallucination, where grounded content is assigned an incorrect safety interpretation. Across rationale-generation methods, multiple vision-language backbones, and safety datasets, we find that rationale hallucination is widespread and does not consistently diminish with higher classification accuracy or increased model scale. Further analysis of the Think-with-Image paradigm shows that hallucination is concentrated in fine-grained attributes and relations, while visual tools are often invoked infrequently or without sufficient spatial focus. Based on these findings, we propose *Tool-Contrastive Grounding Reinforcement Learning* (TCG-RL), which rewards tool use only when it improves rationale grounding over a tool-free reference. TCG-RL substantially reduces rationale hallucination while maintaining competitive safety prediction performance. By revealing the gap between prediction correctness and rationale reliability, our study motivates a shift in multimodal safety guarding from outcome-only evaluation toward safety decisions that are both accurate and verifiably grounded.

cs.AI

新论文 · v1arXiv:2611.25788

Collision-Free Is Not Enough: Passage-Conditioned Navigation for Wheeled-Legged Robots

Wai Ka Sun, Waiyiu Pong, Bowen Wang

原文摘要

A collision-free detour can still bring a legged robot to the next stair or ledge a few centimetres or degrees off, and a fixed locomotion skill, factory or learned, can stall or fall. Existing methods prevent this with a robot model or extensive trial and error, but on a new site with unknown skills neither is available, so they cannot be used. We find that a single 27-minute teaching session already supplies what these methods have to derive or learn: for every stair and ledge, one crossing the skill has completed. Our method, passage-conditioned navigation, makes the route remember how each transition was entered, not only where the path went. It stores each taught crossing as an event and, without training or a robot model, enforces it after every local replan: before each ledge, an entry gate makes the robot turn or back up and retry if it is more than 10 cm or 10° off the taught crossing. Under localization noise, with path, gait schedule, and sensing unchanged, this raises the share of disturbed ledge crossings that stay within these limits from 24.1% to 88.6%. In contact simulation with our learned policies, a robot pushed off course before stairs never falls in 180 climbs, against 9 falls when the stored direction is ignored; pushed 1.2 m away, it rejoins the route, ending on average 0.14 m from it (1.10 m without rejoining), and finishes as often as an undisturbed robot. This suits any robot with fixed skills that repeats a route over terrain transitions, as in inspection and patrol, where one wrong entry can end the task. We deployed it in competition on a real wheeled-legged robot: over 271 m of multi-obstacle terrain spanning 7.0 m of elevation, it completed all six runs, won third place at the 2026 Global Open-source AI Challenge, which drew 2,999 submissions, and was the only finalist in its task to finish fully autonomously.

cs.RO · cs.AI

版本更新 · v2arXiv:2610.33881

Sensorimotor behavior from an untrained brain-and-nerve-cord connectome

John R. Minnick, Jesus Gonzalez-Ferrer, Jinghui Geng, Jason K. Eshraghian, Mohammed A. Mostajo-Radji, David Haussler, Mircea Teodorescu

原文摘要

Connectomes map the neurons and synapses of an adult fly's brain and nerve cord, but how much of behavior follows from the wiring is unknown. Here we turn one such connectome into a spiking network of 172,433 neurons with a published brain model's untuned parameters, and run it alone and inside a simulated body. Two fixed rules connect them: odors and looming objects set the firing of the sensory neurons, and the firing of the leg motor neurons moves the legs. Outside the body, a pathway of known function conducts when it supplies a few percent or more of its target's input. In the body, the fly navigates around obstacles to nearly every odor source. A rewiring that keeps each neuron's connection counts and signs reaches far fewer, and the fly's leg commands replayed with the senses off reach almost none. Navigation needs the measured wiring and sensory feedback. Dopamine-gated weakening of the mushroom body's output synapses turns approach to an odor into avoidance, and the learning is associative once one class of olfactory synapse is scaled. An untrained connectome supports a behavior and its learned reversal. The pathways it cannot drive show what the wiring diagram leaves out.

