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

+1022新增论文
+813其中 AI 相关
+85已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 13:07各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 14:21 — 2026-11-17 14:21(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:2026-11-17 04:58最近发现新增版本:2026-11-17 13:07库内论文最新更新时间:2026-11-16 17:16

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。

24,849 已收录论文20,754 AI 相关7,213 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 84 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.20765

STA: A Split Temporal Adversary Method for Evaluating Robustness of Multimodal RL-based Driving Policies

Shenghao Xiong, Xiaolin Chang

原文摘要

Multimodal reinforcement learning (MRL) offers a promising paradigm for autonomous driving by jointly leveraging complementary sensor observations to learn effective decision-making policies. However, its effectiveness critically depends on temporal alignment across modalities, making temporal inconsistency a fundamental vulnerability. Even subtle misalignment or latency can corrupt fused representations and ultimately lead to decision failures. Existing studies have explored adversarial attacks to induce cross-modal temporal inconsistencies, thereby enabling systematic evaluation of the temporal robustness of MRL policies. However, existing methods remain limited in generality, realism, and adaptivity. To address these limitations, we propose the Split Temporal Adversary (STA), which formulates multimodal temporal attacks as a unified decision process that jointly optimizes attack timing and modality selection under realistic policy-aware and budget-constrained settings. STA includes two mechanisms: a) a unified multimodal temporal perturbation mechanism that delays observations via historical states, removing the need for modality-specific noise; b) a split multimodal adversarial decision mechanism that jointly optimizes attack timing and modality selection through adaptive optimization while leveraging the victim policy's clean actions to identify sensitive decision patterns. We provide a theoretical analysis of the induced distribution shift and a modality selection principle. Experiments in the CARLA simulator show that STA more than doubles the collision rate of the strongest baseline against PPO while using 17.8\% fewer attack attempts, and that it generalizes to a VLM-based driving policy. These results reveal temporal consistency as a critical vulnerability, highlighting temporal robustness as essential for safe autonomous driving.

cs.CR · cs.LG · cs.RO

新论文 · v1arXiv:2611.20759

Instant Weight-Space Consolidation for Long-Term Memory in LLMs

Manan Suri, Dinesh Manocha

原文摘要

Agentic memory systems give LLMs persistent memory by extracting experience into text and retrieving it at query time, but the model itself does not evolve: however many interactions it has had, it starts each query the same. Extraction errors compound, implicit cross-session patterns that no single fragment states cannot be surfaced, and the construction cost grows with every conversation. Fine-tuning on past interactions does change the weights, but requires backpropagation at serving time and degrades on long histories. We introduce CLAM (Carried Latent Adapter Memory), which combines the strengths of both: a recurrent hypernetwork performs parametric consolidation, compiling a stream of session activations into a low-rank adapter in a single forward pass with no gradient steps and no language-model generation calls, while a complementary episodic buffer supplies verbatim detail at inference. A gated latent state carries knowledge across sessions in fixed size, so the parametric memory accumulates without growing. On LoCoMo and LongMemEval-S across three open models (2-7B parameters), CLAM leads all agentic baselines by 1-45 points and all gradient-based parametric methods by 10-45 points, while requiring zero generative LLM calls, zero gradient steps, and 3-151x less wall-clock time than extraction systems to build its memory. The two channels are complementary: the consolidated adapter adds 12-15 accuracy points when the episodic buffer misses the gold evidence, and still adds 4-5 points even with an oracle buffer.

cs.CL

新论文 · v1arXiv:2611.20758

UniGraph: A Unified Graph-based Index for Dynamic Hybrid Dense-Sparse Vector Retrieval

Keyu Chen, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Jingkuan Song, Heng Tao Shen

原文摘要

Hybrid dense-sparse vector retrieval combines semantic signals from dense representations with lexical signals from sparse representations, typically ranking items by a query-dependent weighted sum of dense and sparse vector distances. Existing systems commonly search separate dense and sparse vector indexes and rerank the union of their candidates, incurring two retrieval passes and potentially discarding items that rank highly only after the semantic and lexical signals are combined. Constructing a graph-based index directly under a hybrid distance can mitigate this premature candidate loss. However, because varying the hybrid weight alters the underlying neighborhood relationships, a single static graph built at a fixed weight cannot accommodate dynamic query-specific weights. Therefore, we propose a Unified Hybrid Graph (UniGraph), which merges neighbor sets computed at multiple hybrid weights into a single bounded-degree graph index, enabling hybrid vector retrieval with different query-specific weights without index reconstruction. We further develop an adaptive weight-guided search framework that chooses between sparse- and dense-guided entry points according to the query weight, together with a dense-first hybrid distance pruning strategy that avoids unnecessary exact sparse distance computations. Extensive experiments show that UniGraph provides a favorable Recall-QPS trade-off across different query weights. In the mixed-weight setting, UniGraph delivers 27.6%~52.3% higher QPS than the fastest baseline on each dataset at Recall@100 greater than or equal to 0.95. UniGraph has been deployed at scale in Ant Group's production environment, where hybrid retrieval with query-dependent weights is in strong demand.

cs.IR · cs.DB

新论文 · v1arXiv:2611.20755

GPRM: Global Perspective Process Reward Model

Zifan Zhang, Zhengbo Jiao, Shaobo Wang, Jing Zhou, Guoyi Li, Jiayi Chen, Wei Wang, Bing Zhao 等 13 位作者

