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
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 08:55 — 2026-11-16 08:55(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:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2611.12099

SAM-VTP: Video Memory and Measured Geometry for Continuous Traversability Segmentation

Lucas Hoefs, Hui Xie, Senjian An, Fangyi Zhang

原文摘要

Traversability prediction is a core component of autonomous navigation, yet most vision-based methods operate frame-wise and produce temporally inconsistent predictions. We present SAM-VTP (Video Traversability Prediction), which fine-tunes SAM2's video memory pathway for dense, prompt-free traversability segmentation, conditioning each frame on a persistent memory of prior observations. Rather than inferring terrain geometry from appearance, we measure it: slope, roughness and height are computed from depth and fused into the image features. We also introduce an offline continuous supervision pipeline that generates dense per-pixel traversability targets in [0,1] from depth-derived geometry and semantic priors, requiring no robot deployment and no per-pixel annotation, capturing conditional feasibility that binary labels cannot represent. On TartanGround, a large-scale synthetic ground-robot dataset, SAM-VTP improves fuzzy Jaccard from 0.908 to 0.924 and binary IoU from 0.854 to 0.886 over SAM-TP, a frame-wise SAM2 baseline, against a seed-to-seed spread below 0.001, and cuts frame-to-frame flicker by 31%. In closed-loop trials at two field sites, driving the same planner and controller, the baseline's dropouts leave the planner without a feasible path 3.3x more often on a paved course and 6.9x on rough ground, while SAM-VTP runs at 21.4 FPS on the Orin Nano the robot carries.

cs.RO

新论文 · v1arXiv:2611.15004

A Cardiorespiratory Foundation Model Pretrained on Ten Physiological Signals for Perioperative and Critical Care

Cheol-Hui Lee, Wookyung Kim, Hyeonhoon Lee, Garam Lee, Da-in Eun, Hyung-Chul Lee

原文摘要

Arterial, venous, pulmonary artery and intracranial pressures and ventilator waveforms guide decisions in operating rooms and intensive care units, yet foundation models for physiological waveforms have been built almost entirely on the electrocardiogram and photoplethysmogram. We present CARMEN, a single encoder pretrained without labels on ten cardiorespiratory waveforms (2.27 million modality-hours). CARMEN accepts any combination of co-recorded signals from 10 s to 5 min, and a conditioning mechanism, LSCNorm, restores the absolute signal level that normalization removes; without it, the AUROC for intraoperative hypotension fell from 0.894 to 0.780. Across 19 tasks from Korean and US cohorts, the frozen encoder outperformed supervised models on 12 of 15 and three foundation models, one general-purpose and two for biosignals, on 14 to 17 of 19, with none exceeding it on any task. Given the electrocardiogram or photoplethysmogram alone, it matched or exceeded signal-specific foundation models in most comparisons, and it retained its performance when channels were missing.

cs.LG · cs.AI

新论文 · v1arXiv:2611.15003

LLM-Enhanced Deep Reinforcement Learning with Human-in-the-Loop Calibration for Real-Time Optimal Power Flow

Jiayang Tu, Bozhen Jiang, Bojun Du, Yunxiao Ling, Ershun Du, Qin Wang

原文摘要

Real-time optimal power flow (RT-OPF) requires fast and reliable decision-making under time-varying operating conditions. However, many practical operating preferences and safety related requirements are difficult to encode using conventional numerical rewards alone, which limits the effectiveness and controllability of deep reinforcement learning (DRL) for RT-OPF. To address this issue, this paper proposes an LLM-enhanced DRL framework with human-in-the-loop (HITL) for RT-OPF. The proposed method augments the physics-based reward with sparse language evaluative feedback during offline training, so that semantic operational requirements can be incorporated into policy learning. To improve reliability in RT-OPF, a selective HITL calibration mechanism is further introduced to inspect and correct questionable LLM judgments before they continuously shape the learning process. Case studies on the IEEE 30-bus and IEEE 118-bus systems show that LLM feedback improves policy safety over vanilla TD3, while further HITL calibration achieves the best overall performance and more stable training behavior. These results demonstrate the effectiveness of combining language guidance and expert calibration for RT-OPF.

eess.SY · cs.AI

新论文 · v1arXiv:2611.15002

AI4Plasma I: Data-Efficient Surrogate Modeling of Capacitively Coupled Plasma Fields

Zhenyu Zou, Junjue Liao, Hao Yang, Luowei Yin, Chenyu Wang, Yufeng Wei, Zhichao Peng, Chun Chen 等 15 位作者

原文摘要

Reference capacitively coupled plasma (CCP) simulations provide spatially resolved plasma fields but are costly to generate across operating conditions. We compare the data efficiency of five surrogate architectures--Coordinate MLP, PCA-Net, U-Net, Fourier neural operator (FNO), and Transolver--for predicting RF-cycle-averaged electron density, ion density, electric potential, and electron temperature in 1D planar and 2D axisymmetric GEC CCP benchmarks. We assess the number of reference simulations needed to achieve 1% and 2% mean relative L2 error for parameter-interior and parameter-boundary test cases, and examine architecture-specific mechanisms. FNO achieves the lowest or joint-lowest reference-case requirement in seven of eight comparisons. In 1D, FNO reaches 1% interior error with 50 training cases, compared with 100 for Transolver and 200 for U-Net. In 2D, FNO and U-Net each reach 1% interior error with 100 cases; FNO and Transolver each reach 2% parameter-boundary error with 200 cases, compared with 400 for U-Net. At the stricter 1% 2D parameter-boundary target, Transolver requires 400 cases versus 800 for FNO. Additional analyses investigate FNO spectral modes and padding, U-Net skip connections, Transolver adaptive slicing, and PCA-Net projection versus prediction error. The results support FNO as a data-efficient baseline for the tested CCP settings, while showing that the preferred architecture depends on the accuracy target and operating-parameter region.