q-bio.NC · cs.NE

版本更新 · v2arXiv:2606.06261

DAST: A VLM-LLM Framework for Cross-Interface Anomaly Detection in O-RAN

Francesco Spinelli, Esteban Municio, Pau Baguer, Gines Garcia-Aviles, Xavier Costa-Perez

原文摘要

O-RAN enables a disaggregated baseband stack with programmable functions that communicate over standardized open interfaces. The same openness that enables multi-vendor composition also expands the attack surface across logically decoupled tiers that make up the compute continuum. Among these threats, Denial-of-Service and performance-degradation attacks, which account for the majority of catalogued O-RAN threats, are particularly difficult to detect. Traditional Time-Series Anomaly Detection (TSAD) methods fail in this new regime where labelled baselines are scarce, threats evolve faster than detectors can be retrained, and the high-dimensional multivariate telemetry overwhelms monolithic inference models. To address these challenges, we present DAST, a zero-shot multi-agent framework for cross-interface anomaly detection in O-RAN that chains a three-stage VLM $\rightarrow$ LLM $\rightarrow$ VLM pipeline. DAST converts multivariate KPI streams into visual representations, scores textual per-interface descriptions against O-RAN domain knowledge, and verifies suspects on high-resolution heatmaps to output the problematic interfaces, the anomalous time intervals, an indicative O-RAN WG11-aligned operational impact rating and the decision rationale. We evaluate DAST on real network traces collected from an O-RAN testbed under representative performance degradation scenarios, achieving 0.910 F1-Score and 0.843 Accuracy, outperforming state-of-the-art TSAD baselines.

cs.NI · cs.AI · cs.ET · cs.MA

新论文 · v1arXiv:2611.25781

Sonic Palette: Predicting Dynamic Color Themes from Music

Wen-Li Wei, Kenneth Yang, Jen-Chun Lin

原文摘要

We present Sonic Palette, a music-driven framework for predicting time-varying color themes from audio. Rather than treating music-to-palette generation as a static problem, our method formulates music--color correspondence as a cross-modal sequence prediction task that models how palette-level visual attributes evolve over time in response to music. Specifically, Sonic Palette uses a music-conditioned autoregressive Transformer to predict frame-wise color themes, each represented by five dominant colors, from input audio features. To support this task, we curate a dataset of paired audio--color sequences derived from 265 full-length official music videos. We further visualize the predicted color themes through a palette-guided recoloring process that preserves image structure while revealing temporally varying color appearance associated with the music. Quantitative results show that Sonic Palette predicts color themes that more closely match the ground truth, while subjective results indicate more natural temporal color transitions and stronger perceived music--color atmosphere alignment, highlighting its potential for music-driven visual design, computational art, and creative visual authoring.

cs.MM · cs.SD

新论文 · v1arXiv:2611.25780

RouteVerify: Routing Interventions for Step-Level Verification in Mixture-of-Experts Models

Yucheng Du, Ryan A. Rossi, Xiyang Hu

原文摘要

Routing states in mixture-of-experts (MoE) models can distinguish correct from erroneous reasoning steps. If changing routing also changes a model's step-level verification judgment, it is tempting to conclude that the judgment follows what routing encodes. We test this inference with RouteVerify, a controlled intervention study that replaces selected internal activations from one solution trace with activations from another, while keeping the evaluated input unchanged. Across nine MoE checkpoints, we compare three intervention interfaces: router logits, MoE outputs, and post-MoE residual states. We vary the layers and token positions at which activations are replaced. We measure changes in a verification margin that quantifies the model's preference for INCORRECT over CORRECT. We also evaluate the same input with activations from correct versus erroneous steps to test whether the resulting judgment depends on the source step's correctness. We report four linked results. First, probes on router logits separate correct from erroneous steps in eight checkpoints (AUROC 0.80-0.88). Second, replacing router logits across all routed layers changes the judgment in all nine checkpoints, and by more than a norm-matched random replacement. Third, this change rarely depends on whether the source step is correct. At one layer, routing from erroneous steps and from correct steps produces indistinguishable margins in all nine checkpoints. Under all-layer routing, their difference is resolved and positive in only one. Fourth, the same difference is positive for local residual replacements in eight of nine checkpoints, so the measure does detect such dependence where it exists. Correctness is therefore readable from routing, and routing replacements move the judgment, but the movement rarely follows correctness.

