跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-19 07:43 — 2026-11-20 07:43(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 06:44最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

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

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,249 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 06:42(北京时间)
版本更新 · v3arXiv:2401.10816

Co-Pilot for Health: Personalized Algorithmic AI Nudging to Improve Health Outcomes

Jodi Chiam, Aloysius Lim, Cheryl Nott, Nicholas Mark, Ankur Teredesai, Sunil Shinde

原文摘要

The ability to shape health behaviors of large populations automatically, across wearable types and disease conditions at scale has tremendous potential to improve global health outcomes. We designed and implemented an AI driven platform for digital algorithmic nudging, enabled by a Graph-Neural Network (GNN) based Recommendation System, and granular health behavior data from wearable fitness devices. Here we describe the efficacy results of this platform with its capabilities of personalized and contextual nudging to $n=84,764$ individuals over a 12-week period in Singapore. We statistically validated that participants in the target group who received such AI optimized daily nudges increased daily physical activity like step count by 6.17% ($p = 3.09\times10^{-4}$) and weekly minutes of Moderate to Vigorous Physical Activity (MVPA) by 7.61% ($p = 1.16\times10^{-2}$), compared to matched participants in control group who did not receive any nudges. Further, such nudges were very well received, with a 13.1% of nudges sent being opened (open rate), and 11.7% of the opened nudges rated useful compared to 1.9% rated as not useful thereby demonstrating significant improvement in population level engagement metrics.

cs.HC · cs.AI · cs.LG

新论文 · v1arXiv:2611.23710

CONCORD-Rec: Catalog-Conditioned Modality Utility for Semantic-ID Diffusion Recommendation

Haopeng Jin, Bingkang Shi, Tao Yu, Yifei Ma, Hao Liu, Hongzhu Yi, Jinwen Luo

原文摘要

Multimodal generative recommendation with discrete semantic identifiers (SIDs) requires distinguishing historical modalities that merely alter token predictions from those that genuinely reduce catalog-level ambiguity. When audiovisual, visual, or textual streams are missing, degraded, or semantically conflicting, uniform fusion and unconstrained token gates can propagate misleading content across iterative denoising steps. We propose CONCORD-Rec, a reliability-conditioned discrete diffusion recommender supervised by counterfactual catalog-partition utility. Given a fixed tokenizer and a partially masked SID state, CONCORD-Rec evaluates out-of-fold teacher coalitions over the exact feasible catalog support and aggregates item posteriors across the target code partition at each unresolved position. Rather than distilling raw token probabilities directly, the resulting counterfactual loss differences supervise an availability-masked tokenwise gate that allocates bounded modality residuals around a behavioral denoiser while retaining an exact behavioral fallback slot. We establish theoretical fixed-support ranking stability bounds under gate perturbations and evaluate position-level and code-conditional allocation across audiovisual and image-text recommendation benchmarks under controlled missingness, signal degradation, and semantic conflict. Across 20 source-compatible protocol-dataset rows, CONCORD-Rec improves NDCG by 4%; under matched 30% conflict it improves NDCG by 14.63%. The full-vs-uniform-T=16 sweep improves quality by 2.00-3.58% while reducing p95 latency by up to 86.89%.

cs.IR

新论文 · v1arXiv:2611.23708

Rational Ensemble Logic for Cohort Discovery with Real-World Electrophysiology Data

Guo-Qiang Zhang, Xubing Hao, Yan Huang, Xiaojin Li, Licong Cui

原文摘要

Biomedical knowledge representation should make the passage from observations to conclusions transparent, rigorous, understandable, explainable, and reproducible (TRUER). We introduce Rational Ensemble Logic (QEL) for specifying temporal phenotypes in real-world electrophysiology data (RWED), with a meaning independent of the implementation software. QEL combines three parameterized modal operators (exact displacement, bounded existence, and bounded universality) over rational time with Boolean connectives and first-order quantification. Its Labeled Interval Ensemble (LINE) semantics represents annotated records as finite interval ensembles. We relate the operators to morphological operations and develop endpoint-array algorithms and finite rational evidence sets for model checking. We prove closure and semantic correctness of the interval operations, obtain finite evidence sets by quantifier elimination, and establish polynomial data complexity for fixed formulas. On 54 manually constructed records, a prototype agreed with the assigned outcomes for base and strict post-ictal generalized EEG suppression (PGES) queries. A separate feasibility experiment over 1,976 patients identified 37 qualifying patients and 45 annotation patterns in 16 seconds. The released prototype uses endpoint candidates and numerical tolerances. QEL supports the TRUER principle through explicit phenotype definitions, precise semantics, and provably correct evaluation procedures, with rational witnesses for existential queries. These provide a logical foundation for formal specification and correctness of algorithms that are independent of specific clinical interpretation, data annotation quality, and software implementation.