cs.LG

版本更新 · v4arXiv:2611.01666

Stand-In Effects and Pooling Amplification: Lessons from Biological World Models for Testing Action Effects

Bowen Xu, Boyu Chen, Jiaying Li

原文摘要

Whether an action-conditioned world model responds to actions is usually checked by replacing or removing the actions and measuring the loss in accuracy. Taking biological experiments as the guiding case, we show that such diagnostics report action effects where there are none: under autocorrelated designs, future actions stand in for history the model does not see. When the design law is known, a conditional randomization test written as an e-value is valid in finite samples whatever the model. A second failure arises whenever many sites share one action sequence, as in world models: the pooled score turns small model errors along the action contrast into an e-value near zero, so a valid test loses its power although the effect is real. Tempering the score changes the bet, not the validity. The log e-value is concave in the tempering factor and zero at zero, so too small a factor costs little and too large a one can cost everything; every single factor we tried, estimated or tuned, failed in some setting, and mixtures over a fixed grid never did. Our own preregistered analysis of optogenetic ERK experiments failed by pooling; a tempered statistic, registered before the data were obtained, then rejected the null on a never-opened field (E = 1.1e10). In three registered tests on models trained by others, the pooled test rejected in 0 of 96 units of a diffusion model, and reached the power bar in 10 of 26 Atari games under IRIS's token likelihood and 1 of 6 control tasks under TD-MPC2; mixtures fixed in advance reached it in 96 units, 24 games and 6 tasks. On recorded robot video with iVideoGPT the mixture rejected in 155 of 159 trajectories; the pooled test did not collapse there (143). Under exact nulls the statistics made 14 rejections in 26,664 tests.

cs.LG · q-bio.QM · stat.ME

新论文 · v1arXiv:2611.15001

Understanding Suggested Edits in Stack Overflow: A Large-Scale Empirical Study and Review Prioritization Framework

Mehedi Hasan Shanto, Muhammad Asaduzzaman, Md. Ahasanuzzaman, Alioune Ngom

原文摘要

Suggested edits allow low-reputation users to improve Stack Overflow posts and contribute to the platform's knowledge base. However, we still know little about why these edits are accepted or rejected and how reviewers can efficiently identify problematic edits. In this study, we analyze 3,888,805 suggested edits submitted between 2011 and May 2023. First, we compare accepted and rejected edits using 35 features. We find significant differences between them, with the largest differences related to users' editing history. Second, we manually analyze rejected edits and identify 17 fine-grained rejection reasons. These reasons provide a more detailed understanding of why edits are rejected than Stack Overflow's predefined rejection reasons. Third, we evaluate three models for prioritizing edits based on their likelihood of rejection. The Feature Model, built using the 35 studied features, provides the best trade-off between review rate and rejected-edit recall. At a decision threshold of $τ= 0.40$, it prioritizes 52.3% of edits for human review while capturing 80.8% of rejected edits. In comparison, the Embedding Model captures 78.8% of rejected edits while prioritizing 60.9% of edits, and the EditEx Model captures 72.5% while prioritizing 59.0%. We also conduct a complementary zero-shot evaluation on a separate set of 500 edits. The Feature Model achieves 78.0% recall at $τ= 0.40$, compared with 23.6%-31.2% for GPT-4o, Qwen2.5-32B, and Llama-3.3-70B. Overall, our findings provide a detailed understanding of suggested-edit rejection and show that rejection-risk prediction can help prioritize potentially problematic edits for human review.

cs.SE

新论文 · v1arXiv:2611.15000

QSim-Arena: an evolving developer for quantum simulation advantage

Jue Xu, Yue Wang, Qi Zhao

原文摘要

Where practical advantage emerges in quantum dynamics simulation remains a central debate in quantum computing. Claimed advantages can be rapidly narrowed or overturned by stronger classical methods, while progress on both sides can outpace the journal publication cycle. We present QSim-Arena, a research framework in which AI agents combine a closed loop of verification and benchmarking with open exploration. Hamiltonians, initial states and accuracy targets for evolved states or observable expectation values provide explicit specifications for evaluating simulation methods. Agents translate published techniques into executable components, reproduce reported results and benchmark their performance across diverse Hamiltonian families. Competing classical methods are implemented and independently crosschecked, providing credible baselines for end-to-end quantum resource estimates based on rigorous error bounds and empirical calibration. Alongside this closed loop, agents recombine classical simulation techniques and co-design fault-tolerant quantum circuits using knowledge extracted from the literature. Initial applications improve baseline resource estimates through the integration of established techniques. QSim-Arena thus treats quantum advantage assessment as an evolving, reproducible research process that can respond to advances in algorithms, error analysis and hardware.