原文摘要

Process Reward Models (PRMs) are widely used for step-level evaluation of multi-step reasoning in large language models, but existing methods are often limited by weak historical dependency modeling and insufficient global awareness. They typically fail to leverage prior step evaluations for coherent judgment and lack visibility into subsequent reasoning, leading to suboptimal assessment of intermediate steps. To address this issue, we propose the Global Perspective Process Reward Model (GPRM), which jointly models the problem, previous reasoning steps and their evaluations, the current step, and future steps to enable history-aware and globally informed process evaluation. We further introduce a structured evaluation framework along four dimensions---look back, look ahead, self-check, and goal alignment---to assess prior consistency, future plausibility, step validity, and task alignment. Based on this framework, we construct datasets for supervised fine-tuning (SFT) and reinforcement learning (GRPO). Experiments show that, despite using less training data and smaller model sizes, GPRM outperforms strong baseline models by 7.8 and 5.4 points on PRMBench and ProcessBench, respectively. GPRM also generalizes well across tasks, surpassing the GPT-4.1 baseline on Agent Error Bench, improving strong baselines by around 4 points under test-time scaling (TTS), and achieving competitive performance on PPE.

cs.CL

新论文 · v1arXiv:2611.20752

Who Benefits from Telemonitoring? Uplift Modelling of a Nationwide Home Blood Pressure Monitoring Programme

Connie Kou

原文摘要

Home blood pressure (BP) telemonitoring programmes are being deployed at national scale, yet enrolment resources are finite and the benefit of telemonitoring is unlikely to be uniform across patients. We study the Primary Technology-Enhanced Care for Hypertension (PTEC-HT) programme, a nationwide telemonitoring programme for hypertensive patients in Singapore. Using retrospective data on 16,694 patients registered between August 2020 and May 2024, we first estimate the average treatment effect of the programme on 6-month BP control against a propensity-score-matched non-participant cohort, finding an absolute improvement of 5 percentage points in the rate of BP control (74% vs. 69%, $p = 3\times10^{-12}$), rising to 12 percentage points (63% vs. 50%, $p = 1\times10^{-15}$) among patients with uncontrolled BP at baseline. We then move beyond the average effect and apply uplift modelling to estimate individual treatment effects. Across five uplift learners evaluated with 5-fold cross-validation and Qini curves, an uplift random forest performed best on the full cohort and an S-learner on the uncontrolled-baseline subcohort, although performance bands overlapped across learners. On held-out patients, realised uplift was largest in the top predicted-uplift groups and declined across the ranking. These patients had higher baseline BP grade, more recent hypertension diagnosis and lower medication and diagnosis burden, a profile we offer as hypothesis-generating for targeted enrolment. A handcrafted rule built from these features was competitive with the learned models, outperforming all of them on the uncontrolled-baseline cohort, suggesting that uplift models are useful for discovering heterogeneity that can be distilled into simple enrolment criteria for directing limited care team capacity.

cs.LG

新论文 · v1arXiv:2611.20745

A Seismic Foundation Model for Dense Feature Extraction

Zhixiang Guo, Xinming Wu, Yimin Dou, Hui Gao, Siyao Zhao, He Huang, Wei Liu

原文摘要

Deep-learning-based seismic interpretation is constrained by scarce high-quality annotations, and most existing models are trained separately for individual tasks. We present SeisDFE, a 7B-parameter seismic foundation model for dense feature extraction, pretrained on 5.34 million 2D images derived from more than 500 seismic volumes. A three-stage pretraining strategy, combining discriminative self-supervised learning, Gram feature anchoring, and multi-resolution adaptation, improves feature discriminability while preserving spatial coherence. With its encoder frozen, SeisDFE supports seismic facies classification, salt detection, fault detection, and relative geologic time estimation. It outperforms existing seismic foundation models on all four tasks and a natural-image-pretrained model on all but fault detection, with the largest gains under scarce supervision: using only two annotated sections of the F3 dataset, it improves whole-volume mIoU by 12-19 percentage points over the baselines. The learned features remain effective with task-specific decoders and extend to synthetic-to-field transfer and sparse 3D geobody interpretation. These results show that large-scale seismic pretraining organizes geological information into dense representations that are directly reusable across interpretation tasks.

cs.CV

新论文 · v1arXiv:2611.20741

Robotic Reward Models in the Foundation-Model Era

Guoqiang Liang, Yiqi Lin, Shangchen Zhou, Wenzheng Zeng, Yanzhe Chen, Zechen Bai, Mike Zheng Shou

原文摘要

Robotic reward models (RRMs) use foundation models to replace per-task reward engineering with reusable, task-conditioned evaluation. Yet under one name, their outputs answer different questions, from whether a task succeeded to which execution is better. This survey organizes 114 methods into five semantic families by the question their native outputs answer: Outcome, Absolute Progress, Relative, Temporal Value, and Hybrid. Within this taxonomy, we review how model design determines what an evaluator can judge, how raw experience becomes supervision, and how existing evaluation practice tests the result. The review exposes a gap: agreement with demonstration order and downstream policy gains do not show whether a reward tracks task fulfillment. We therefore introduce RRM-Bench-1K, 1,117 real-robot videos of closed-loop executions with task-state and camera-evidence labels, and four contrast suites that separate the credited condition from its usual cues. A unified study of 27 evaluators shows that the strongest final scores rank whole executions well enough for selection and filtering. Dense credit, however, follows the progression of an execution more closely than its task state, and no evaluator signals when the decisive view is missing. How much fidelity a reward model needs therefore depends on the decision it drives. We outline directions from real-failure supervision to metrics that separate task state from chronology, and open-source RRM-Hub, a toolbox in which 14 existing RRMs can be readily applied and new evaluators tested on the same capabilities.