cs.LO · cs.AI

版本更新 · v3arXiv:2611.11148

MOSU2: Long-range Navigation System with Multi-modal Scene Understanding

Jing Liang, Zhenyu Hou, Senthurbavan Kirubaharan, Md Safwan Mondal, Ashok Gudivada, Xuesu Xiao, Dinesh Manocha

原文摘要

Robots that travel long distances through public outdoor spaces must do more than avoid obstacles: they must remain on terrain suited to their mobility and decide when to proceed, yield, or detour around pedestrians, cyclists, vehicles, traffic signals, and temporary restrictions. These decisions are difficult because their correctness often depends on how a scene evolves, such as whether an approaching car is slowing or a cyclist will cross the robot's path. Vision-language models (VLMs) can interpret such cues, but they reason over images that lack metric geometry and motion. Supplying this evidence at every step is too slow for real-time navigation, and hand-crafted triggers cannot anticipate the open-ended variety of outdoor situations. We present MOSU2, a long-range navigation system with two-stage trajectory selection, in which first-stage contextual reasoning determines when additional evidence is needed and what to retrieve. Only when an interaction remains unresolved does the first stage trigger the second stage to retrieve geometric and dynamic information and align it with scene context to make navigation decisions. Building on MOSU, MOSU2 follows routes from GPS-based route planning and filters candidate trajectories through multi-modal traversability analysis before selecting a trajectory to move the robot. In real-world experiments spanning stop gestures, construction sites, crosswalks, and roads shared with vehicles, cyclists, and pedestrians, MOSU2 raises mean navigation success from 61.8% to 94.2% and condition-detection accuracy from 72.2% to 91.4% over its single-image predecessor, at about 2.2 times its mean decision latency. Project website: https://jinggm.github.io/mosu2/

cs.RO

版本更新 · v2arXiv:2609.35629

SANTA++: Sampling Attention through Representative Keys

Kyle Lee, Christian Z. Pratt, Ruoyu Fang, Heekyung Lee, Avinash Lohitsa, Ryan Modafe, Kerem Y. Camsari

原文摘要

Attention often concentrates on a small subset of tokens in the context, but which subset matters changes from one query to the next. To exploit this changing structure, we introduce SANTA++, a training-free stochastic attention method that uses representative keys for memory-efficient selection without scanning the entire key-value (KV) cache. Cached keys are organized into teams, and the query scores one representative from each team to decide which teams to sample. We compute exact attention scores within the sampled teams and reweight each team's contribution by the inverse of its inclusion probability. This importance sampling correction estimates attention over the full cache, with a sampling budget that lets us trade memory reads for accuracy. With Qwen2.5-7B-Instruct at 32K context, contiguous SANTA++ at S=1024 retains 95-98% of dense aggregate scores on LongBench v2, HELMET RAG, and RULER using 28-31% logical KV access. On RULER, SANTA++ outperforms Quest across the tested accuracy-access sweep, using 48.7% fewer KV reads at approximately 79% accuracy. It also outperforms MagicPIG at low access. At S=1024, our Triton implementation gives a 1.38x attention-operator speedup over the Flash backend of PyTorch scaled dot-product attention (Flash SDPA) in FP16. At batch eight, full-model decoding is 1.23x faster than dense Flash SDPA with matched INT4 model weights and FP16 KV-cache precision on an RTX 5090 Laptop GPU. Our kernels are available at https://github.com/OPUSLab/santapp-kernel-demo.

cs.LG · cs.CL

版本更新 · v2arXiv:2606.19711

A Differentiable Composite Approximation Framework for Autonomous Underwater Vehicle Maneuvering Modeling from Sea-Trial Data

