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

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 07:39 — 2026-11-21 07:39(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 08:48最近发现新增版本:2026-11-20 19:58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。

28,961 已收录论文24,030 AI 相关8,912 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 95 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.26444

Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation

Yuzhi Huang, Jie Wu, Fanding Huang, Junchao Lin, Weichen Zhang, Ziyi Xiong, Yang Li, Zhengwei Xie 等 43 位作者

原文摘要

Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task has three difficulty levels and two scene settings (Clean and Random), yielding 180 configurations. The tasks form three views: Mind tests decisions based on past observations, Act tests precise and timely execution, and Mind2Act combines both in closed-loop tasks where action outcomes guide later decisions. Comparing the three views shows whether a system lacks a capability or fails to compose capabilities it already has. A diagnosis harness further attributes the failed episodes of three representative systems to Mind, Act, or their composition and summarizes each system in a profile card. Our evaluation of multimodal agents, vision-language-action models (VLAs), and world-action models (WAMs) shows that competence in a single view does not carry over to Mind2Act tasks. Even the strongest agent succeeds in 52.7% of Mind and 39.0% of Act episodes but in only 12.0% of Mind2Act episodes. The strongest agent retains task state but struggles with sustained contact, whereas end-to-end policies execute practiced motions but retain little task state. These findings point to composing reasoning and execution through environmental feedback as the main open problem.

cs.RO · cs.AI · cs.CV

新论文 · v1arXiv:2611.26434

HumanCOIN: A 12,500-Hour Dataset for Human Intent in Egocentric Manipulation

Shihan Wu, You Liu, Chunyu He, Minghui Qin, Longhan Jiao, Jinbang Guo, Shaoxuan Xie, Kaixi Tian 等 51 位作者

原文摘要

First-person manipulation datasets treat the observation-action pair as the atomic unit and compress the generation and execution of an action into a policy network's weights, rendering the intent state behind the action unobservable. Human motor control research shows that intent mediates between observation and action and leaves observable traces along the intent pathway from decision to effect: gaze reaches the target before the hand, muscle load builds before contact, and cortical activity precedes the motor command. To record this pathway at scale, we present HumanCOIN, a first-person manipulation dataset built around human intent: 12,500 hours across 38 scene classes with three tiers of proxies. At the output end, the L1 attention tier (10,000 h) infers gaze from headband camera video, exposing the operator's next object of attention and reach before the hand moves. Midway, the L2 exertion tier (2,000 h) records surface EMG from armbands, making load expectations readable before execution is complete. At the origin, the L3 cognition tier (500 h) records scalp EEG, giving early readouts of task decisions and monitoring. Each tier inherits all proxies from the tiers below. The dataset further provides multi-view RGB images, depth maps and point clouds, 6-DoF head and wrist pose, and step-level action and object annotations. The controlled L3 setting additionally measures gaze, hand pose and finger kinematics directly. Clock and calibration data are released with the dataset so that any read rate can be re-aligned. The three tiers cover three stations, from visual orienting to cortical preparation, making the process behind visual-action pairs available for modeling at dataset scale. Project page: https://flagopen.github.io/HumanCOIN.

cs.CV · cs.RO

新论文 · v1arXiv:2611.25474

TuringPAI: A Foundation for On-Device Physical AI

Qiman Wu, Hanlin Chen, Yuhua Wei, Mingyuan Wang, Shaman Tang, Minghao Li, Rui Xin, Xingye Liu 等 28 位作者

原文摘要

Physical AI requires models that understand spatial relationships and dynamic environments and translate observations into actions under limited onboard compute. We present TuringPAI, a family of models for on-device Physical AI comprising TuringPAI-VL for shared vision-language understanding, TuringPAI-Drive for autonomous driving, and TuringPAI-Embodied for robotic manipulation. TuringPAI-VL is a 0.65B model built on HybridViT-MLQ, which combines convolutional local aggregation with Transformer-based global modeling. Multi-scale Latent Queries integrate spatial features and observation history within the same visual Transformer, providing a compact, structured interface to the language model. Training combines general vision-language data with geometric, cross-view, and temporal supervision. TuringPAI-VL supports general multimodal understanding and improves quantitative geometric perception over Qwen2-VL-2B, while providing a shared initialization for the two downstream VLA models. For autonomous driving, TuringPAI-Drive maintains all evaluated ADE/FDE metrics within 1.2\% of a full-token HybridViT baseline using the MLQ interface and achieves comparable aggregate scores in an in-house simulation evaluation. Using XPeng Native Runtime (XNRT) on a single NVIDIA Orin-X SoC, TuringPAI-Drive generates trajectories at 12\,Hz in on-vehicle operation. For robotic manipulation, TuringPAI-Embodied achieves a 96.8\% average success rate across the four LIBERO suites. These results demonstrate a shared vision-language foundation for driving and robotic manipulation under practical on-device constraints.

cs.CV · cs.RO

新论文 · v1arXiv:2611.25428

GenAI-DBT: Evaluating a DBT-Informed Generative AI Platform for Mindfulness Skills Training: A Pilot Randomized Study

Jingchen Ye, Yujia Chen, Leyang Han, Siyuan Wang, Mark Zachary Rosenthal, Yucheng Jin