cs.RO · cs.CV

版本更新 · v2arXiv:2611.17442

Racing the Clock: Teaching VLNs Budget-Conditioned Object Search

Maitree Meher, Siming He, S. Shankar Sastry, Jitendra Malik, Claire Tomlin, Jonas Frey

原文摘要

How do action budgets shape vision-language navigation (VLN) exploration, and what expert supervision best teaches budget-aware search? We study budget-conditioned object search: finding as many distinct instances of a requested category as possible within a budget, with discovery defined geometrically by camera field of view and proximity. Distinct discoveries provide a denser evaluation signal than single-target success. We cast expert design as a choice of scene abstraction: a single budget-indexed Bellman recursion, applied to different abstractions of the full environment, yields experts that differ in what they know. An object-level Bellman expert is given every target location and reduces search to budgeted routing. A room-level Bellman expert retains observed room connectivity, doorway evidence, and cross-scene semantic priors but withholds the contents of unexplored rooms, so it must search for targets that its student also cannot see. We distill both experts into Uni-NaVid under matched training conditions and also evaluate greedy-frontier supervision on held-out HM3D scenes. Changing only the stated budget changes learned trajectories. Despite higher object-level expert return, room-level supervision achieves the highest mean collection among evaluated VLNs at every tested budget. At 2000 steps, it finds 72.7% of reachable targets, versus 68.5% under greedy-frontier supervision, 65.5% under object-level supervision, and 44.8% for the pretrained VLN. These results show that expert-return rankings need not predict supervision quality for VLN exploration, and motivate choosing an expert's abstraction with the student's information in mind rather than by expert return alone.

cs.RO · cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.20737

CLIFT: Contrastive LiDAR Instance Features for 3D Pedestrian Tracking

German Devchich, Timur Akhtyamov, Denis Fatykhoph, Gonzalo Ferrer

原文摘要

A social robot has to keep track of the people around it over time to plan its motion, a task handled by 3D multi-object tracking. For the LiDAR modality, trackers usually sit on top of a detector and link its detections across frames with a separate motion model or re-identification network. We instead show how a 3D LiDAR detector itself can be turned into a tracker by adding an instance-level contrastive objective on its intermediate voxel features. Each embedding is read from the voxels inside a detected box, and boxes are matched across frames by cosine similarity and the Hungarian algorithm, without a motion model. The detector backbone is fine-tuned together with this objective, which learns identity-aware features while leaving detection accuracy essen- tially intact. Because the method uses only the voxel features that Li- DAR detectors already produce, it is backbone-agnostic. On the JRDB 3D tracking leaderboard our LiDAR-only tracker ranks first on HOTA (38.58) and IDF1 (37.99), 13.04 and 9.30 points above the next pub- lished method, and second on MOTA and OSPA. Code is available at https://hermak56.github.io/CLIFT/.

cs.CV

新论文 · v1arXiv:2611.20736

GainCtrl: Predicting Remaining Gains for Efficient LLM Agent Execution

Kangwen Zhao, Jianfeng Cai, Ruopei Sun, Mingxiao Feng, Peng Zhang, Wengang Zhou, Houqiang Li

原文摘要

Large language models (LLMs) are widely used to power agents that interact with tools and environments to solve complex tasks. Repeated attempts improve the quality of tool-using agents, but continued execution incurs additional costs even when it is unlikely to improve the best result ultimately returned. This raises the question of when to stop an attempt to reduce execution cost while preserving task-level Best-of-N quality. To address this question, we introduce GainCtrl, a gain-based execution controller for LLMs. In GainCtrl, a lightweight CPU predictor uses interaction histories to estimate expected positive gains over retained scores, which are then used to guide stopping decisions with calibrated thresholds to limit the loss in mean Best-of-N task quality. We evaluate the controller through trajectory replay across three environments and three LLM actors. Comparisons of interpolated quality-cost Pareto frontiers show that GainCtrl generally uses fewer tokens than baselines at matched target quality. Fixed policies also achieve quality close to that of full execution while substantially reducing token consumption. The predictor runs at millisecond latency on a single CPU thread, supporting repeated monitoring without access to LLM internals.

cs.AI

新论文 · v1arXiv:2611.20734

Can LLMs Give Good Product Advice? A Framework for Diagnosing Failures

Assaf Hallak, Yftah Ziser, Gal Chechik

原文摘要

Evaluating product advice from a language model requires assessing whether the recommendation meets the user's needs and identifying where the model falls short when it does not. However, matching a product mentioned in an online reply cannot answer either question on its own: several products may be suitable, and the recorded answer may itself be poor advice. When shown a community-listed alternative alongside their own sampled car recommendation, six models prefer the alternative in 1.9 to 6.5 percent of eligible disagreements, consistently across both source-blind presentation orders. We propose a diagnostic framework that separates the user's stated needs, the model's added assumptions, candidate generation, filtering, and final choice, with 19 possible failure modes and the evidence needed to assess them. We apply this framework to product-advice data and to a separate product-selection task with externally assigned relevance labels. The experiments distinguish naming a community-listed product from selecting it and show how answer extraction and candidate-list construction affect the outcome.

cs.CL

新论文 · v1arXiv:2611.20733

MemEmo: Evaluating Emotion in Memory Systems

Peng Liu, Zhen Tao, Jihao Zhao, Ding Chen, Yansong Zhang, Cuiping Li, Zhiyu Li, Hong Chen