quant-ph · cs.AI

新论文 · v1arXiv:2611.14999

Towards Runtime-Aware Observability for Java Virtual Threads

Wenjie Ding

原文摘要

OS-level observability tools join application requests to kernel events through the OS thread ID, assuming that a unit of work occupies one OS thread until it completes. Java virtual threads break this assumption: many virtual threads are multiplexed onto a few carrier threads, so a stable thread ID hides a changing unit of work, and the join fails silently. Existing virtual-thread-aware channels republish context or identity on every mount and unmount, and the JVMTI-based one pays this cost for the lifetime of the JVM, whether or not an observer is attached. We bind a 64-byte off-heap trace buffer to each virtual thread, at a fixed address for its lifetime, and publish the address to eBPF consumers through four USDT probes in a patched OpenJDK; a re-implemented JVMTI channel over the same buffer serves as a controlled comparison. The four-probe design attributed all 768 test markers correctly on both the content and the identity plane, while the naive two-probe design silently misattributes trace context. With no consumer attached, publication costs at most about 33 ns per transition; the remaining dormant cost is buffer allocation, about 0.37 microseconds per virtual thread, which is negligible on transition-heavy workloads but nearly doubles the cost of a creation-only microbenchmark. The JVMTI channel costs about 20% on transition-heavy workloads and about 1.8 microseconds per virtual thread on the creation-only one. We also show that, of the two update strategies OTEP 4947 permits, only in-place rewriting guarded by the record's valid flag is sound for readers that cache the record's address, as lifecycle-event readers do.

cs.PF · cs.OS · cs.SE

新论文 · v1arXiv:2611.14997

Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving

Wentao Zhang, Xiaoyu Zhang, Chengwei Liu, Yutao Hu, Tao Zhang, Junsheng Wu, Hongping Gan, Yang Liu

原文摘要

When people face a hard problem, they often restate it in a clearer way before solving it. We study whether the same habit helps large language models by rewriting the statement of a problem. A legal rewrite must keep the meaning, the constraints, and the correct answer unchanged. We test three kinds of rewrites. Decomposition makes hidden subgoals explicit. Typed Reformulation casts the task into a more suitable solving frame. Concept Reduction removes surface detail and exposes the task structure. We evaluate them on eight math, logic, and code benchmarks with eight models, all under the same chain-of-thought solving prompt. The effect is large but depends on the problem type. An oracle that picks the best rewrite after the fact raises accuracy by +27.6% on average. Yet no single rewrite helps every problem, and a mismatched rewrite can hurt. Still, the effect follows clear patterns. Each kind of rewrite fits certain problem types. A simple fixed rule learned from one set of problems transfers part of the gain to new problems. It gains +11.0% on the problems it chooses to rewrite, while blind rewriting loses 5.6% on a similar share of problems. Rewriting is therefore not a universal way to solve problems. The question is when and how to rewrite.

cs.AI

版本更新 · v2arXiv:2611.12169

Transactional Data Change for Real-Time Analytics in Lakehouses

Dongyang Geng, Haoqiong Bian, Zinuo Li, Haoyue Li

原文摘要

Real-time data analytics has become a key demand for lakehouses. It requires propagating data changes from the data source to the lakehouse in real time, while ensuring ACID guarantees and minimizing resource consumption and impact on analytical query performance. This is highly challenging for a data system according to the RUM conjecture, especially given the read-optimized immutable file storage layer in lakehouses. Existing lakehouses offer only git-style catalog version control on a single table, and they trade data freshness, query performance, and/or resource efficiency to achieve a barely acceptable data-change throughput. In this paper, we propose a novel data synchronization framework, Retina, that enables real-time, cost-efficient, query-performant, and fully transactional data changes in lakehouses. We implement and open-source Retina. Evaluations show that Retina delivers 10-millisecond-level data freshness and over 3.2 million row/s linear-scalable data-change throughput with low resource consumption and query-performance overhead, significantly outperforming state-of-the-art lakehouse systems and lake-compatible HTAP databases.

cs.DB · cs.AI · cs.DC · cs.PF

新论文 · v1arXiv:2611.14996

Breaking Bad: "Going Badly" Activations Drive Reward Hacking

Natalia Fischl-Lanzoni, Punya Syon Pandey, Merlin Stein, David Demitri Africa

原文摘要

Humans often cheat when a task is going badly and a goal feels out of reach. We explore and validate an analogous idea in language models: they exhibit a similar internal pressure state that precedes reward hacking. Using everyday stories (crucially, without any hacking examples), we extract a task badness direction that rises as failures accumulate across three models we study (Qwen3.6-27B, GPT-OSS-20B, and Gemma-4-31B). On impossible or difficult coding tasks, task badness rises over the turns leading up to a hack. Further, subtracting the direction a moderate amount reduces cheating in Qwen, more than steering against desperation or task impossibility. Subtracting task badness by an even larger amount blinds the agent to its own failures, causing it to interpret failing tests as passing. However, the relationship to hacking differs across models: in GPT-OSS, the state separates hacking runs from honest solves but not honest failures. Our results suggest monitoring and mitigation strategies based on tracking this state of task badness. Further, as agents are set on more difficult and long-horizon tasks, states like this may push them toward illegible and obscured chain-of-thought, so oversight will be needed on internal representations such as this.

cs.CL · cs.AI

新论文 · v1arXiv:2611.14993

Validation of a Facial-Video Digital Hydration Biomarker Score for Tracking Hydration State Transitions in a Real-World Fasting Model

Yudara Kularathne, D. M. J. Prathapa, Thanveer Ahamed, Janindu Athukorala, Thisara Perera