Aobo Wang, Aifei Xia, Zihao Wang, Lizhu Hao, Shaorong Xie

原文摘要

Field-based modeling from onboard measurements can produce autonomous underwater vehicle (AUV) maneuvering models that reflect real operating characteristics. From an approximation perspective, conventional maneuvering models use predefined constraint polynomial bases, whereas data-driven models use data-adaptive bases. Motivated by this basis-function view, this paper presents a differentiable composite approximation formulation, in which the polynomial basis component and the data-adaptive basis component are treated as differentiable parts of a unified predictor and calibrated jointly. A gradient-based co-calibration method is developed for full-scale AUV maneuvering prediction, where a sensitivity-aware mechanism regulates bounded polynomial updates while the neural residual captures remaining nonlinear discrepancies under a shared prediction objective. To account for ocean-current effects in field data, a turning-motion-based current estimation and compensation procedure is incorporated to construct current-compensated learning targets for training and rollout. The framework is evaluated using sea-trial data collected from a 7-meter AUV under multiple maneuvering conditions. Results show that the proposed method improves recursive trajectory and velocity prediction compared with polynomial-only, neural-only, and frozen-prior hybrid baselines, demonstrating its applicability to field-data-based AUV maneuvering modeling.

cs.RO · cs.LG · eess.SY

新论文 · v1arXiv:2611.23705

A Hardware-Aware Comprehensive Study of Edge Vision Deployment with A Unified Hardware-Model-Runtime Mapping Framework

Le Duc An, Le Duc Thanh, Vo Hoai Viet

原文摘要

The rapid growth of deep learning has driven the deployment of computer vision directly on resource-constrained edge devices. However, the extreme heterogeneity of edge hardware architectures poses major challenges in selecting and designing suitable vision models. This survey bridges the gap between edge hardware constraints, model architectures, and deployment software toolchains. We establish a comprehensive taxonomy classifying edge hardware into three distinct tiers: mid-range devices (GPUs and dedicated NPUs or TPUs), dedicated embedded MPU or SoC processors, and microcontrollers (MCUs). We aggregate and analyze multi-source benchmark results for image classification and object detection across the computing spectrum, spanning from tens of watts down to milliwatt-scale bare-metal MCUs. Based on these empirical findings, we propose a two-tiered hardware-to-model mapping framework that provides concrete model selection matrices across performance priorities (Speed, Balanced, Accuracy) and actionable architectural design principles (peak SRAM budgeting, resolution-first scaling, and algorithm-compiler co-design). Finally, we highlight critical deployment challenges including toolchain fragmentation, operator incompatibility, and Vision Transformer feasibility, and outline promising future research directions in on-device adaptation and sustainable Edge AI.

cs.CV

新论文 · v1arXiv:2611.23704

Localizing Text Anonymization for Trustworthy AI: Extending RAT-Bench to Malaysian Microdata and PII

David Hong Liang Chew, Zexi Yao, Nataša Krčo, Matthieu Meeus, Waqas Khalid Obeidy, Yves-Alexandre de Montjoye

原文摘要

As governments and organizations adopt foundation models for public services and workplace productivity, sensitive citizen, employee, and administrative text may enter LLM workflows through inference, retrieval, fine-tuning, or local model development. We examine whether text anonymizers transfer to new deployment settings by extending RAT-Bench to Malaysia using local microdata, Malaysian PII formats, and culturally grounded transcripts in Malaysian English and Bahasa Malaysia. We evaluate NER- and LLM-based anonymizers using an LLM attacker that infers attributes from anonymized text, measuring both re-identification success and text utility. Across Malaysian English and Bahasa Malaysia, the two LLM anonymizers provide the strongest explicit privacy-utility trade-offs, reducing Easy/Hard re-identification risk to 23-29% while preserving BLEU scores of 0.77-0.94. Non-LLM tools show sharper failure modes, either preserving utility while leaving high residual risk or reducing risk through severe over-redaction, especially in Bahasa Malaysia. These findings suggest that anonymizers should be evaluated against deployment-relevant languages, identifier formats, and cultural contexts before being relied on in public-sector, workplace, or local AI pipelines.

cs.CL

版本更新 · v2arXiv:2610.38366

TCC-RAG: Temporal Causal Chain-Guided RAG for Temporal Knowledge Graph Question Answering

Xinxun Zhang, Yuxiang Wang, Shanshan Feng, Jun Zhang, Tieyun Qian, Binhang Yuan, Kai Yin, Xiao Yan 等 9 位作者