原文摘要

We evaluated the feasibility, acceptability, and engagement of three digital formats for dialectical behavior therapy (DBT) mindfulness skills training. In a 30-day randomized pilot study, 45 university students were assigned to GenAI-DBT, a general-purpose large language model chatbot (Chatbot), or a static web resource (Web). Forty-two completed the study, and nine completed follow-up interviews. Usability scores were within acceptable ranges across conditions, with no significant between-group differences. GenAI-DBT showed the highest observed participant-week adherence (71.4%, vs. 53.3% for Web and 42.3% for Chatbot), a descriptive difference. Mindful Attention Awareness Scale and Difficulties in Emotion Regulation Scale scores showed no significant time-by-group interactions, and session-level self-reported mood changes did not differ significantly across conditions. GenAI-DBT showed a larger positive change in linguistic valence than Chatbot (4.28 vs. 1.59, P = .02, Cohen's d = 0.99). Interviewees valued contextualized, scenario-based practice and identified response latency, repetition, and limited personalization as areas for improvement. The findings support the feasibility and acceptability of DBT-informed conversational AI for skills practice and motivate further evaluation in larger, more clinically relevant samples. Clinical efficacy remains to be established.

cs.HC

版本更新 · v2arXiv:2611.22717

PCRG: Training-Free Pruning and Caching of Reference Tokens for Video Generation

Siyuan Wang, Haoran Li, Yi Yue, Tak L. Fung, Quan Chen

原文摘要

Reference-to-video diffusion transformers pack the variational autoencoder (VAE) latents of all references and the generated tokens into one full-attention sequence, in which reference tokens make up about half. Because attention cost grows quadratically with sequence length, these tokens take up an even larger share of the attention computation, yet most of them are static, smooth or irrelevant to the output. To accelerate reference-conditioned generation, we propose pruning and caching of reference tokens for video generation (PCRG), a training-free, plug-and-play method that uses two signals the model already computes to assign each reference token to one of three tiers, namely pruned, cached or kept. The first is a low-level redundancy r from VAE latents, since a token whose latent barely changes over time or across its neighbors adds little new content. The second is a high-level importance g from the vision-language-model (VLM) conditioner, where the attention that the prompt and any first or last frames pay to a token tells whether the output needs to read it. Tokens that are not redundant are kept, and redundant tokens are cached if important and pruned otherwise. Pruned tokens leave the sequence before the first step with all rotary position embedding positions unchanged. Cached tokens have their keys and values computed once and reused, and kept tokens are processed as usual. On MiniMax-H3, already distilled to 8 timesteps and quantized to int8, PCRG is 1.57x faster end to end on our V2V-Bench and 1.49x faster on the public VACE-Benchmark, while the quality of VBench drops by only 0.24% and 0.17%, respectively. PCRG shortens the sequence rather than changing how attention is computed or which steps are run, so it also stacks on step caching and sparse attention. On V2V-Bench it reaches 1.86x with TeaCache, 1.82x with Spark at nearly unchanged fidelity and 2.15x with Veda.

cs.CV

新论文 · v1arXiv:2611.24025

Intent Contracts: Taking Tools Away from Agents

Ziyuan Wang, Genliang Zhu, Xiaobo Chen, Chu Wang

原文摘要

Intent contracts are an authorization interface for tool-using LLM agents in which the planning model holds no tools. For each step it submits a short logged contract: a goal, a verbatim quotation of the user, and scope fields. Code validates the contract, and a small trusted model checks it against the user's words and writes the tool call itself. Provided the validation and dispatch code is correct, every executed call is written by the trusted model, the planner's influence on a call is confined to a contract logged before it, and the trusted side decides how much of a request to carry out. We compare contracts with two reviewers of planner-written commands: one sees only the user's words and the command, the information boundary of a reasoning-blind permission classifier, and one also sees the planner's goal and a checked quotation. With gpt-6.1-terra as planner and GLM-5.3-Flash as the trusted model on three AmPermBench task families, every object changed under contracts is named in the goal of the contract that produced the change; under review the planner names objects in its commands and rarely in its goals. When the planner adds work the user never asked for, contracts complete the user's task in 27/30 runs and the intent-visible reviewer in 16/30, because a reviewer can only refuse a whole command. Contracts do not reduce unauthorized actions. They are indistinguishable from blind review, and once the benchmark's environment terms are clarified, every condition that changes state hits a wrong target in 40-49% of those runs. That error is the planner's choice of objects for an ambiguous reference, which no trusted model here can see the environment to check; telling the executor to decline when unsure does not change it. We evaluate benign over-reach with one pair of models, not adversarial planners. We release the plugin and run records.

cs.CR · cs.AI

新论文 · v1arXiv:2611.22901

Done, But Still Working: Anytime Evaluation of When Coding Agents Should Stop

Zerui Yang, Quan Xue, Miaomiao Dong, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents often continue working after their own tests pass. Does this additional work improve the patch, and how much could be saved by stopping earlier? We study these questions through anytime evaluation: replaying recorded runs, scoring intermediate patches with hidden tests, and measuring the cost incurred at each step. For policies that only stop a run or select an earlier patch, this allows paired comparisons without generating new trajectories, provided replay preserves the relevant states. Across about 6,000 runs of eight open models in two scaffolds on SWE-bench Verified, we find substantial differences in the value of continued work. The hindsight saving available at passing self-tests ranges from under 1% to 57%, depending on the model and scaffold. A rule that stops after the same patch passes twice saves 23% in a preregistered replication, but the preregistered quality test does not establish non-inferiority. We explain these differences by measuring how often a rule fires, how often the patch changes afterwards, and whether those changes repair or break it. Fine-tuning agents to imitate the rule saves 30% over six seeds, while quality preservation remains uncertain. Our results help identify both the opportunities and the risks of early stopping.