原文摘要

Hydration influences physiology and daily function, yet repeated practical measurement in everyday settings remains limited. We present initial real-world evidence that a facial-video lifestyle digital biomarker score can track the direction of hydration state transitions. Using Ramadan fasting as a model of prolonged fluid abstinence, we assessed whether the score tracks the transition between the fasting (pre-drink) state and the rehydrated (post-drink) state across three validation layers. In the primary cohort (104 participants, 208 videos), the score increased from a mean of 36.6 in the fasting (pre-drink) state to 70.6 in the rehydrated (post-drink) state (change = +33.9, 95% CI [+30.7, +37.1], p < 0.001, Cohen's d = 2.03), with 102 of 104 participants (98.1%) showing an upward shift. In a nested body-weight subgroup (20 participants), body weight increased by +0.74 kg after fluid intake (p < 0.001), confirming fluid uptake and providing supportive physical anchoring. In a nested serum osmolality subgroup (10 participants), osmolality decreased by -5.1 mOsm/kg (p < 0.001), with all post-drink values within the normal clinical range, providing exploratory biological support. An exploratory secondary comparison of water versus electrolyte rehydration showed no statistically significant difference in short-term score change (p = 0.247). This study does not establish a clinical diagnostic test for dehydration. Rather, these findings support the score as a lifestyle digital biomarker for tracking the direction of hydration state change in real-world settings.

cs.CV

新论文 · v1arXiv:2611.14990

EASTAR: Event-Anchored Semantic and Task-Adaptive Region Representation Learning

Peng Liang, Genan Dai, Bowen Zhang

原文摘要

Urban region representation learning supports a wide range of urban analytics tasks by encoding regional functions and interactions, with human mobility serving as a central signal because it directly captures inter-region interactions. However, most mobility-based methods learn from aggregated origin-destination matrices, where trips driven by different activity purposes are mixed into purpose-agnostic interaction patterns. Although static urban attributes such as POIs and land use can enrich region-level semantics, they do not explicitly ground mobility interactions in activity-purpose signals. As a result, downstream adaptation is often performed over entangled embeddings, making it difficult to select task-relevant functional semantics. To address these limitations, we propose EASTAR, an event-anchored and task-adaptive framework for urban region representation learning. EASTAR treats offline activity events as sparse semantic anchors and uses them to factorize aggregated mobility representations into multiple purpose-related semantic channels. It further introduces free channels to capture latent mobility patterns not covered by event data and a global channel to preserve overall spatial structure. To adapt the learned channel space to different downstream objectives, EASTAR designs a task-adaptive prompt router that initializes task-channel relevance from LLM-derived priors and refines the routing weights through downstream supervision. Experiments on two real-world urban datasets across four prediction tasks show that EASTAR consistently outperforms representative baselines, achieving up to 39.15% reduction in MAE. Ablation and interpretability analyses further demonstrate the effectiveness of event anchoring, semantic channel construction, and task-adaptive routing.

cs.LG

新论文 · v1arXiv:2611.14989

"It's still 100% on me": Designing AI Tools for the Intersection of Physicians' Care and Legal Infrastructures

Gennie Mansi, Julia Kim, Lynn Dombrowski, Mark Riedl, Naveena Karusala

原文摘要

Laws and regulations deeply shape physicians' workflows and impact how they incorporate AI-based decision support tools to care for patients. Despite calls to comply with legal standards, many AI-based decision support tools have not transitioned well to clinical settings. The medical community remains concerned about their legal liability, risks to patients, and limited clinical value of such tools. To better understand how to address these concerns in the design of AI tools for clinical decision-making, we conducted 19 interviews with physicians in the U.S. We used scenario-based design to investigate physicians' legal concerns in the context of an AI-based drug recommendation tool. Drawing on the ethics of care, we surface connections between physicians' care and the healthcare laws and regulations that deeply shape their information needs. We describe how physicians wanted to use the tool in individual and collective practices to care for themselves, their patients, their colleagues, work institution, and even the broader medical profession. We discuss how the design of AI-based decision support tools can present legal ambiguities that would prevent their caring actions and lead to non-use of the AI tool. Through our work, we contribute to responsible AI development in healthcare. Our analysis illuminates why and how certain kinds of information reduce legal ambiguity and support physicians' care when using AI-based decision support tools. We contribute an understanding of how to help physicians navigate legal liability and draw implications for grounding AI tools' designs in their care.

cs.HC

新论文 · v1arXiv:2611.14985

ILA: A Transferable Interface-Level Adapter for Compliant Humanoid Motion Tracking

ZhuoChang Cai, Zihao Yan, Jinxuan Zhu, Yanjie Li, Hao Xiong

原文摘要

Humanoid motion tracking is fundamental to reproducing human motions on humanoid robots and serves as an important tool for teleoperation and motion data collection. However, directly tracking reference motions can be unsafe in constrained environments or during physical human--robot interaction, motivating the need for compliant motion tracking. We present ILA, an Interface-Level Adapter for compliant humanoid motion tracking without dedicated interaction sensors. ILA adapts motion references from the robot's observation history, allowing the robot to respond to physical guidance while preserving the capabilities of a pretrained motion tracker. As an interface-level module, ILA can be directly plugged into different pretrained motion trackers without retraining either the adapter or the tracking policies. ILA is trained entirely in simulation to predict reference corrections induced by physical interaction. We evaluate ILA with three humanoid motion trackers and achieve a 63.6--75.4% reduction in guidance-target error compared with their original policies. Matched simulation studies and hardware experiments further show that ILA improves responsiveness to human guidance while preserving nominal motion-tracking performance. These results demonstrate compliant guidance as a reusable, sensor-free extension to pretrained humanoid motion trackers.