原文摘要

Recent advances in large language models (LLMs) have spurred growing interest in temporal knowledge graph question answering (TKGQA). Most existing methods rely on semantic retrieval augmented generation (RAG), which suffers from fundamental limitations in complex temporal reasoning. On the one hand, semantic-based RAG methods struggle to capture the multi-hop causal knowledge required for complex temporal reasoning. On the other hand, these methods introduce excessive redundant knowledge, trapping LLMs in spurious reasoning chains that potentially result in erroneous answers. To address these problems, we propose a Temporal Causal Chain-guided RAG (TCC-RAG) to retrieve a concise yet sufficient set of causal knowledge to support complex temporal reasoning. Specifically, we reformulate the temporal knowledge graph into a multi-view causal cue graph, with causal cues inducing connections that explicitly encode temporal evolution and causal dynamics. Based on the causal cue graph, we construct a query-specific temporal causal chain to guide the retrieval process, enabling the model to focus on a concise set of causally relevant knowledge. Finally, we introduce a causal evidence filter to refine the retrieved knowledge, ensuring its causal consistency with the underlying temporal logic of the query. Experiments show that TCC-RAG achieves substantial performance gains of 10.72% and 8.40% on two TKGQA benchmarks, and delivers a remarkable 62.97% improvement for multi-step temporal reasoning.

cs.CL

新论文 · v1arXiv:2611.23702

KnowMe Paper Radar: Lightweight Discovery of Promising Papers in the Age of Autoresearch

Zhuo Chen, Jian Wang, Jinjie Gu, Lijun Wu

原文摘要

The growing volume of topically similar papers makes it difficult to identify new work that can offer useful research insights or methodological guidance. We present KnowMe Paper Radar, a lightweight discovery tool that combines multiple sources of evidence into personalized reading priorities. Users specify topics, priorities, exclusions and dates; the system brings together topical relevance, recency, author research histories, collaboration paths and direction-specific institutional context. By exposing each score component and its supporting sources, KnowMe helps readers select promising papers for their current questions and discover relevant work beyond familiar authors. Automatic acquisition, version merging and graph-cache reuse keep this workflow convenient without large language model (LLM) inference during ordinary use. Experiments on 174,640 acquired records show more than threefold faster repeated context preparation, while cached abstracts improve normalized discounted cumulative gain at rank 10 (NDCG@10) from 0.412 to 0.598 on expert-judged retrieval tasks. Complementary analyses examine how the same accumulated records support semantic retrieval, research-history modeling and literature-grounded planning. A browser interface and a structured command-line interface (CLI) make these capabilities available to both researchers and research agents, positioning KnowMe as a practical upstream tool for literature-informed recursive self-improvement (RSI) workflows.

cs.AI · cs.IR

版本更新 · v2arXiv:2608.07855

CommitKV: Commit-Aligned KV Cache Compression for Multimodal Agents

Weizhong Huang, Jinchao Zhang, Xiawu Zheng

原文摘要

Multimodal agents gather visual evidence through reasoning and tool use, extending their ability to solve tasks beyond the initial input. However, accumulating observations increases KV cache memory and inference costs. Token eviction reduces these costs by retaining useful cached tokens. Existing methods use attention, redundancy, or stage-specific queries to rank tokens, without explicitly comparing the same history across tool interactions. When observations shift attention, they may mistake temporarily reduced influence for lost usefulness and evict information needed later. We propose CommitKV, a training-free KV cache compression method that accounts for this changing evidence use. Commit-aligned measurement compares the deletion effects of the same page before a tool call completes and after its observation returns. Lifecycle-aware compression retires pages with low influence in both windows and temporarily protects pages influential before the call. Joint scoring combines attention importance, key redundancy, and token-level deletion effects to fill the remaining budget. Extensive experiments cover four open-weight multimodal models and eight benchmarks. CommitKV achieves the highest average accuracy among the compared compression methods on all four models. On Qwen3-VL-8B, it achieves 69.85% at a 512-token budget, only 0.91% below FullKV, and exceeds the strongest compression baseline by 8.44% at 256 tokens. Deploying the Qwen3-VL-8B agent with SGLang and vLLM at a 256-token budget reduces peak allocated GPU memory by 54.37%-55.23% and accelerates end-to-end inference by 2.12-2.17$\times$ over FullKV on the matched workload.