cs.AI

版本更新 · v4arXiv:2610.12941

DeepRFTv3: Deep Residual Fourier Convolution for Unified Image Deblurring

Xintian Mao, Haofei Song, Huaiyuan Wang, Jiansheng Wang, Qingli Li, Yan Wang

原文摘要

Image deblurring is a fundamental task in computer vision, yet existing methods mainly specialize in isolated scenarios. Consequently, the deblurring performance of these models drops significantly across scenarios with different cameras and image contents. This motivates the development of a unified motion deblurring framework that can handle diverse blur patterns. To this end, we construct a multi-source dataset and develop a data pruning and quality control pipeline. Then, to restore blur images with various motion blur kernels across different scenarios, we propose a unified motion deblurring framework via Fourier Convolution Learning. Existing deblurring networks usually rely on pixel-level mappings and overlook the convolutional nature of blur. Thus, the network mostly fits the image content itself rather than learning the convolution process, making it difficult to handle multi-source blur images. Instead of relying on spatial mapping, we perform blur-adaptive global filter learning in Fourier space, which avoids the limited spatial support of kernel estimation. Extensive experiments demonstrate that our unified model effectively handles motion blurs across diverse sources and scenes, achieving competitive performance across both in-domain and OOD benchmarks.

cs.CV

新论文 · v1arXiv:2611.22356

SR-VLA: Stall-Reduced VLA Execution via Predicted-Input Lookahead and Selective KV Cache Repair

Tao Zhang, Yi Zhong, Jinhao Ruan, Yipeng Gao, Linfeng Zhong, Youming Yang, Yuan Wang

原文摘要

Vision-language-action (VLA) policies incur control stalls when inference blocks the next action chunk. Asynchronous early inference can hide latency, but its results may be inconsistent with the arriving actual inputs. Unconditional reuse risks acting on mismatched inputs, whereas full recomputation discards useful precomputation. We propose SR-VLA, combining predicted-input lookahead with selective KV cache repair. During current chunk execution, a lightweight action-conditioned predictor generates next-boundary visual observations and proprioceptive state. These predictions, together with the task instruction, drive the frozen VLA to precompute a speculative KV cache and action chunk. After real inputs are available to VLA, predicted--real differences and task conditions determine whether to accept the action chunk or trigger selective KV repair. On LIBERO, SR-VLA achieves $2.67\times$ and $1.27\times$ query speedups over the respective synchronous $π_{0.5}$ and OpenVLA-OFT baselines, while maintaining competitive average task success rates. Under target-motion perturbation, success remains baseline-comparable, with $1.52\times$--$1.93\times$ query speedup.

cs.RO · eess.SY

新论文 · v1arXiv:2611.22328

PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows

Zichen Kong, Minghuan Song, Xiyuan Tang, Ziming Wei, Yi Zhong, Yuan Wang

原文摘要

Analog circuit design automation requires both coordinated tool execution and efficient numerical search. Large language models (LLMs) offer new ways to organize tool execution, but finding one sizing that satisfies specifications across process, voltage, and temperature (PVT) corners remains costly. PVTSizing 2.0 addresses these needs through a human-agent workflow built around an independently usable numerical optimizer. An agent carries the designer's approved task through execution and result review. The optimizer reduces unnecessary training through loss-guided updates and uses critic-guided local refinement to explore additional candidates while accounting for cross-corner conflicts. An optional LLM adviser supplies parameter relationships to focus numerical search on circuit-informed directions, while the optimizer selects adjustment amplitudes and verifies their effects through simulation. Across four circuit benchmarks, the standalone optimizer completes all 40 runs and achieves a 7.3x speedup in overall mean runtime over the original PVTSizing, with a comparable mean sample count. In a separate study, the best tested knowledge-injection configuration further reduces mean runtime by 39.9% and simulation samples by 35.4% relative to the standalone optimizer.

cs.AR · cs.LG

版本更新 · v2arXiv:2611.07483

Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs

Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang

原文摘要

Enterprise AI agents split requests across subagents, and each handoff can drop, alter or ignore a requirement. A preregistered study on synthetic, exactly scorable tasks compares free-text, structured JSON and signed requirement-manifest handoffs: the orchestrator extracts each requirement as a verbatim quote plus a checkable predicate, code signs it and deterministically verifies the merger's decision. With Qwen3-8B (1,440 trajectories, five threats), signed manifests cut unsafe commits under attack from 69.4% to 9.0% (60.4 pp, 95% CI [51.4, 69.4]) with no detectable utility loss versus structured handoffs (S2 -0.4 pp, 95% CI [-14.2, 13.3]). Signing defeats in-transit mutation: unsigned manifests violated 79.2 pp more often than signed ones, which never did; this replicated in gpt-oss-20b and gemma-4-12b. There, without an adversary, signed manifests were descriptively slightly worse than structured handoffs (11.1% vs 2.8%; 16.7% vs 8.3%; not tested) and lost utility overall (gpt-oss-20b, all threats: -28.7 pp). On identical Qwen3-8B trajectories, the deterministic verifier caught 78.7% of violating decisions versus 59.0% for an LLM checker, and an oracle manifest removed all remaining unsafe commits, so the residual risk is in extraction. A preregistered pre-signing injection confirmed this: one adversarial line raised signed-manifest unsafe commits from 14.6% to 37.5% (Qwen3-8B), 11.1% to 63.9% (gpt-oss-20b) and 16.7% to 97.2% (gemma-4-12b), and every such commit carried a manifest corrupted before signing. Signing protects transit; extraction is the trust boundary. A testable pre-signing specification (PSE), specified after the injection results and frozen before an offline evaluation, blocked all these injected commits (fixed templates) but refused 45.8%, 11.1% and 22.2% of benign requests, changing completions by -8.3 pp, -2.8 pp and 0.0 pp.