cs.LG · cs.CL

新论文 · v1arXiv:2611.25778

ECHO: In-Context Behavior foundation model for Humanoid Whole-Body Control

Xingyi Wang, Bin Li, Jiyuan Shi, Chenyun Zhang, Weiji Xie, Xiangyu Miao, Junsong Wu, Wei Song 等 10 位作者

原文摘要

Humanoid behavior foundation models (BFMs) acquire diverse skills through large-scale motion imitation and massively parallel reinforcement learning, yet broad behavioral capability does not ensure precise execution across physical conditions. Without distinguishing the underlying dynamics, policies may favor conservative compromises over environment-specific precision. We introduce ECHO, an in-context BFM that turns interaction experience into environment-specific control, separating general behavioral capability from dynamics-specific execution. Mixed and Annealed Sampling first establishes a behavior prior in a single pretraining stage by balancing targeted practice with broad motion coverage. Building on this prior, Context Representation and Residual Adaptation learns structured dynamics representations from interaction histories to guide residual corrections to the frozen prior, enabling adaptation without test-time parameter updates. Extensive experiments show that ECHO outperforms all baseline methods across diverse motions and physical conditions. Moreover, deployment on the Unitree G1 demonstrates whole-body teleoperation spanning extreme acrobatics and terrain interaction, alongside payload adaptation in manipulation and whole-body control. Page is available at https://mwondering.github.io/echo-bfm/

cs.RO

新论文 · v1arXiv:2611.25776

Suppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-Tuning

Youngwoo Shin, Jongsuk Kim, Junmo Kim

原文摘要

Supervised fine-tuning (SFT) is the stage in which Video Large Language Models (VideoLLMs) advance their capability to reason over video. However, the VideoLLM also learns to answer from textual regularities of its training data, a shortcut that bypasses the video. The regularities behind the shortcut are hard to define at the data level, and the shortcut forms regardless of training epoch, data size, or backbone. The shortcut is hidden behind a rise in accuracy within the training distribution, yet it is not required for the rise and even costs SFT the gain the video offers under distribution shift. We therefore propose Video-Evidence Training via Orthogonal projection (VETO), which intervenes on the fine-tuning update where the shortcut is written rather than on the data. VETO calibrates the subspace that the text alone occupies in the activations of the base model and projects the update onto its orthogonal complement. The VideoLLM is thus left to ground its answer in the full input, with the shortcut suppressed as it forms and never defined. Across seven VideoLLMs, VETO preserves the gain of SFT on the training distribution and suppresses the shortcut. On six benchmarks under shift it gains more than SFT and answers from the full input rather than the shortcut. Code is available at https://github.com/Youngwoo-git/VETO.