原文摘要

Memory systems address the challenge of context loss in Large Language Models during prolonged interactions. However, as an essential tool for warm companionship and personalized services, the effectiveness of memory systems in processing affective information remains underexamined. To bridge this gap, we propose an emotion-enhanced memory evaluation benchmark to assess the performance of mainstream and state-of-the-art memory systems in integrating and harnessing emotional information. First, we design a benchmark called \textbf{MemEmo} to assess the affective reasoning and tracking capabilities of memory systems across four dimensions: emotional information extraction, emotional memory updating, emotional memory question-answering, and emotional conflict detection. Second, we construct the \textbf{H}uman-\textbf{L}ike \textbf{M}emory \textbf{E}motion (\textbf{HLME}) dataset to provide an empirical foundation for scrutinizing memory systems. Finally, We evaluate five representative memory systems on the HLME dataset, reporting 11 performance metrics across four dimensions. Experimental results reveal that aggregating scores for all tested memory systems is up to 45\%, far below 100\% scale, exposing a profound disparity between memory system and affective intelligence.

cs.CL · cs.AI

新论文 · v1arXiv:2611.20732

Routing Beyond Task Categories: A Cost-Aware LAB-Bench Study

Ahmed Tariq, Leo Guinan

原文摘要

We tested whether features of biology questions or of a model's first answer can improve accuracy within an inference budget. In a LAB-Bench pilot, we compared a category router with one that adds six structural features. Neither reached the primary 80% accuracy target on development. At the 50% and 60% secondary targets, both chose Haiku for all 120 held-out questions and scored 71/120. We then froze a new comparison before collecting responses on 144 additional questions. Semantic routing scored 86/144. A policy that could defer after reading Haiku's answer scored 87/144. Both stayed within the inference budget of USD 0.678 per 1,000 queries. Against a 95% Haiku and 5% GPT mixture, the accuracy gains were 0.66 percentage points for semantic routing and 1.35 points for deferral. The paired 95% intervals were [-0.28,2.25] and [-0.14,3.47] points. A simple rule that escalated Haiku nonanswers scored 92/144 at USD 0.710 per 1,000 queries, above the budget. A retrospective nonanswer rule with a calibration-selected escalation probability gave an expected 85.63/144. At the learned deferral policy's observed inference cost, post hoc interpolation gave an expected 86.14/144. In a later development check, Astra and Gemini each scored 30/40. The best tested policy in each router family matched that score. The pair covered 33/40 in hindsight. The routers missed the 32/40 criterion, so the proposed 120-question evaluation did not start.

cs.AI

新论文 · v1arXiv:2611.20730

Selective Sensor Acquisition for Multimodal Place Recognition

Margaux Edwards, Tobias Fischer, Michael Milford

原文摘要

Multimodal Place Recognition (PR) can improve robustness, but most systems rigidly read and process every sensor for every query, even when the primary sensor is sufficient, with implications for energy consumption, second sensor update rate, and domain-specific considerations such as passive stealth. We introduce selective, controllable sensor acquisition, where a user specifies a desired second sensor usage rate and the system acquires the additional sensor only when the primary sensor's estimated performance is sufficiently poor. An online threshold adjustment achieves the requested usage rate by adapting to recent primary sensor performance, directing additional sensing towards queries where fusion is most likely to help without calibration specific to sensor modality, PR method, or environment. The approach requires only a PR method that produces a match score and applies to both single-frame and sequence-based PR. Our system, across multiple datasets, PR descriptors, and sensor combinations, recovers 55% of the available PR performance gain while using the second sensor on only 25% of queries, and 81% while using it on 50%. We further analyse alternative acquisition decision mechanisms and usage-rate control methods, and examine performance when the second sensor is stronger than, comparable to, or weaker than the primary sensor.

cs.RO · cs.CV

新论文 · v1arXiv:2611.20728

ANCHOR: Cluster-Grounded 5W1H Extraction via Large-Small Model Collaboration

Hongyu Jiang, Chenang Cai, Lei Gao, Zhao Kang, Ling Tian, Jinchuan Zhang

原文摘要

Deep semantic understanding of events requires recognizing related events and distinguishing why an event occurs from how it is carried out. 5W1H extraction provides a structured foundation for such understanding by organizing event information around six fundamental questions. However, single-event slot filling provides limited support for these distinctions. We propose ANCHOR, a cluster-grounded framework that combines a large language model (LLM) with a small language model equipped with discriminative heads for accurate 5W1H extraction. The LLM proposes candidate events and generates their initial 4W records, which guide the selection of an event cluster and the subsequent anchoring of its main event. A shared document encoder provides evidence for joint 4W refinement, and two separate sets of boundary and role-scoring heads then extract why and how under event-specific constraints, respectively. Document representations are reused across events and stages, and unsupported roles can remain empty. Following the same principles, an agent-and-skill annotation workflow constructs a benchmark of 26,110 documents from ten source corpora covering three languages and seven domains. We select nine of the resulting datasets to evaluate ANCHOR against strong baselines using four open-weight LLMs. ANCHOR achieves competitive performance. The datasets and code are available at https://github.com/revolution6575/ANCHOR-5W1H.

cs.CL

新论文 · v1arXiv:2611.20726

PEETS: Preference-aware Embeddings with Explicit Tree Structure for Auxiliary Product Bundling