cs.CR · cs.AI · cs.MA

新论文 · v1arXiv:2611.22238

Context Has a Price: Adding and Removing Context for LLM Coding Agents under Prefix Caching

Zerui Yang, Miaomiao Dong, Quan Xue, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents repeatedly send their conversation history to a language model. Adding useful code may reduce search, while removing old tool outputs may shorten later prompts. But do these changes reduce the cost of solving a task? We study this as a measurement problem in more than 20,000 runs of open models on SWE-bench Verified, SWE-bench and Loc-Bench. We account separately for uncached input, cached input and output tokens. Three findings emerge. First, in our main evidence-package experiments, retrieved code reduces read and search commands by 18--34%, but increases cost by 33--42% when cached input costs one tenth of uncached input, without a measurable improvement in resolution. Second, removing old observations can either save money or increase cost: the same approach saves 19--36% without a cache discount but increases cost by 38--116% with a tenth-price cache. Third, shorter prompts do not guarantee cheaper runs because agents may respond by taking more steps. We also find that concurrent experiments can share cached prefixes and distort cost comparisons. These results show why context-management methods should be evaluated using both token prices and the agent's subsequent behavior.

cs.AI

新论文 · v1arXiv:2611.22045

Beyond Acuity Accuracy: A Multidimensional Framework for Evaluating Patient-Facing Emergency Triage AI Tools

Ruio Heerschap, Henry Foote, Mahmoud Alwakeel, Zhouhan Qian, Jiaqi Wang, Elisabeth Bond, Yang Yang, Jonathan Chong Kai Liew 等 22 位作者

原文摘要

Patient-facing AI triage tools may support care-seeking and emergency department prioritization, but require evaluation beyond acuity accuracy alone. We developed SAFE-Triage, a framework integrating human review, automated metrics, LLM-as-judge evaluation, and simulation testing across clinical performance, patient interaction, and clinician-facing summary quality. We applied SAFE-Triage to 40 MIMIC-IV-derived emergency vignettes and a 10,030-case acuity analysis comparing prompted LLM triage (PLT) with rule-augmented prompted LLM triage (rPLT). PLT achieved higher emergency severity index (ESI) accuracy (57.5% vs 42.8%, $P < 0.001$), lower undertriage (13.1% vs 29.8%, $P < 0.001$), and higher clinician ratings across all domains. rPLT produced shorter and more stable outputs with higher automated readability scores. SAFE-Triage identified trade-offs between acuity accuracy, undertriage risk, communication quality, readability, and summary quality, supporting pre-deployment refinement and ongoing monitoring by showing where triage tools are efficient, need improvement, or need clinician oversight.

cs.CL · cs.CY

版本更新 · v3arXiv:2610.04337

FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration

Haopeng Deng, Thomas He, Dayuan Wang

原文摘要

Calibrating microscopic traffic models for urban digital twins is an expensive black-box optimization problem: evaluating each set of car-following and lane-changing parameters requires a full simulation, limiting the evaluations available per recalibration window. Matching raw trajectories yields a rugged objective that sparse surrogates struggle to learn, reducing sequential acquisition to near-random probing. We present FLAT, which couples what to optimize with where to sample next. An eight-dimensional behavioral fingerprint smooths the parameter-error landscape, making the objective learnable from a few dozen samples; annealed lower-confidence-bound (LCB) acquisition then spends each remaining run where it most reduces error. The LCB loop supports a Gaussian process (GP), random forest (RF), or multi-layer-perceptron (MLP) ensemble. Across six heterogeneous real-world scenes, FLAT-GP achieves the lowest scene-averaged behavioral error, winning 6/6 scenes against SPSA, GA, and CMA-ES and 5/6 against TPE under the matched 100-run budget. Some baselines require up to 4.4 times as many simulations to match. Ablations show objective choice shifts final behavioral error by 80.6% on average, removing sequential LCB raises the six-scene mean by 21.7%, and surrogate choice shifts it by at most 4.2%, confirming gains trace to objective geometry and sequential allocation rather than surrogate capacity.

physics.soc-ph · cs.CE · cs.LG

新论文 · v1arXiv:2611.21384

Stability-Compensated Threshold Calibration for Selection-Conditioned Risk Control in Large Language Models

Zhiyuan Wang, Yuanchang Ye, Jiahao Yuan, Jinhao Duan, Xiaoshuang Shi, Weijun Xie, Ye Wei, Kaidi Xu