cs.CV

新论文 · v1arXiv:2611.25774

DS2Agent: Holistic Device Agents for Accelerated Embedded Board-Level Design

Hongbin Yang, Chi Zhang, Yinhao Xiao, Runyu Pan, Yanni Yang, Xiuzhen Cheng

原文摘要

Embedded board-level development demands extensive expertise, from component selection and device characteristics to interface configuration, driver writing, and system composition. Recently, LLM-based agents have shown strong capabilities, raising the prospect of automating board-level design tasks. However, existing agents either target chip-level design or treat datasheets as static text, offering little guidance on whether a specific component should---or even could---be used for a given board-level design. Moreover, without touching real hardware, they hallucinate incorrect details. To fill this gap, we present {\setlength{\fboxsep}{1pt}\href{https://anonymous.4open.science/r/DS2Agent-9FE8/}{\fcolorbox{blue}{white}{DS2Agent}}}, an open-source framework that constructs interactive agents from device datasheets. Each agent comprises three models: a knowledge model supporting retrieval and question answering; a digital-twin model capturing the physical functionality of the device; and an interface model supporting driver development and system integration. To suppress hallucinations, we also allow optional connections to real devices, so that the agent can calibrate its internalized knowledge against the device. We evaluate DS2Agent on ten devices spanning seven functional categories. Compared with the baseline, the DS2Agent-augmented agent improves the question-answering score from 87 to 97 out of 100 while using 44.8\% fewer tokens. For driver generation, it reduces average token usage per device by 72.9\%. For system integration, it reduces total token usage across three FreeRTOS applications by 29.7\%.

cs.MA

新论文 · v1arXiv:2611.25773

Duopra: From Full-Duplex Conversation to Full-Duplex Agency

Chiyu Chen, Pengzhou Cheng, Yuezhao Ma, Xiaocheng Li, Can Liu, Haonan Hu, Yao Yao, Yifei Yang 等 15 位作者

原文摘要

Full-duplex interaction models exhibit strong conversational agency, enabling natural, low-latency turn-taking, backchannels, and interruptions. However, completing tasks further requires task agency: timely tool invocation and argument revision following user corrections. Frontend-backend agents separate initiation from execution: the frontend decides whether and what to request, while the backend determines how. Execution can be offloaded, but unsent requests cannot be executed, and incomplete ones can misdirect the backend. On Full-Duplex-Bench v3 (FDB v3), most failures of Realtime-Venus-Audio + Harness in our streaming pipeline occur before a domain tool executes. We introduce Duopra, a full-duplex interaction model that learns task execution alongside conversational control. Duopra treats the backend as a tool, accepting a self-contained natural-language request. Direct calls and backend delegation share an action interface and requirements for faithful initiation and correct execution. Its three-stage training combines protocol SFT, full-duplex RL rewarding timely and complete execution, and projector-only repair of talker conditioning after thinker updates. With the same backend, Pass@1 rises from 4.7% to 44.7%; Duopra achieves 47.7% calling tools directly (26.0% after SFT) and 49.3% with a DeepSeek backend. It improves three FDB v1.0 takeover rates over the base model. These results show that task agency can coexist with key conversational agency.

cs.AI

新论文 · v1arXiv:2611.25771

Driver Gaze Target Identification via Gaze Estimation and Structured Driving Scene Understanding

Xinze Cao, Ke Wang, Deyong Guan, Yuanquan Li, Ke Zhang

原文摘要

Identifying a driver's gaze target provides object-level information for visual attention monitoring in intelligent vehicles. Gaze-zone classification and continuous attention localization provide limited information about the identity of the attended scene target. This paper proposes a modular framework that identifies object- or region-level gaze targets from synchronized in-cabin driver images and forward-view road images. The framework comprises four components: MFGaze, which combines a Vision Transformer pretrained with a masked autoencoder (MAE) and head-pose conditioning through feature-wise linear modulation (FiLM); panoptic scene understanding, which constructs a structured candidate set; polynomial ridge regression, which maps gaze features to 2D scene-image coordinates through individualized calibration; and entropy-driven target inference, which adaptively fuses boundary-distance geometry with class-level semantic priors. Experiments evaluate the framework using three public gaze datasets, a laboratory test using Cityscapes road scenes and self-collected gaze data, and the Look Both Ways (LBW) dataset. The complete framework achieves an overall Top-1 gaze target identification accuracy of 96.27% in the laboratory experiment. After sequence-specific calibration, it achieves Top-1 accuracies of 79.92% for task-relevant objects and 85.58% for the road class on LBW. MFGaze achieves the lowest mean angular errors among the compared methods, with 4.06$^\circ$, 4.23$^\circ$, and 10.52$^\circ$ on MPIIFaceGaze, ETH-XGaze, and Gaze360, respectively, and demonstrates strong cross-dataset generalization. Sensitivity analyses show stable performance under hyperparameter perturbations. These results support the framework as a source of object-level gaze information for driver monitoring.