Maolei Huang, Jing Tian, Dexuan Duan, Yan Chen, Huawei Cao, Shuhan Song

原文摘要

Auxiliary products such as flight protection and flexible-change services are recommended alongside primary travel purchases. This setting creates a granularity ambiguity: SKUs within one product type share semantics but differ in price and coverage, while rejecting one offer does not imply disinterest in the entire type. We present \textbf{PEETS} (\textbf{P}reference-aware \textbf{E}mbeddings with \textbf{E}xplicit \textbf{T}ree \textbf{S}tructure), a training-time framework for auxiliary product bundling. PEETS regularizes an existing click--conversion predictor through two conditional comparisons. Hierarchical Contrastive Loss uses the pair's common ancestor as a reference; Negative Contrastive Loss conditions structural sampling and comparison shifts on logged rejection events. Both act on shared SKU representations during training. This separates catalog relatedness from individual preference supervision and leaves the predictive serving path intact. PEETS achieves 78.20\% AUC, exceeding TWIN V2 by 0.90 percentage points and the matched base model by 1.15 points. In a 14-day online evaluation, gross auxiliary GMV per exposed user-day improves by 8.20\% over Policies, 3.06\% over Base, and 0.84\% over TWIN V2, with all three user-bootstrap 95\% intervals above zero. Bundling rate is 0.51 points below Policies. The cancellation interval's upper limit exceeds the prespecified margin. PEETS adds no auxiliary-loss computation to serving and records 42.1~ms p95 latency, compared with 42.0~ms for Base.

cs.AI

版本更新 · v2arXiv:2611.12412

Unprompted coordination through shared memory in LLM agents: a locked two-implementation replication and extension

Pekka Abrahamsson, Muhammad Waseem, Esa Karjalainen, Petrus Jussila, Henri Hansen, Jussi Rasku, Bilhanan Silverajan, Kai-Kristian Kemell

原文摘要

Coordination between large language-model agents has become a central question for AI safety and software engineering, as such agents are deployed in groups that share infrastructure. Existing research typically tells the agents that partners exist or asks them to coordinate. Whether coordination arises through shared state alone, with nothing disclosing that anyone else is present, is the key question for deployments that share caches and memory between agents, yet it has rarely been examined, and to our knowledge not with independent replication; this study does both. Four agents each received a short arithmetic task and a key-value store presented to each as its own scratch space; two held complementary halves of one computation, and no prompt mentioned other agents, sharing or collaboration. For reliability, the environment was rebuilt independently from a written protocol, and both implementations ran under hashed locks on design, data and analysis. The results bear novelty value in three respects. Joint success occurred only through the shared store. Whether a model coordinated depended not on its vendor tier but on whether it wrote its intermediate result and looked at the store again, and one ordinary sentence, "check your workspace again before submitting", switched that second look on and off. The findings held under replication. For practice, state shared between agents is a communication channel and should be separated, namespaced and logged. For research, designs should be locked before the data, and the parse rule, endpoint and parameters reported. Future work should test open-weight models and separate using another agent's output from intending to communicate.

cs.MA · cs.CL · cs.SE

新论文 · v1arXiv:2611.20721

CARE: Contrastive-Anchored Residual Encoding with Listwise Reconstruction for Retrieval-Oriented Semantic IDs

Yuan Xu, Dawei Chen, Xiaoguang Lin, Xin Chen, Yulong Ou, Haijun Wu

原文摘要

Generative retrieval replaces nearest-neighbor search with the generation of a document's semantic ID (SID), so the SID tokenizer bounds what the retriever can recall. Common SID constructions (residual k-means, RQ-VAE, finite scalar quantization, capacity balancing) optimize criteria defined on document embeddings alone and do not control whether a query can still find its relevant documents after quantization. We propose two retrieval-oriented SID tokenizers. CARE-SID (Contrastive-Anchored Residual Encoding for Semantic IDs) quantizes in a retrieval-aligned space: a zero-initialized residual alignment network is trained with a query-document contrastive loss before quantization, an anchor loss and a reconstruction target fixed to the original embedding prevent drift and collapse, and reference-vector rating residual quantization assigns the codes. CARE-LR (CARE with Listwise Reconstruction) then distills, for each training query, the similarity distribution that the original embeddings induce over a candidate list into the SID reconstructions, through a function-preserving layer-resolved head. Both keep a document-only encoding interface. We judge SIDs without training a generator, by row-budget recall in a bucketing view (the partition) and a reconstruction view (the SID with its reconstruction). In offline evaluation on industrial video search data, both tokenizers achieve higher reconstruction-view recall than residual k-means, and CARE-LR improves further on CARE-SID, mainly through the listwise distillation. A comparison of two document embeddings shows that contrastive alignment helps most when the embedding has not been trained on search data, and that the embedding affects SID recall far more than the quantizer. CARE-SID is deployed in the generative retrieval stage of an industrial video search system.

cs.IR

新论文 · v1arXiv:2611.20720

AVD: A Multi-Sensor Teleoperated Wheelchair Platform with Safety-Aware Control

Namai Chandra, Madhur Thareja, Boby George

原文摘要

Electric wheelchairs predominantly rely on manual joystick interfaces, which present critical barriers to independent mobility for individuals with severe motor and visual impairments. This paper presents AVD (Autonomous Vehicle Drive), a dependable teleoperation architecture for assistive mobility that unifies perception, communication, embedded control, and remote supervision in a single low-cost platform built entirely from commercially available hardware. The central engineering contribution is a safety-oriented design framework: control authority follows a static hierarchy, a manual emergency stop and the occupant's joystick pre-empt remote commands, and the on-board sensing layer has stop-only authority. The compute design partitions primary and safety functions and specifies a heartbeat-driven safe-state transition for the fault cases considered. The sensing stack this framework depends on is characterized against measured data: per-channel acquisition latency, a 2,025-scan LiDAR degradation campaign spanning five target configurations and a control under water mist, airborne dust, and direct aperture occlusion, and attitude measurements across static inclines to 47 degrees. The lowest pooled environmental-condition mean retained 76.6% of the clear-baseline forward-sector yield, and no scan lost the sector completely. A logged vibration-induced inertial dropout occurred while LiDAR and camera logging continued, illustrating complementary channel behavior. The result is a documented prototype and an explicit validation path for a deployable wheelchair implementation.