原文摘要

Large language models often produce hallucinated answers, motivating selective prediction policies that abstain on uncertain queries. However, heuristic uncertainty thresholds alone do not provide statistical control of errors among accepted predictions. Linear Expectation Constraints (LEC) reduce selection-conditioned error rate (SCER) calibration to a nonpositive expected linear-loss constraint, but the associated loss is non-monotonic in the acceptance threshold. We construct an exact counterexample under i.i.d. sampling demonstrating that LEC's empirical threshold-selection rule can violate the population SCER target. To address this risk-transfer gap, we introduce Stability-Compensated Linear Expectation Control (SC-LEC), which uses the negative linear risk of a theoretical full-data reference to compensate for threshold-selection instability. For local expansion beyond a safe anchor, we derive two finite-sample certificates: a stability-based certificate exploiting rank crossings and a direct certificate using the structure of threshold expansion to reduce conservatism. With a valid population anchor margin, our certificate conditions ensure finite-sample marginal SCER control, and independent margin certification further provides a $1-δ$ high-probability guarantee for this calibration-averaged control. Experiments on CommonsenseQA, ARC-Challenge, and TriviaQA show useful retention gains beyond the same certified anchor, while revealing conservative behavior in small-margin regimes.

cs.CL

新论文 · v1arXiv:2611.21098

MedicalDPO: Multi-Objective Direct Preference Optimization for CT to PET Translation

Huiting Zhang, Yingxin Cai, Siyuan Wang, Xi Yang, Yuyao Yan, Rui Zhang, Kaizhu Huang

原文摘要

CT-to-PET synthesis estimates functional PET images from anatomical CT scans for auxiliary analysis, representation pretraining, and missing-modality completion. Brownian Bridge diffusion models can produce multiple PET candidates of different quality under the same CT condition, exposing an intra-condition quality hierarchy. Candidate quality spans complementary spatial, structural, and intensity dimensions, while DPO-only fine-tuning may compromise absolute synthesis fidelity. We propose MedicalDPO which converts this hierarchy into preference supervision automatically constructed from paired CT-PET training data. Multiple candidates are ranked across the three fidelity dimensions, and strict cross-metric verification retains preferred-rejected pairs with consistent quality separation. Relative denoising-error preference optimization is jointly trained with the original Brownian Bridge objective to anchor the pretrained CT-to-PET mapping, while condition-balanced multi-pair rotation distributes preference supervision across CT conditions. Experiments on BBDM and CPDM show improvements across LPIPS, MAE, SSIM, and PSNR. Further analyses demonstrate metric complementarity and clear pair separation, while ablations show that the original training objective prevents the substantial degradation caused by DPO-only fine-tuning.

cs.CV

版本更新 · v2arXiv:2611.16424

PhysCapBench: A Cross-Domain Benchmark for Physically Grounded Video Captioning

Haofeng Wang, Xuanyi Liu, Pengcheng Wen, Ruiqi Li, Yuhao Zhang, Tiange Zhang, Boren Zheng, Siyu Tao 等 15 位作者

原文摘要

Physical AI aims to learn transferable physical knowledge from real-world experience to understand, predict, and act in the physical world. Internet videos and embodied demonstrations provide complementary observations of motion, interaction, and state evolution. A foundational data challenge is to measure and preserve this physical information as training supervision. In video-language pretraining, captions express observed processes in language, yet a semantically correct description can omit the interactions and transitions that define those processes. Rich physical experience in video does not automatically translate into sufficient language supervision. This gap calls for a yardstick to assess annotation quality, compare captioning strategies, and guide training-data refinement. Motivated by our data construction for world-model pretraining, we introduce PhysCapBench, to our knowledge the first unified physical-caption benchmark spanning all three domains: third-person scenes, egocentric manipulation, and handheld-gripper demonstrations. It provides human-verified annotations for 1,500 video sequences and evaluates accuracy and coverage through seven physical dimensions. We examine downstream utility through video reconstruction and manipulation-policy fine-tuning. Physical captions reduce reconstruction LPIPS by 8.6-9.5% on third-person videos and 26.9-30.9% on egocentric videos relative to metadata captions. Training-instruction enrichment improves both PhysCapBench scores and policy success, including a 7.5-percentage-point gain for pi0.5 on a RoboTwin 2.0 subtask. PhysCapBench makes the physical content of language supervision inspectable and comparable, providing a cross-domain basis for its evaluation and improvement.

cs.CV · cs.AI

新论文 · v1arXiv:2611.18305

PROOF: Perceptive Robustness via Out-of-Distribution Fallback for Legged Locomotion

Siyuan Wang, Dongjie Zhu, Jinxuan Lu, Wenjun Xu, Jiankun Wang

原文摘要

Vision-based perceptive locomotion has enabled legged robots to achieve agile and terrain-aware locomotion across complex environments. However, the reliability of such systems heavily depends on visual observations, which are inherently susceptible to occlusion, reflective surfaces, and illumination variations, often resulting in catastrophic locomotion failures under degraded perception conditions. In this paper, we present PROOF (Perceptive Robustness via Out-of-Distribution Fallback for Legged Locomotion), a perceptive locomotion framework that enables robust locomotion under severe visual disturbances. Our method adopts a two-stage teacher-student learning paradigm that explicitly models perception reliability: the teacher learns both perception-driven and proprioceptive fallback behaviors, while the student predicts exteroceptive features with uncertainty and suppresses them under out-of-distribution inputs. We evaluate our method on a Unitree Go2 quadruped equipped with a RealSense D435 depth camera in real-world settings. Under normal visual conditions, our method enables the robot to successfully perform high-dynamic parkour maneuvers, including traversing large gaps, elevated platforms, and narrow beam terrains. Under severe visual degradation, such as heavy occlusion and strong illumination changes, the robot continues to maintain stable and robust locomotion performance.

cs.RO

版本更新 · v2arXiv:2611.12762

Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

Weida Wang, Benteng Chen, Yigeng Jiang, Shuchen Pu, Weiping Shen, Zichao Liu, Yulin Su, Zitong Wang 等 90 位作者