cs.CV · cs.LG

新论文 · v1arXiv:2611.25765

Disentangling Monitor Hardware Artifacts and Smoothing Lag for Shift-Robust Intraoperative EEG and Hemodynamic Risk Calibration

Zeyu Jia

原文摘要

Commercial intraoperative electroencephalography (EEG) and blood pressure monitors introduce cyclic impedance pulses, smoothing delays, direct-current (DC) drift, and cuff holds that confound risk forecasting and uncertainty calibration. We developed a causal signal-conditioning and shift-robust conformal calibration framework across 5,439 public anesthesia procedures. Streaming filters blank 10.13-min 64-Hz impedance checks, apply unclipped post-notch conditioning, separate 63-s suppression-ratio lag, and distinguish three-channel cuff inflations from dropouts across propofol-remifentanil total intravenous anesthesia (TIVA; N = 3,214), volatile anesthesia (N = 2,046), European endoscopy sedation (N = 171), and DC-coupled surgery (N = 8). De-impedanced cortical tree ensembles were compared against deep sequence models, paired with patient-cluster Subgroup-Covariate-Weighted Conformal Risk Control (CRC) and lag-buffered online Conformal Proportional-Integral-Derivative (PID) tracking. Pre-filter blanking removed 97.90% and 97.60% of false flatline conflicts while preserving 99.23% and 98.96% of deep suppression. On unseen TIVA surgeries (N = 525), cortical features achieved area under the precision-recall curve (AUPRC) 0.3135 (1.94% prevalence) and 0.1627 (0.82% lag-free prevalence), with no detectable difference from deep encoders (p >= 0.36) and no cortical gain for hypotension (0.3432 vs. 0.3437, p = 0.784). Zero-retraining volatile transfer (N = 1,048) showed no detectable difference from an end-tidal gas oracle on lag-free suppression (0.0820 vs. 0.0736, p = 0.472). Subgroup-Covariate-Weighted CRC bounded all 70 TIVA shift cells at <= 4.38% (alpha = 5.0%) in 66.32 ms per 30-s epoch. Causal artifact disentangling and shift-aware conformal calibration support reliable real-time intraoperative risk bounds within explicit physiological observability limits.

cs.LG

新论文 · v1arXiv:2611.25763

Closing Performance Gap for Diffusion Language Models under Low Inference Budgets

Hao Wu, Sipeng Chen, Jingwen Fu, Yuwang Wang

原文摘要

Diffusion language models offer an architectural route to low-budget generation by updating multiple tokens in parallel, which can reduce the number of sequential decoding steps relative to token-by-token autoregressive decoding. However, realizing this advantage at low budgets is challenging, as generation quality often declines when the number of denoising and refinement steps is reduced. Editable diffusion models address this quality loss through post-draft refinement, but useful intermediate results may still be lost before final submission. We introduce CaRR (Commitment-aware Refinement and Recovery), a training-free framework which improves submission quality from a fixed editable checkpoint through updated-context refill and trajectory-based recovery within its existing forward schedule. Token Commitment Remasking (TCR) remasks selected native pure replacements and refills them on the next scheduled edit forward using the updated context. Submission Commitment Recovery (SCR) uses the resulting refinement trajectory to recover supported candidates when the final response does not satisfy task-specific output requirements. Both modules operate within the native mask/edit schedule without additional backbone forwards. Experiments on code generation and mathematical reasoning show consistent gains in average accuracy over native ME-DLM across four inference budgets, with the largest gains under tight budgets. At one-eighth of the full scheduled forward budget, CaRR improves the six-metric average accuracy by 7.44 pp, including gains of 11.37 and 10.05 on MBPP and MBPP+.

cs.CL · cs.AI · cs.LG · stat.ML