cs.RO

新论文 · v1arXiv:2611.20719

ACiT: Proprioceptive-Prior Action Chunking with Inverted Transformers

Haixiang Wu, Zhihao Guan, Yang Yang

原文摘要

Visuomotor policies condition action prediction on visual and proprioceptive observations. While historical proprioceptive sequences carry rich dynamic priors, current methods treat them as equal to high-dimensional vision, causing the proprioceptive signal to be overwhelmed. To identify what is lost in equal-conditioning fusion, we analyze proprioceptive data and find that strong inter-joint coupling is the key action-determining structure. This finding aligns with the neural sensorimotor loop, in which proprioception first forms a body-centered prior and vision is later calibrated via parietal remapping. Inspired by this, we propose ACiT, Proprioceptive-Prior Action Chunking with Inverted Transformers, which reinforces historical joint-coupling as the primary condition with vision as a later calibration. This design is instantiated through three modules: Inverted State Encoding builds a proprioceptive prior via per-joint tokens and inter-joint self-attention. State-Visual Grounding lets joint tokens query visual evidence, making vision goal- and calibration-only. Inverted Action Chunking decodes per-joint trajectories independently. ACiT improves success rates on most LIBERO, RoboTwin 2.0, and real-world tasks, with the largest gains on those that require dynamics and coordination. The same conditioning design transferred to the VLA backbone pi_0-ACiT yields significant gains with better execution efficiency.

cs.RO

新论文 · v1arXiv:2611.20718

TaF-Foundation: Wrench-Grounded Cross-Sensor Tactile Representations

Jiaming Jiang, Yuzhe Huang, Baokun Yang, Hao Liang, Li Gao, Haoran Guo, Pei Lin, Shengcheng Luo 等 11 位作者

原文摘要

Tactile sensing is essential for contact-rich manipulation, yet heterogeneous sensing mechanisms and observation formats hinder cross-hardware transfer. Since physical contact is governed by Newtonian mechanics, we ground tactile representations in six-dimensional wrenches, establishing a common physical reference across sensing mechanisms. Specifically, we pair tactile observations from all sensors with wrench measurements, enabling shared physical supervision without requiring direct tactile-to-tactile pairing between sensors. To support learning at scale, we develop a dedicated acquisition platform and collect over 100 million paired tactile observations and wrench measurements from 24 sensors spanning four families of sensing principles. Building on this dataset, our framework combines sensor-specific input adaptation with a shared tactile encoder. By learning to reconstruct wrenches, the encoder maps observations from different sensors into a shared, continuous feature space grounded in contact physics. To leverage these representations for manipulation, we introduce TaF-Policy, which integrates tactile features with visual observations and robot states to generate action chunks. We evaluate the learned representations through wrench estimation, cross-sensor retrieval, few-shot adaptation to unseen sensors, and robotic manipulation. On the core benchmark, our method reduces single-frame force RMSE by 17.1% and improves cross-sensor retrieval R@1 by 13.11 percentage points over the strongest baseline. In manipulation experiments, TaF-Policy achieves average success rates of 51.33% across three simulated tasks and 46.25% across four real-world tasks, compared with 47.33% and 23.75%, respectively, for the strongest baselines evaluated on the same task sets. Project page: https://mrjiangjm.github.io/TaF-Foundation/.

cs.RO

新论文 · v1arXiv:2611.20715

Calibrate Once, Grow the Vocabulary: Candidate-Independent Scores for Conformal Risk Control in Open-Vocabulary Segmentation

Md Tanveer Hossain Munim, Bijoy Ahmed Saiem, Muhammad Abdullah Adnan

原文摘要

Open-vocabulary segmenters accept class names at inference. Conformal risk control can bound how often their prediction sets miss the true label, but we show that this bound breaks when names are added after calibration. On ADE20K, a threshold calibrated for 10% risk at 150 names reaches up to 15.4% risk at 845 names in released CAT-Seg models. The risk exceeds the target on every calibration split, yet the prediction sets grow far less than the target requires. In SED they instead grow larger than needed. The cause is that pruning, cross-label attention and vocabulary normalisation make each label's score depend on the other requested labels. Scores can move either way, so a threshold recalibrated at a larger vocabulary need not hold at smaller ones. We remove this dependence without training by scoring each label against a fixed reference bank of names. A label's score then stays the same when names are added, so one calibration keeps its guarantee as the vocabulary grows. The guarantee holds whatever names are added, even ones chosen per image after seeing it. On three benchmarks and five segmenters, the converted models meet the target at every vocabulary size we evaluate. For CAT-Seg and SED at alpha=10%, they use at most one more label per pixel than the released models recalibrated at the grown vocabulary. Treating names instead of images as calibration samples also bounds the miss rate of added names. If the annotated names are a random sample of the names in the calibration images, an added name's expected miss rate on those images is at most the target. For harder added names, the excess is at most their gap in mean miss rate. Applied to Grounding DINO, which splits large vocabularies into chunks, the conversion also makes inference about six times faster.