cs.LG

版本更新 · v3arXiv:2606.19817

Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance

Myeongseok Nam, Donghun Yeo, Seungwook Kim

原文摘要

Synthetic images are increasingly used to augment scarce real data for object detection. However, not all synthetic sets help equally, and the only way to know a set's value is to train a detector on it, which is slow and demands dense annotation. We ask whether a training-free metric can instead rank candidate synthetic training sets by their downstream utility. We propose Conditional-Composition Domain Match (CCDM), which converts any feature-space distance into a composition-stratified comparison, matching candidate and target within metadata-defined strata without training a detector. On COCO and VisDrone-DET, the best CCDM variant ranks 20 and 19 candidate training sets in strong agreement with YOLOv8 mAP (Spearman $ρ$ = 0.98 and 0.96), outperforming FID, KID, and MMD. Furthermore, CCDM holds when reference metadata comes from detector pseudo-labels instead of ground truth.

cs.CV

版本更新 · v2arXiv:2609.34299

Difficulty-Aware Statistical Matching for Dataset Distillation

Hongxu Ma, Guang Li, Shijie Wang, Dongzhan Zhou, Suorong Yang, Baoli Sun, Takahiro Ogawa, Miki Haseyama 等 9 位作者

原文摘要

Dataset distillation (DD) condenses a large original set into a small distilled set with high training utility. Decoupled statistical matching methods substantially reduce distillation time and memory overhead while achieving strong performance. However, they typically supervise all distilled data with running statistics estimated from the entire original set. These statistics mainly capture the average feature distribution while ignoring the difficulty differences among original data, making them insufficient for characterizing the difficulty structure of the original data. To address this issue, we propose Difficulty-aware Statistical Matching (DSM) for Dataset Distillation. After pretraining, DSM uses the Global Difficulty Score (GDS) to evaluate image difficulty, sorts the original data according to the scores, and then partitions it into IPC (Images per Class of distilled data) difficulty groups. During distillation, Statistics Updated Again (SUA) updates the teacher's BN running statistics using original data from each group via forward passes, providing difficulty-specific supervision for each corresponding distilled batch. Meanwhile, Initial Sample Screening (ISS) initializes distilled data with original images from the corresponding group, providing an effective starting point for precise matching. Experiments across multiple datasets and model architectures demonstrate the effectiveness of DSM, showing that it broadens the difficulty range of distilled samples and further improves the final performance. Code will be released.

cs.CV

新论文 · v1arXiv:2611.23700

Auditable Clinical Support with Decision Agents

Tiancheng Bao, Riga Wu, Jan Wienhold, Sebastian Billig, Patrick Winnersbach, Hsuan-Chih Chen, Akis Giannoukos, Jiayang Li 等 16 位作者

原文摘要

Clinicians reviewing a diagnostic work-up will ask what was considered at each step and why the assessment changed. Agents powered by free text can reach physician-level diagnostic accuracy, but their written reasoning does not always reflect the factors that went into the decision. Here, we present Decision2Care, a decision agent that works up the acutely ill patient without producing any text. A decision model assigns a probability to each permitted EHR action, and fixed rules carry out the most probable one. We evaluated Decision2Care on the records of 546 emergency admissions across 12 diseases. Decision2Care reached a diagnostic accuracy of 86.5%, compared with 86.1% for the MIRA-v2 agent, and required a median of 2.2 s per work-up, compared with 92-100 s. Each work-up tracked which options Decision2Care was considering at each step. In 10 of the 12 diseases, the differential diagnosis changed most at the test on which the guideline bases the diagnosis. Where Decision2Care was most confident after a single work-up, all but four of its diagnoses were correct (98.5%). We traced each of these four errors back to a single imaging report. Three of them were corrected when that report was removed. The same kind of decision was used to select the treatments, and Decision2Care's drug orders were judged guideline-adherent more often than MIRA-v2's. In emergency patients, its prediction of death was comparable to that of three intensivists on the same cases. In five of the eight intensive care cohorts, it exceeded the best of the three 24-h severity scores within 2-6 h of records. Our results show that decision agents can carry out clinical work-ups while recording the options, probabilities, and execution rules behind each action for audit.

cs.AI

新论文 · v1arXiv:2611.23697

What Do Learned 3D Models Add to Localization from Posed References?