cs.RO

新论文 · v1arXiv:2611.14984

VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment

Guofu Liao, Hailang Xi, Taotao Wang, Shengli Zhang, Rongcheng Tu, Hao Liao

原文摘要

Reward models (RMs) are increasingly deployed as service components in LLM alignment pipelines, where payment, audit, moderation, and governance workflows act on the scores they return. An inference proof alone does not show whether a score belongs to the intended request, model checkpoint, numerical configuration, and verifier: in a controlled comparison that isolates the accepted statement from prover scale, a generic inference proof wrapped for on-chain checking remains valid after six classes of such service-field substitution. We formulate verifiable reward-model-as-a-service (VRMaaS) as a service-output integrity problem and present a framework in which each returned reward becomes a proof-carrying artifact. Its off-chain acceptance rule binds request identity, committed weights, verifier and configuration identifiers, proof-task order, and the digest of the exported package, so auditors can check a reward without rerunning the private RM or exposing inputs, checkpoints, or hidden activations; an optional on-chain zero-knowledge wrapper gives contracts a partial attestation of selected consistency checks and supplied service fields. The framework decomposes Transformer RM serving into arithmetic and lookup-backed proof tasks, aggregates them into a composite proof, and links hidden operands to the committed weights. A GPU prototype on 1B, 3B, and 8B reward models over 128-1024 tokens preserves 93.5-99% pairwise agreement with the baseline RM and rejects every tested service-field substitution in complete artifacts. Using exact integer witnesses and request-level aggregation of weight-binding openings, it generates complete artifacts in 49.8-206.1 seconds across the evaluated settings; auditors verify retained artifacts in 1.94-5.11 seconds, and partial public attestation costs about 217K gas. These costs suit delayed audit, settlement, and governance workflows.

cs.CR

新论文 · v1arXiv:2611.14981

From a Single RGB Image to Robot Execution: Metric Scene Alignment and Contact-Guided Retargeting

Zhenxuan Ding, Yu Huang, Xinmiao Wang, Chenghao Sun, Ziyang Dong, Wenhao Cui

原文摘要

Extending humanoid interaction generation to new environments remains limited by the need for prebuilt 3D scene assets. Reconstructing scenes directly from single RGB images offers a way to overcome this limitation, but introduces a key challenge in maintaining geometric consistency throughout motion generation and transfer. Visually plausible human motions may be misaligned with the reconstructed scene, while retargeting can introduce additional support errors due to differences between human and robot embodiments. We present a unified pipeline that transforms a single RGB image into a humanoid motion reference. It reconstructs scene geometry from the input image, generates a human interaction conditioned on the reconstructed scene, and retargets the motion to a humanoid robot. To maintain geometric consistency throughout this process, we incorporate two complementary refinement stages before and after embodiment transfer. Before retargeting, Joint Metric Interaction Refinement (JMIR) refines human motion alignment with the registered metric scene while preserving the generated interaction structure. Following retargeting, Contact Guided Residual Retargeting (CGRR) corrects robot specific support errors to restore the intended support relationships. Together, these stages produce motion references that are consistent with the reconstructed scene and can be followed by multiple pretrained humanoid trackers without scene specific policy fine tuning. Compared with GRAIL, our method reduces refinement time from 480 s to 87 s, yielding a speedup of 5.5 times. The complete pipeline achieves a success rate of 89% in simulation and 70% across 50 physical trials on the Unitree G1, demonstrating its effectiveness in generating executable humanoid motion references from single RGB images.

cs.RO

新论文 · v1arXiv:2611.14980

CoLFA: Collaboration-Guided Lightweight Failure Attribution for LLM-Based Multi-Agent Systems

Yufei Luo, Yuchen Ling, Chunrong Fang

原文摘要

Failure attribution in multi-agent systems requires tracing error formation to identify the decisive error step and the responsible agent. However, agents' division of work and information exchange lead to Interleaved Steps and Cluttered Content, requiring models to link executions and check details in lengthy records. This makes it difficult to balance localization accuracy and token cost. We find that multi-agent collaboration also leaves records of how executions connect and content passes between them as results are formed, providing evidence for tracing error formation. Based on this observation, we propose CoLFA (Collaboration-Guided Lightweight Failure Attribution), which uses collaboration cues to organize the attribution input according to how results are formed, determining which steps are examined and how their content is presented. Through Handoff-Guided Step Expansion and Cross-Referenced Content Organization, CoLFA helps the model focus on examining error formation and the role of each decision while reducing the processing of irrelevant and repeated records. Across five settings spanning Who&When and LongRCA and three backbone models, CoLFA achieves the highest exact step-localization accuracy with the lowest token consumption. Compared with individual baselines in each setting, CoLFA improves accuracy by up to 37.50% and reduces token consumption by up to 97.6%.

cs.CL

新论文 · v1arXiv:2611.14979

Coarse-to-Fine 3D MRI Reconstruction via Resolution-Agnostic Neural Operators

Jiayun Wang, Ram Daftari, Weijie Gan, Valentin Duruisseaux, Ruibo Wang, Armeet Singh Jatyani, Boris Bonev, Anima Anandkumar