cs.LG

版本更新 · v2arXiv:2611.18176

ESI: An Embodied Self-Improvement Flywheel for LLM-VLA Agents

Yundi Cai, Zihan Wang, Chenxi Han, Yi Cheng, Houde Liu, Zilei Wang

原文摘要

Independently pretrained language models and vision-language-action (VLA) policies provide complementary building blocks for embodied agents, but connecting them does not automatically produce coordinated behavior. The VLA may generate actions that diverge from the LLM's intended subtask and, upon regaining control after a correction, undo the promising state restored by the LLM. We introduce ESI (Embodied Self-Improvement), an automated flywheel that uses environmental interaction to align reasoning and action. ESI treats the modular agent as the unit of post-training, repeatedly refining the prompts that guide the LLM, the shared skill interface that expresses its intent, and the VLA parameters that realize that intent, then redeploying these components together. Our key insight is that collaboration itself can supply supervision for improving this interface. The LLM's subtask decisions provide semantic supervision for what the policy should execute, while its effective corrections and subsequent student continuations provide action-level supervision for recovery and handoff. The student also learns from its own effective execution, allowing locally useful experience to contribute even when the overall episode fails. On ten selected RoboDojo tasks, ESI achieves a mean Score of 62.03 and a mean success rate of 49.41% using an LLM-VLA agent without generating task-specific control code. On both metrics, it outperforms the published reference results of all hybrid embodied agents, including the Agent+WAM system GO-3 Nano Preview (47.27 Score and 36.60% success), as well as all compared code-based methods.

cs.RO

新论文 · v1arXiv:2611.20714

MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling

Fanda Fan, Kuiye Ding, Liming Mao, Bingsong Wang, Yao Wang, Xiaorui Wang, Ruijie Jian, Zhipeng Liu 等 12 位作者

原文摘要

Time series forecasting underpins critical applications in finance, energy, healthcare, and transportation. Although deep models have achieved strong results, most adopt single-scale modeling or restrict multiscale processing to the input side, causing a misalignment between multiscale inputs and single-scale outputs and limiting predictive power. We introduce the Modular Scale-wise Autoregressive Framework (MSAR), a model-agnostic design that forecasts progressively across multiple temporal resolutions. MSAR offers three advantages: (1) scale-wise aligned modeling, which disentangles heterogeneous temporal patterns by aligning inputs and outputs at each scale; (2) scale-wise autoregression, where coarse-scale predictions guide finer-scale forecasting through hierarchical information flow; and (3) a modular architecture, enabling seamless integration with diverse backbones such as CNNs, MLPs, and Transformers. Extensive experiments across a broad set of datasets and forecasting models demonstrate that MSAR achieves consistent improvements in both accuracy and inference efficiency, validating the effectiveness of scale-aligned autoregression for multiscale time series forecasting. The code is available at: https://github.com/Oryxo/MSAR.

cs.LG

新论文 · v1arXiv:2611.20711

AgentFaultBench: State-Verified Evaluation of Tool-Fault Recovery

Sachin Gupta

原文摘要

Does recovery advice help an agent finish a task after a tool fails? AgentFaultBench evaluates LangGraph and CrewAI agents performing specified tasks in an isolated GitLab installation. We inject tool errors and check both the resulting files and issues and the required reads, verification and final response. The prompt supplies the expected issue and report text, so the task tests execution rather than content generation. In the primary comparison of 1,944 planned runs, advice changes success by -8.33, 0.00 and +1.06 percentage points relative to a neutral reminder; missing outcomes leave the latter two comparisons inconclusive. Later experiments test a revised recovery policy. GPT-4o mini improves, while Sol and Claude already complete the recoverable cases. In a separate 624-run study on six related tasks not previously used by that policy, the guided condition records 161 correct final states and one unknown outcome in 192 planned runs, versus 142/192 with neutral feedback. The gain lies between +9.90 and +10.42 pp when missing outcomes are included. Removing issue IDs gives 47/48 successes versus 46/48 with IDs; other execution information remains. A second checker agrees on 1,879 observed primary outcomes and 241 constructed test cases. No human validation was collected. The findings support testing advice against explicit recovery controls rather than assuming it helps.

cs.AI · cs.LG

新论文 · v1arXiv:2611.20710

SG-ODOM: Event-Driven Proprioceptive State Estimation with Stability-Gated Contact Updates for Legged Robots

Francesco Iotti, Chiyun Noh, Franco Angelini, Manolo Garabini, Ayoung Kim, Maurice Fallon, Frank Dellaert

原文摘要

Reliable proprioceptive state estimation for legged robots fuses inertial sensing with kinematic sensing from leg encoders. The latter assumes a foot is stationary during the stance phase; however, physical foot touchdown does not necessarily provide a stationary reference for odometry, particularly during impact and load transfer. Repeatedly applying kinematic corrections throughout the same contact phase can introduce redundant or unreliable information. We present SG-ODOM, a proprioceptive odometry framework that uses stability-gated contact selection to schedule kinematic updates. Following physical touchdown, a stability gate accepts the contact for state estimation only after the foot reaches a sufficiently stable support condition. The resulting validated touchdown event triggers an estimator correction, while additional timeout updates bound the maximum duration of uninterrupted IMU propagation. The framework is evaluated on multiple legged platforms, both quadrupedal and humanoid robots, against representative state-of-the-art proprioceptive estimators. Across the evaluated sequences, SG-ODOM demonstrates competitive or superior estimation accuracy, reducing Relative Pose Error (RPE) by up to 25% compared to the baseline estimator on outdoor sequences from the GrandTour dataset. Source code: https://github.com/ori-drs/SG-ODOM. Video: https://youtu.be/-583_RyuhqQ

cs.RO

版本更新 · v2arXiv:2610.22872

Look Back, Correct Forward: Error Feedback Calibration for Time Series Forecasting