Jaehyun Kim, Wonseok Kang, Jeongmin Lee, Tae-Wan Kim

原文摘要

Localizing a query from a few posed reference images avoids building a 3D point map. We ask what the camera predictions of learned 3D models add to geometric estimation from the same references, and where failures arise. Across eight learned models and variants and five test sets, we compare reference budgets, swap pose components, and intervene on the references a model sees. At fine pose-error thresholds, geometric estimation with one additional reference is significantly more accurate than every model on two references on Cambridge and NAVER B1 and never significantly worse, alone or as a fallback behind a shared acceptance gate; with the same three references, the more accurate approach depends on the scene. The gain from the learned translation magnitude depends on reference selection: it improves seven of the eight models on 12-Scenes with the spread-out pairs we select, but none of the five we test with the two top-ranked retrieved references. Where retrieval also returns references from other locations, at NAVER Gangnam Station, models fail at different stages. A robust alignment brings Pi3X and MapAnything within 3.3 pp of adding references as needed. In controlled tests, aligning on the nearby references largely restores VGGT, Pi3X and MapAnything but not Depth Anything 3, and pose-conditioned Pi3X recovers only if the far poses are masked and left out of its input-pose normalization.

cs.CV

版本更新 · v4arXiv:2603.09145

Counterfactual Feature Regularization for Expansion-Based Class-Incremental Learning

Zhen Zhang, Jielei Chu, Jiangtao Hu, Bin Liu, Jie Wang, Ya Liu, Fengmao Lv, Tianrui Li

原文摘要

Current expansion-based methods for Class Incremental Learning (CIL) effectively mitigate catastrophic forgetting by freezing old features. However, such task-specific features learned from the new task may collide with the old features. From a causal perspective, spurious feature correlations are the main cause of this collision, manifesting in two scopes: (i) guided by empirical risk minimization (ERM), intra-task spurious correlations cause task-specific features to rely on shortcut features. These non-robust features are vulnerable to interference, inevitably drifting into the feature space of other tasks; (ii) inter-task spurious correlations induce semantic confusion between visually similar classes across tasks. To address this, we propose a Probability of Necessity and Sufficiency (PNS)-based regularization method to guide feature expansion in CIL. Specifically, we first extend the definition of PNS to expansion-based CIL, termed CPNS, which quantifies both the causal completeness of intra-task representations and the separability of inter-task representations. We then introduce a dual-scope counterfactual generator based on twin networks to ensure the measurement of CPNS, which simultaneously generates: (i) intra-task counterfactual features to minimize intra-task PNS risk and ensure causal completeness of task-specific features, and (ii) inter-task interfering features to minimize inter-task PNS risk, ensuring the separability of inter-task representations. Theoretical analyses confirm its reliability. The regularization is a plug-and-play method for expansion-based CIL to mitigate feature collision. Extensive experiments demonstrate the effectiveness of the proposed method.

cs.LG · cs.AI

新论文 · v1arXiv:2611.23695

MoMoVL: Modality-Aware Adaptive Compression for On-Device Sparsely-Activated Vision-Language Models

Dongkeun Lee, Wonjun Lee

原文摘要

The rise of the agentic web has been accompanied by growing demand for on-device Vision-Language Models (VLMs) that perform diverse cross-modal web tasks with enhanced privacy and reduced latency. Mixture-of-Experts (MoE) models are widely adopted in modern VLMs for compute-efficient scalability, yet their multi-expert architecture poses deployment challenges due to substantial memory demands. Mixed-precision quantization is an effective compression technique that reduces bit-widths while adapting to the heterogeneous hardware budgets of edge devices, particularly well-suited for MoE due to its inherent structural sparsity, which causes imbalanced importance among experts. While prior work has applied quantization for efficient MoE inference at the edge, we point out that in MoE-based VLMs, the modality-specific characteristics of visual and text tokens further impact expert quantization. To address this issue, we present MoMoVL, a modality-aware adaptive compression framework for MoE-based VLMs that brings vision-language inference within reach of on-device resource budgets. Motivated by our empirical findings on modality-induced disparities across experts, MoMoVL jointly exploits the per-expert activation profile and per-modality quantization sensitivity to guide bit-width assignment. Experimental results show that MoMoVL improves the accuracy-compression trade-off relative to state-of-the-art mixed-precision baselines and reduces memory footprint by up to 15.44% with a modest drop in accuracy over its uniform-precision baseline. Our code and data are publicly available at https://github.com/sco-edge/MoMoVL.

cs.CV · cs.LG

版本更新 · v2arXiv:2609.17781

SPROUT: The Open-Source Soft Growing Robot for Search and Rescue

Antonio Alvarez Valdivia, Ciera McFarland, Robert Reeve, Ankush Dhawan, Chad Council, Megan Richardson, Margaret McGuinness, Nathaniel Hanson