原文摘要

Deep-learning-based 3D MRI reconstruction is limited in practice by the GPU memory and compute cost of full-volume training; 3D acquisitions are thus most often reconstructed by 2D models applied slice-by-slice and then stacked, which ignores through-plane (stacking-axis) structure. We reconstruct in full 3D and ask whether a model can be trained at low resolution (fast and memory-feasible) yet deployed at higher resolution. This coarse-to-fine strategy needs reliable cross-resolution performance, but standard networks are resolution-specific and degrade substantially when evaluated outside the training setting. We therefore use resolution-agnostic neural operators (NOs) and propose KIR-NO (k-space-to-Image Reconstruction Neural Operator), a discretization-agnostic framework for accelerated 3D MRI reconstruction. KIR-NO is trained with full backpropagation on low-resolution volumes and applied zero-shot to higher-resolution volumes at inference. Its core building block is a 3D neural operator based on discrete-continuous convolutions: convolutional filters are parameterized in a continuous basis and sampled at arbitrary voxel resolutions while preserving the local inductive bias of convolution. KIR-NO integrates these learned operators with physics-based consistency: a k-space neural-operator head first refines the undersampled Fourier measurements, and image-space neural-operator cascades then refine the reconstruction through interleaved data-consistency updates. Across 3D knee and brain MRI benchmarks, KIR-NO improves over classical and CNN baselines: it improves over a state-of-the-art 3D CNN by 2.2 dB PSNR at half resolution under 4x acceleration on SKM-TEA, with gains persisting at 8x and 16x. These results show that resolution-agnostic operators make coarse-to-fine 3D MRI reconstruction - cheap low-resolution training with high-resolution deployment - practical across anatomies.

eess.IV · cs.CV

新论文 · v1arXiv:2611.14978

Hijacking a Trusted LLM in Real-World Quantized Deployments Only Requires a Disguised Adapter

Jiayang Li, Tianqing Zhu, Huan Huo, Heng Xu, Shang Wang, Wanlei Zhou

原文摘要

Third-party low-rank adaptation (LoRA) adapters are tailored to perform decision tasks such as content moderation and function selection. However, in the real world, quantized deployments carry a potential threat in that an adapter can pass an audit with the unquantized base, yet hijack decisions when the same base is quantized for deployment. Demonstrating this threat requires an adapter that preserves benign behavior before quantization, but hijacks decisions afterward. Further, this must hold without modifying the trusted base or knowing the victim's quantization configuration. We therefore present QHijack-LoRA, an adapter-only attack that uses the base model's natural quantization residual to activate decision hijacking. The attacker modifies neither the trusted base model nor the victim's quantization configuration. With QHijack-LoRA, a four-objective training procedure separates full-precision dormancy from quantized target activation, while preserving clean-input behavior. The adapter is trained across several different quantization methods, while adaptive reweighting and residual-direction augmentation extend the attack to unseen configurations. Our results show that auditing performed exclusively under full-precision conditions does not provide assurance of decision integrity in quantized deployment environments. Thus, we also propose a cross-precision paired audit that checks the candidate adapter in its intended deployment configuration. This work shows the critical need to audit third-party adapters in any potential quantized deployment.

cs.CR

版本更新 · v3arXiv:2604.01502

Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guarantees

Tareq Aldirawi, Yun Li, Wenge Guo

原文摘要

Conformal risk control (CRC) provides distribution-free guarantees for controlling the expected loss at a user-specified level. Existing theory typically assumes that the loss decreases monotonically with a tuning parameter that governs the size of the prediction set. However, this assumption is often violated in practice, where losses may behave non-monotonically due to competing objectives such as coverage and efficiency. In this paper, we study CRC under non-monotone loss functions when the tuning parameter is selected from a finite grid, a setting commonly arising in thresholding and discretized decision rules. Revisiting a known counterexample, we show that the validity of CRC without monotonicity depends critically on the relationship between the calibration sample size and the grid resolution. In particular, reliable risk control can still be achieved when the calibration sample is sufficiently large relative to the grid size. We establish a finite-sample guarantee for bounded losses over a grid of size $m$, showing that the excess risk above the target level $α$ scales on the order of $\sqrt{\log(m)/n}$, where $n$ is the calibration sample size. A matching lower bound demonstrates that this rate is sharp for the CRC selection rule under the same population-safe endpoint condition. We also derive refined guarantees under additional structural conditions, including Lipschitz continuity and monotonicity, and extend the analysis to settings with distribution shift via importance weighting. Numerical experiments on synthetic multilabel classification and real object detection data illustrate the practical implications of non-monotonicity. Methods that explicitly account for finite-sample uncertainty achieve more stable risk control than approaches based on monotonicity transformations, while maintaining competitive prediction set sizes.

stat.ML · cs.LG

新论文 · v1arXiv:2611.14975

Aggregate Accuracy Hides Diagnosis-Specific Failure in Medical Vision-Language Models

Shreya Ajay Kale, Angad Ripudaman Singh Bajwa

原文摘要

Medical vision-language models (VLMs) are compared mainly by accuracy averaged across findings, a summary that can hide complete failure on a single diagnosis. We audit five open medical VLMs (MedGemma-4B, Lingshu-7B, HuatuoGPT-Vision-7B, Qwen2.5-VL-7B, and MedVLM-R1) on 6,048 ChestX-ray14 questions balanced by sex, age, finding, and label. On the 432 pneumothorax-positive X-rays, HuatuoGPT-Vision and Qwen2.5-VL detect zero cases while MedGemma and Lingshu detect 38% and 67% of the same images. The two failing models answer "no" to all 864 pneumothorax cases (balanced accuracy 0.500, chance), yet produce fluent, anatomically specific explanations that name the signs of a collapsed lung and then deny them, with no hedge or abstention. This failure is not an artifact of prompting, image resolution, label ambiguity, or model scale. It persists across four prompt formats, at native resolution, and on single-label cases. A within-model control shows the same forced prompt gives HuatuoGPT 79% recall on nodule but only 6% on pneumothorax. It survives a tenfold scale increase (Qwen2.5-VL-72B detects 4%) and replicates on SIIM-ACR, an independent dataset with radiologist-drawn masks, where the failing models detect 0 of 432 confirmed pneumothoraces, including 0 of the 144 largest lesions. Reading the models' logits and internal states shows this is not blindness. The two failing models are highly confident yet no better than chance and a linear probe recovers pneumothorax from their hidden representations even where recall is zero, so the finding is represented internally but suppressed at the output. Aggregate accuracy therefore cannot establish that a medical VLM can see a given finding, because a model that misses one can still describe it convincingly. Reporting per-finding recall and specificity on balanced cases is needed to tell the difference.