原文摘要

We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2. It also performs well on two external scientific ideation benchmarks. Five expert-guided collaborations further connect its proposals to experimental and computational validation across chemistry, materials science, and engineering. In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. These results support metacognitive regulation as an approach to scientific ideation and its progression toward practical validation.

cs.AI

新论文 · v1arXiv:2611.17864

Disentangling Forgetting from Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection

Xiuyuan Wang, Weiming Liu, Zongxin Yang, Fan Wang, Liemiao Jin, Rubin Qin, Wei Chen, Bin Shi 等 10 位作者

原文摘要

Large Language Models (LLMs) pose significant security risks by retaining private or hazardous information, creating an urgent need for unlearning techniques that excise specific knowledge without compromising general utility. However, prevailing fine-tuning-based unlearning methods struggle to achieve this balance, often suffering from computational inefficiency and unintended utility degradation due to the entangled nature of knowledge within model parameters. To disentangle forgetting from utility, we propose UUE, a theoretically grounded framework that reformulates unlearning as controllable model editing. First, UUE projects parameter updates into the orthogonal left null space of retained knowledge representations, strictly ensuring that the editing process causes minimal interference to the model's general capabilities. Second, distinct from targeted mapping, we introduce a convex untargeted objective that derives a closed-form analytical solution to effectively disrupt undesired knowledge by pushing forget-set embeddings toward their antipodal points. We implement UUE via lightweight, pluggable adapters (including a low-rank variant, UUE-L), enabling efficient deployment without modifying the frozen backbone. Extensive experiments on TOFU and WMDP benchmarks demonstrate that UUE and UUE-L achieve superior unlearning efficacy, significantly outperforming existing methods.

cs.LG

版本更新 · v2arXiv:2611.08269

Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations

Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang

原文摘要

After an API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a typical-input release check ships it. We report a preregistered study of 73 tasks on 60 documented changes in CPython, Node.js and SQLite. In the main stages, repairs are choices among documented code fragments, run on the real runtimes against withheld contracts. Over the complete repair space, the all-assertions gate on typical inputs released 0.410 of wrong repairs. One edge input written from the release note cut this to 0.065, and to 0.061 on 15 unseen clusters; three inputs from a blind low-cost commercial writer (GPT-5.6-luna) reached 0.070. Two more frozen stages enlarged the menu to 1491 fragments and added 233 hard distractors that match legacy output on typical inputs. The edge input (0.058) and the GPT-5.6-luna writer (0.058) passed preregistered tests (two local-model writers did not), yet 0.168 and 0.153 of hard wrong programs still passed (task means; post hoc: pooled 0.104 and 0.081; models rarely chose them). In all three open-weight families and menus, the edge input cut wrong releases per attempt without materially lowering correct completion; self-tests helped less. A blind AI audit flagged 34 of 73 contracts (20 as too strict). Three post-hoc blind human reviewers of strictness (the first author and two non-author software practitioners) upheld none of its 11 such flags in 40 sampled contracts; a majority judged one contract (py-random-seed-tuple) stricter than its requirement. Dropping disputed checks changed 0 verdicts; class-label disputes are open. In a preregistered free-form addendum, models wrote whole programs, run only in a sandbox; for clean-running wrong programs, the edge input cut releases from 0.517 to 0.114 for gpt-oss-20b (Holm p 0.001) and from 0.653 to 0.113 for qwen3.6, but only from 0.713 to 0.481 for GPT-5.6-luna (descriptive).

cs.SE · cs.AI

版本更新 · v3arXiv:2606.28228

Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

Yuanyuan Wang, Wenjie Wang, Haoxuan Li, Mingming Gong, Kun Zhang

原文摘要

Causal representation learning for time series has developed strong identifiability results in discrete-time latent causal models, but identifiability in continuous-time latent stochastic differential equation (SDE) models remains largely open. We address this gap using environment-induced shifts in diffusion covariance. We study additive-noise latent SDEs observed through an unknown nonlinear diffeomorphism, with shared drift but environment-specific diffusion covariance. We show that two diagonal diffusion regimes with pairwise distinct coordinate-wise variance ratios identify the latent coordinates up to permutation, coordinate-wise scaling, and a possible constant shift, without any sparsity assumption on the drift. We first prove this result for linear Ornstein-Uhlenbeck systems and then extend it to general additive-noise latent SDEs. Under mild smoothness, the instantaneous drift-Jacobian causal graph is identifiable up to the same permutation. We propose a two-stage estimator for latent disentanglement and optional graph recovery; experiments on synthetic systems confirm the predicted identifiability boundary, and an application to Hardanger Bridge monitoring data illustrates the approach on real sensor trajectories.

cs.LG · stat.ML

新论文 · v1arXiv:2611.16201

An Extensive Evaluation of Machine Learning and Deep Learning Approaches for Sentiment Analysis: Insights from Amazon Customer Reviews