Haonan Yang, Yulin He, Zhuo Li, Jing Zhao, Huibin Tan

原文摘要

Time series forecasting models are increasingly deployed in continuously evolving environments. After a forecast is issued, future observations gradually arrive and reveal how the model has failed. Existing methods mainly treat such observations as supervision for parameter updates. However, it remains unclear whether verified forecasting errors can themselves provide causal feedback for correcting future predictions. To address this, we introduce Error Feedback Calibration (EFC), a fully test-time framework for deterministic post-hoc correction of time series forecasting. EFC constructs a Causal Error Diagonal (CED) from revealed errors of overlapping historical forecasts, providing a fresh view of the frozen forecaster's recent failure behavior. Then Cumulative Error Transport (CET) maps this error state to future residuals using cumulative estimation, while temporal out-of-sample validation controls the correction strength. Temporal Residual Learning (TRL) further predicts only the residual structure left after CET from recent CED trajectories, rather than relearning the entire forecasting error. Extensive experiments across forecasting backbones and datasets show that EFC broadly improves forecasting performance while substantially controlling harmful over correction.

cs.AI

新论文 · v1arXiv:2611.20704

QASK-Edit: Adaptive Sparse Attention Across Queries and Key Sources for Efficient Video Editing

Hengrui Liu, Wenbo Xu, Ziqi Sheng, Wei lu

原文摘要

Diffusion Transformers (DiTs) have achieved strong performance in generation based video editing, but suffer from high inference latency due to the long token sequences formed by conditioning inputs and generated videos. Although training-free sparse attention reduces this cost, existing methods typically apply a fixed retention ratio or a single threshold shared across all tokens. In this work, we view video editing as conditional generation and identify a key insight: attention demand varies significantly both across different key sources (e.g., source videos, reference images, audio, text, and generated videos) and across queries within each source. Motivated by this, we propose QASK-Edit (Query-Adaptive Sparsity over Key Sources for Video Editing), a training-free sparse attention framework that allocates computation independently for each query and key source. Specifically, for each query, QASK-Edit considers both the attention mass and approximation risk of each block. It then evaluates candidate routing thresholds against each key source's risk budget, choosing exact computation or approximations to dynamically adjust sparsity for each query. Extensive experiments on three video editing models demonstrate that QASK-Edit achieves up to $1.46\times$ end-to-end speedup over dense attention pipeline while preserving both editing quality and unedited region fidelity. Furthermore, QASK-Edit generalizes directly to Reference-to-Video generation, delivering up to $1.36\times$ speedup while maintaining generation quality.

cs.CV

版本更新 · v2arXiv:2611.11249

Understanding When and Where Self-Supervised Speech Models Learn Phonemes and Prosodic Cues through Layer-Wise and Time-Resolved Probing

Masaru Tanibata, Shun Takahashi, Hiroki Ouchi, Sakriani Sakti

原文摘要

Self-supervised speech models (S3Ms) encode a rich hierarchy of acoustic, prosodic, and phonetic information, yet when and where it emerges during pretraining remains unclear. We train frozen-encoder probes on every Transformer layer across pretraining checkpoints of two matched models: HuBERT-Base, whose stage 2 is a separately initialized model trained on new pseudo-label targets, and single-objective wav2vec 2.0-Base. Our five tasks span an acoustic-to-abstract gradient: absolute pitch (F0), speaker-relative pitch, lexical stress, phoneme boundaries, and 38-way phoneme identity. Acoustic-prosodic cues and phone boundaries are decodable from the earliest checkpoints and barely shift across layers, whereas phoneme identity is constructed during pretraining, re-localizing to upper-middle layers under HuBERT's stage-2 targets at a matched update count. Acquisition order therefore tracks abstraction from the acoustic surface, not the segmental/suprasegmental distinction, extending to prosody an account established for phonetic, lexical and syntactic structure; the no-switch wav2vec 2.0 shows no comparable re-localization.

cs.CL

新论文 · v1arXiv:2611.20703

Efficient Multi-View Generation with Iterative Global-Local Proxy Attention

Wei Tan, Kunming Luo, Hongyu Yan, Yu Zhang, Zihao Zhang, Xiatian Zhu, Lei Xie

原文摘要

Generating consistent multi-view RGB images and normal maps from a single input image provides complementary appearance and geometric cues for 3D reconstruction. However, maintaining cross-view consistency requires information exchange across viewpoints, and dense cross-view attention becomes computationally expensive as the number of views and spatial resolution increase. In this paper, we propose Global-Local Proxy Attention (GLPA) to reduce cross-view communication costs while preserving fine-grained within-view processing. Specifically, GLPA retains full-resolution interactions within each view and uses compact global proxies for cross-view communication. To further leverage the exchanged information, GLPA incorporates iterative proxy refinement, which rebuilds the proxies from updated features and reuses the same attention parameters for subsequent interactions within a single denoising step. We evaluate GLPA on two structurally different diffusion backbones, FLUX and Stable Diffusion. Experiments on FLUX show that GLPA achieves a $2.65\times$ speedup in attention computation per denoising step over dense attention, while improving reconstruction IoU from 0.6849 to 0.7019 and reducing NVS LPIPS from 0.086 to 0.076. Results on Stable Diffusion further demonstrate the effectiveness of GLPA, with a $1.80\times$ attention speedup and improvements across all five quality metrics.

cs.CV