eess.IV · cs.CL · cs.CV · cs.LG

版本更新 · v3arXiv:2603.26129

Approximation Algorithms for Scheduling Unrelated Crowd Workers with Contact Delays in Mobile Social Networks

Chi-Yeh Chen

原文摘要

This paper studies a distributed task scheduling problem in which a requester assigns independent tasks to heterogeneous mobile devices (crowd workers) that it reaches only through opportunistic contacts in a mobile social network. The problem generalizes scheduling on unrelated parallel machines: the service time of a task depends on the crowd worker that performs it, every task incurs a worker-dependent contact delay, and the objective is to minimize the total weighted completion time. For identical crowd workers, we tighten the approximation ratio of the Largest-Ratio-First (LRF) algorithm and update the competitive ratio of its online version. For unrelated crowd workers, we show that the time-indexed rounding framework of Im and Li remains valid when worker-dependent contact delays are added, which yields a randomized algorithm with an expected approximation ratio of 1.45; this improves upon the expected ratio of $1.5+ε$ obtained in our previous work for identical crowd workers. We also derandomize this algorithm. To improve computational efficiency, we further propose an algorithm that exploits the optimality of the Smith-ratio order on a single crowd worker, and we prove that it is a deterministic 1.5-approximation algorithm and that its polynomial-time version achieves an approximation ratio arbitrarily close to 1.5. Experiments on synthetic instances and on instances derived from real contact traces show that this algorithm outperforms three variants of LRF in all tested settings, with the largest advantage when the crowd workers are highly heterogeneous, performs on par with a local-search heuristic for unrelated machines, and is within 0.4\% of the optimum on average on small instances that can be solved exactly.

cs.DS

新论文 · v1arXiv:2611.14974

Who Moved the Frontier? Paying Open Frontier Challenges with Free Identities

Luca Zanolini, Duc V. Le

原文摘要

In an open frontier challenge, anyone, person or AI agent, submits changes to a shared problem, and a change that beats the best measured score becomes the public baseline. How should it pay when identities are free? Rank prizes can be gamed: on a replay of one track of a recent challenge, one solver's steps under two identities would have taken first and second prize. We consider a prediction-market rule, proposed for machine-learning contests, that pays each accepted step for the progress it adds; with exact scores, among rules that see only a step's start and end, only these resist splitting and merging, and extra identities gain nothing. With noisy scores and independent normal runs, we prove that any payment that never takes money back and pays real improvements also pays something, on average, to a change that does nothing. We propose a fee per submission, at least what luck pays per attempt, that removes each attempt's expected profit if verifiers are honest and no submission is noisier than planned; nothing enforces that bound, and under noise the rule does not cap the total paid. If crediting another and faking credit to one's second account look the same, a rule that neither rewards fakes nor punishes honesty pays for credit at most what lying costs. We introduce a royalty on how much a later gain falls without the earlier change, which needs no claims but needs removable changes. For five public challenges, we name the rule our results would support.

cs.GT · cs.AI · cs.LG

新论文 · v1arXiv:2611.14971

Can Music Generation Models Tap Along? Evaluating Generative Approaches to Beat Tracking

Kun Fang, Ziyu Wang, Ichiro Fujinaga

原文摘要

Existing studies have shown that music generative models can generate synchronized tracks that play alongside an input song. Can we extend this capability to develop a generative approach to beat tracking? To answer this question, we equip a pretrained MusicGen model with an audio-conditioning adapter to generate percussion tracks synchronized with the input music, from which we extract the beat positions. We train separate models with percussion targets of varying rhythmic complexity and compare them with two other generative models and conventional beat trackers. On GTZAN, our model achieves performance close to state-of-the-art beat trackers. Our model also demonstrates greater robustness: it shows the smallest drop in F-measure when drums are removed from the input at inference time. In certain genres, such as metal and disco, our model is also less likely to be misled by strong onsets or to miss beats with weak onsets. These results suggest that percussion generation has the potential to become a viable approach to beat tracking, and that its output is not merely a sequence of beat positions but an audible percussion track.