Muhammed Ihsan Corak, Cuiyuan Wang, Xiaowen Zhang

原文摘要

The rapid growth of user-generated text on online platforms creates opportunities for understanding customer opinion and supporting data-driven decisions. This study compares five traditional machine learning classifiers (Random Forest, Logistic Regression, Bernoulli Naive Bayes, Linear Support Vector Classifier, and Multinomial Naive Bayes) and six deep learning architectures (LSTM, Bi-LSTM, GRU, RNN, Attention, and FastText) for three-class sentiment classification of 568,454 Amazon Fine Food Reviews. Machine learning models used Bag-of-Words (BoW) and TF-IDF features limited to 5,000 terms; deep learning models used learned embeddings over a 20,000-word vocabulary. Models were evaluated on the original imbalanced data and on a random-oversampled balanced set of 1,070,469 reviews, using accuracy, macro and per-class precision, recall, and F1-score, and training time. On the balanced set, Random Forest with BoW achieved 99\% accuracy and the Attention model achieved 98.7\%. Linear SVC reached 89\% accuracy in 1 min 15 s, and Logistic Regression reached 90\% in 3 min 37 s. On the imbalanced set, the Attention model achieved 97.8\% accuracy, and FastText achieved 95.3\% in 3 min 26 s, while the RNN reached 91.9\% with a neutral-class F1-score of 0.08. Deep learning models were more stable across class distributions, whereas the best classical model depended on balancing. We also report a user-facing application that applies the trained Random Forest and Attention models to new review text. Because the labels are derived from star ratings, the results measure agreement with rating-derived sentiment classes rather than annotated sentiment; the dataset is a single source, and the findings should be read with that limitation in mind.

cs.LG

新论文 · v1arXiv:2611.16072

KVPath: Connecting Key-Value Representations Across Transformer Layers

Xuan Luo, Zhiyuan Wang, Hanzhong Cao, Xifeng Yan

原文摘要

Transformers typically cache an independent key-value (KV) representation for each token at every layer. Recent work reveals that a token's KV representations across neighboring layers are correlated and contain shared information. We hypothesize that this correlation implies incremental inter-layer changes, which can be effectively captured by low-dimensional deltas. Motivated by this, we propose KVPath, a new KV representation paradigm that connects KV representations across the network depth into a path. The path establishes a full-dimensional base KV at the first layer, while subsequent layers generate low-dimensional delta KVs to update the preceding KV, thereby constructing their own KV states. By caching the base KV once alongside these compact delta KVs, KVPath preserves distinct layer-specific representations without storing full KV states at every layer. We develop two variants of KVPath: KVPath-Residual, which updates vector values via residual addition, and KVPath-Rolling, which progressively updates feature dimensions in a rolling manner. Under matched parameter counts, KVPath reduces KV-cache storage by up to 68\% for Grouped-Query Attention (GQA) and 55\% for Multi-Head Latent Attention (MLA), while maintaining or even improving model performance.

cs.LG

版本更新 · v2arXiv:2602.13961

MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars

Shuoyuan Wang, Yiran Wang, Hongxin Wei

原文摘要

Data-driven approaches like deep learning are rapidly advancing planetary science, particularly in Mars exploration. Despite recent progress, most existing benchmarks remain confined to closed-set supervised visual tasks and do not support text-guided retrieval for geospatial discovery. We introduce MarsRetrieval, a retrieval benchmark for evaluating vision-language models for Martian geospatial discovery. MarsRetrieval includes three tasks: (1) paired image-text retrieval, (2) landform retrieval, and (3) global geo-localization, covering multiple spatial scales and diverse geomorphic origins. We propose a unified retrieval-centric protocol to benchmark multimodal embedding architectures, including contrastive dual-tower encoders and generative vision-language models. Our evaluation shows MarsRetrieval is challenging: even strong foundation models often fail to capture domain-specific geomorphic distinctions. We further show that domain-specific fine-tuning is critical for generalizable geospatial discovery in planetary settings. Our code is available at https://github.com/ml-stat-Sustech/MarsRetrieval

cs.CV · astro-ph.IM · cs.CL

版本更新 · v2arXiv:2605.15729

Constructing Generalizable Parallel Algorithm Portfolios for Multi-Objective Binary Optimization via General-Purpose Instance Generation

Zhiyuan Wang, Shengcai Liu, Shaofeng Zhang, Ke Tang

原文摘要

Despite progress in constructing generalizable parallel algorithm portfolios~(PAPs), no general-purpose method is yet available for multi-objective binary optimization problems~(MOBOPs) without problem-specific customization. To fill this gap, this work proposes domain-agnostic co-evolution of parameterized search for multi-objective binary optimization~(DACMO), the first general-purpose method for automatic PAP construction on MOBOPs. Its core, Unified Instance Representation~(UIR), represents and generates MOBOP instances with varying dimensions without knowledge of problem-specific instance structures. UIR separates common features of the target class from instance-specific features, preserving the common features learned from real instances during generation. DACMO co-evolves the training instances and PAP by alternating UIR-based instance augmentation with PAP updates. Experiments cover four structurally different MOBOP classes, including two black-box classes from real-world applications. Starting from five real training instances per class, DACMO constructs high-performance PAPs without problem-specific customization. On unseen instances from all four classes, these PAPs outperform portfolios of tuned classical multi-objective evolutionary algorithms and those constructed by the recent automatic PAP construction method EoH-S. DACMO also achieves overall performance comparable to the strong CEPS baseline and significantly outperforms it on two classes, without the substantial expert effort CEPS requires for problem-specific instance generator design.

cs.NE

新论文 · v1arXiv:2611.14941

Reality Perception Gap: Are AI-Manipulated Video Detectors Ready for the Real World?