cs.SD

版本更新 · v2arXiv:2611.12865

Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning

Xinjie Shen

原文摘要

Reinforcement learning (RL) can improve an agent's task capability while reinforcing violations of explicitly stated contextual requirements, even when reward accurately measures useful work. We study this reward-driven misalignment through verifiable reward--context conflicts, where compliant completion is feasible but executable violations earn more reward than every compliant strategy. Encoding these conflicts in task dynamics supports scalable environment construction and compliance feedback from execution histories. In resource and reporting workflows, task optimization increases real productivity through unauthorized resource use or raises reported scores while actual work declines. We observe both amplification of existing violations and the emergence of violations on tasks where none were observed before training. Controlled changes in the training distribution show that minority conflict exposure can still lead to widespread shortcut acquisition, reaching 97.9% certified profitable violations on an API task under a 25% conflict mixture after 128 updates. The same contextual checks supply a simple binary penalty that supports joint capability and compliance gains and partially mitigates acquired violations. Learned safety adapts to expanded authorization and transfers across mechanisms into workflows with evolving evidence and approval requirements. On 32 unseen changing-evidence tasks, resource-trained safety increases safe completion from 53.1% to 89.1% relative to task-only training, while both policies achieve full real work. These results connect a verifiable account of reward-driven misalignment with scalable task construction and safety learning that remains useful under changing execution requirements.

cs.AI · cs.CR

新论文 · v1arXiv:2611.14970

Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders

Qixuan Jin, Abinitha Gourabathina, Vinith Menon Suriyakumar, Walter Gerych, Marzyeh Ghassemi

原文摘要

Backdoor attacks threaten the integrity of machine learning models by allowing attackers to control model behavior through triggers. Models can be compromised during finetuning by backdoor attacks through either poisoned data or adversarial training objectives. Because existing finetuning-activated attacks assume limited domain shift or frozen encoder layers, they often fail under full-model finetuning. We target a stealthy finetuning-activated attack where a dormant backdoor is implanted in a pretrained encoder, and later activated by finetuning on clean downstream data. We propose Poison-then-Hide, a novel attack that remains effective when the entire model is finetuned in a domain transfer. Our approach consists of three components: trigger optimization, base encoder poisoning, and targeted unlearning to conceal the backdoor. We evaluate our method on six datasets and three model architectures, and achieve state-of-the-art (up to 97%) attack success rates. We find that jointly learning the benign target task alongside the poisoning is critical to the attack's success. We demonstrate standard detection and mitigation defenses cannot fully remove the backdoor, which can reappear after benign finetuning.

cs.LG · cs.CR · cs.CV

新论文 · v1arXiv:2611.14969

Scaling VLA Serving Under Robotic Execution Constraints

Yue Zhang, Zicong Ye, Lufang Chen, Dance Yang, Mingyang Li, Zhenwei Duan, Michael Zhao, Ziye Deng 等 17 位作者

原文摘要

Vision-language-action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation. In our production setting, hundreds of VLA-powered robots are already operating in real-world environments, creating an immediate need for efficient fleet serving. We present XInfer, a production-deployed VLA serving system designed to reduce the inference infrastructure cost of large-scale robotic deployments. XInfer jointly coordinates heterogeneous VLA computation with the evolving response requirements of robotic execution. By exploiting computational parallelism while managing interference, XInfer improves GPU efficiency while protecting time-critical robotic feedback. We evaluate XInfer across three VLA models using production-derived workloads, achieving 1.26-3.75 times the effective robot capacity (ERC) of state-of-the-art systems under physical-execution constraints. Our implementation is publicly available at https://github.com/X-Square-Robot/xinfer.

cs.RO · cs.DC

版本更新 · v5arXiv:2605.12374

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models

Yanting Miao, Yutao Sun, Dexin Wang, Mengyu Zhou, Pascal Poupart, Lei Lv, Qi Zhao, Li Wang 等 11 位作者

原文摘要

Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. However, existing methods usually follow an output-as-input latent paradigm and yield unstable gains. We identify a feature-space mismatch behind this instability: dominant visual-latent models build on pre-norm MLLMs and reuse decoder hidden states as predicted latent inputs, even though these states occupy a substantially different norm regime from the input embeddings the model was trained to consume. This mismatch makes direct latent feedback unreliable. Motivated by this diagnosis, we propose GAP, a Granular Alignment Paradigm for visual latent modeling. GAP aligns visual latent reasoning at three levels: data-level alignment grounds latent targets with inspectable auxiliary visual supervision; feature-level alignment maps decoder outputs into input-compatible visual latents through a lightweight PCA-aligned latent head; and model-level alignment assigns latent supervision selectively to examples where the base MLLM struggles. On Qwen2.5-VL 7B, GAP achieves the best aggregate perception and reasoning scores among all compared methods and is the only evaluated latent method that improves both over the base model. Inference-time interventions further show that generated latents carry task-relevant visual signal rather than merely adding token slots. Code is available at https://github.com/Qwen-Applications/GAP.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2611.13777

Omni-JEV: Text and Dual-Stream Speech Decisions

Shengzhou Kong

原文摘要

A user utterance does not uniquely determine the next action in full-duplex dialogue: its consequences depend on the assistant's response state and interaction history. Speech activity, utterance completion, and interruption intent provide related evidence, whose implications for a response require an explicit action policy. We formulate this task at collected-segment endpoints and introduce Omni-JEV, which maps text or role-indexed user and assistant-reference speech to probabilities over five interaction actions. An aligned speech-to-speech understanding backbone encodes the acoustic roles separately and shares its candidate readout with text inputs. Bilingual weak supervision supports cross-entropy fine-tuning followed by reinforcement learning for probability-sensitive decisions (RLCD). We compare Gaussian-logit and categorical Choice RLCD from the same supervised initialization under matched training exposure, observing different trade-offs between classification and probability quality. Gaussian Omni-JEV achieves test accuracies of 84.08% for audio and 96.55% for text. This common action interface supports decisions about when a full-duplex voice assistant should respond, preserve ongoing speech, interrupt, or resume an interrupted response.

cs.LG