Xiangrui Liu, Xinmiao Luan, Xinyuan Wang, Zhiyuan Fang, Chi-Yao Huang, Douglas C. Montgomery, Yanjie Fu, Felix Juefei-Xu 等 9 位作者

原文摘要

AI-manipulated video detectors are typically evaluated on clean, curated datasets. In deployment, however, videos have usually passed through repost compression on social-media platforms and sometimes were captured by imperfect hardware. To measure detection under these conditions, we introduce Reality Perception Gap (RPG), a benchmark of 10,000 videos from frontier generators and partially synthetic edits, processed with cross-platform repost compression and paired with real footage that carries camera-side optical artifacts. RPG also includes socially fragile content, such as crime and wartime footage, where fabricated videos can cause severe social harm. Across 18 detectors, none catches more than 15% of fakes at a 1% false-positive rate. A positive control and a re-encoding sweep separate two sources of failure: generator and content shift degrades detectors before any compression, and repost compression erases the low-level traces that the artifact-based detectors relies on. Existing detectors therefore struggle when deployment conditions strip away the generation artifacts they rely on. These complementary failures suggest that robust detection requires training under deployment conditions and combining low-level, temporal, and semantic evidence, where passive detection may have reached its limits.

cs.CV

新论文 · v1arXiv:2611.13596

Towards Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics

Qinan Zhang, Xinyu Wang, Qihang Jin, Tianyuan Wang, Hongbing Luo, Pengfei Li, Wenjun Lv, Yu Kang 等 9 位作者

原文摘要

Vision-language models (VLMs) are increasingly used as automated judges for multimodal and embodied tasks, yet aggregate accuracy or consistency alone does not reveal whether a judge changes its verdict for the right reason. We propose State-Conditional Invariance (SCI), a reliability principle requiring a judge to remain stable under semantics-preserving changes in presentation while responding to causal interventions that change the task outcome. We instantiate SCI in GridWM-Judge, a simulator-grounded diagnostic benchmark built from deterministic MiniGrid trajectories with aligned Full, evidence-removal, and counterfactual variants, plus presentation and representation probes. Across five diagnostic tasks, GridWM-Judge tests local perception, action-conditioned transitions, presentation stability, representation exchangeability, and Full-CF causal discrimination. Our diagnostic evaluations reveal heterogeneous failure modes, including sensitivity to evidence presentation and encoding, low activation on successful trajectories, and weak paired counterfactual discrimination. Perception-controlled analyses further indicate that visual grounding and objective recovery are substantial, model-dependent bottlenecks. These results motivate jointly reporting correctness, presentation stability, and causal sensitivity instead of relying on a single score.

cs.AI · cs.CL · cs.CV · cs.LG

版本更新 · v2arXiv:2604.23442

资源受限边缘设备上基于无人机的杂草检测用于特定地点管理

Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices

Linyuan Wang, Haibo Yao, Te-Ming Tseng, Kelvin Betitame, Xin Sun, Yanbo Huang, Dong Chen

AI 速读 基于摘要

该研究提出面向部署的无人机实时杂草检测框架,在三种Jetson边缘设备上系统评估YOLO与RT-DETR系列模型的精度—延迟权衡。

cs.CV

查看原文摘要

Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although deep learning models have been deployed on UAV-based edge systems, a systematic understanding of how different model architectures perform under real-world resource constraints is still lacking. To address this gap, this study proposes a deployment-oriented framework for real-time UAV-based weed detection on resource-constrained edge platforms. The framework integrates UAV data acquisition, model development, and on-device inference, with a focus on balancing detection accuracy and computational efficiency. A diverse set of state-of-the-art object detection models is evaluated, including convolution-based YOLO models (v8-v12) and transformer-based RT-DETR models (v1-v2). Experiments on three edge devices (Jetson Orin Nano, Jetson AGX Xavier, and Jetson AGX Orin) demonstrate clear trade-offs between accuracy and inference latency across models and hardware configurations. Results show that high-capacity models achieve up to 86.9% mAP50 but suffer from high latency, limiting real-time deployment. In contrast, lightweight models achieve 66%-71% mAP50 with significantly lower latency, enabling real-time performance. Among all models, RT-DETRv2-R50-M achieves competitive accuracy (79% mAP50) with improved efficiency, while YOLOv10n provides the fastest inference speed. YOLOv11s and RT-DETRv2-R50-M offer the best balance between accuracy and speed, making them strong candidates for real-time UAV deployment.

版本更新 · v2arXiv:2607.26515

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Yaoyuan Wang, Yao Wang, Junsong Wang 等 13 位作者

原文摘要

We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 baseline, exposing rollout--training mismatch as the principal failure mode and ruling out standard pretraining-style fixes. We address this with Rollout Residual Quantization (Rollout-ResQ): a single residual correction term constrained to a hardware-friendly sparsity pattern, added only to the FP4 rollout matmul -- a lightweight correction that recovers most of the precision lost to outlier-driven underflow without inflating the rollout's compute footprint. On Qwen2.5-3B, Rollout-ResQ paired with the HiFloat4 (HiF4) format -- whose three-level hierarchical scaling preserves resolution under FP4's tight 4-bit budget -- closes the accuracy gap to BF16 from 3.59% to 1.39%, bringing fully quantized FP4 RL within close reach of full precision. Applied to the open-standard MXFP4, the same recipe narrows the gap from 13.6% to 5.3%, revealing that FP4 format choice is a key factor that determines the ceiling on recoverable accuracy. The experimental results on Qwen2.5-Math-7B further confirm the recovery benefits of Rollout-ResQ with HiF4. Together, these results establish HiF4 as the enabling format for end-to-end FP4 RL post-training, and Rollout-ResQ as the activation-side mechanism that makes the gap to BF16 closable.

cs.LG · cs.AI