原文摘要

Soft robotic systems have long been theorized as ideal candidates for use in search and rescue operations; however, there have been significant barriers to entry in graduating soft robotic systems from the laboratory to the field. To address this gap in replicable, reliable soft robot systems, we present the designs for SPROUT, the Soft Pathfinding Robotic Observation Unit. The system has matured over years of interaction with professional urban search and rescue communities, with the goal of operating in dusty, wet, and isolated conditions. This manuscript contains supplementary material, including code, parts manifests, CAD assemblies, and build instructions to allow the broader robotics research community to build their own SPROUT systems. The modular hardware and ROS 2-based software stack support task-specific payloads and control functions, allowing SPROUT to be adapted for applications beyond search and rescue, including infrastructure inspection and archaeology. Here, we demonstrate SPROUT performing a variety of challenging inspection and traversal tasks in collapsed structure training sites used by first responders. The main project page is available online at https://sprout-mitll.github.io/sprout/.

cs.RO · eess.SY

新论文 · v1arXiv:2611.23691

MEM-STRESS: Longitudinal Field Study of a Wearable-Informed AI Chatbot for Stress Management

Soorya Ram Shimgekar, Pragya Singh, Shivam Sharma, Chandrayee Roy, Koustuv Saha, Antti Oulasvirta, Talayeh Aledavood

原文摘要

Stress is an increasingly prevalent concern, creating a need for accessible and personalized support. Stress-management chatbots primarily rely on what users report, which may not capture their physiological changes. Wearables capture these changes, but chatbots rarely use them as memory across conversations. We therefore present MEM-STRESS, a stress-support chatbot that turns a wearable ring's physiological data into a layered memory of daily records, baseline deviations, LLM-generated summaries, and uses it to drive multi-session conversations grounded in Dialectical Behavior Therapy (DBT). In a four-week, non-randomized study with 60 adults, we compared MEM-STRESS (Treatment) with a chatbot remembering only past conversations (Control). Memory shaped the conversations: The Treatment chatbot referenced participants' physiological features (e.g., activity in 71.8% of sessions) and suggested more body-related DBT skills than Control (14.5% vs. 5.7%), with Treatment participants also using slightly more body-related words (1.76% vs. 1.45%). Treatment participants praised personalization three times as often (44.4% vs. 14.3%), more frequently reported reflecting differently on stress (69.0% vs. 46.4%, not significant), and described gaining insight into their stress signals. Their perceived stress fell 14.2% from baseline versus 3.6% for Control, though the group difference was not significant. Grounding stress-support chatbots in layered physiological memory is thus feasible and may improve perceived personalization, motivating larger randomized studies.

cs.HC · cs.AI

版本更新 · v3arXiv:2606.14990

Rational Sparse Autoencoder

Naiyu Yin, Maosen Tang, Alex Townsend, Yue Yu

原文摘要

Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK. This hard-codes a particular sparsity mechanism into the model and can distort the reconstruction-versus-sparsity trade-off. We introduce the Rational Sparse Autoencoder (RSAE), which replaces the fixed encoder activation with a trainable rational function. The design is motivated by a reconstruction advantage that we prove for RSAE at matched expected sparsity, with guaranteed non-inferiority to ReLU and, under stated assumptions, provable improvements over JumpReLU and TopK. The model is then implemented through a two-stage pipeline: an initialization procedure that copies the pre-trained baseline SAE weights and calibrates the scale parameters along with the rational coefficients; followed by a fine-tuning step under a sparsity-regularized reconstruction objective that holds $\ell_0$ at the teacher's value. Consistent with this theory, on residual-stream activations of three open-weight language models and across all three baseline activation families, the RSAE improves reconstruction fidelity after the fine-tuning step at the same level of sparsity. These gains are consistent across host language models, across baseline activation families, and across the full range of baseline sparsity we tested, while the upgrade itself adds only 20 scalar parameters per autoencoder and one training run takes between about 4 and 25 minutes on a single consumer GPU.

cs.LG · cs.AI

版本更新 · v3arXiv:2510.03666

MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations

Jiang Wu, Sichao Wu, Yinsong Ma, Guangyuan Yu, Haoyuan Xu, Lifang Zheng, Jingliang Duan

原文摘要

Industrial accidents, particularly in high-risk domains such as surface and underground mining, are frequently caused by unsafe worker behaviors. Traditional manual inspection remains labor-intensive, error-prone, and insufficient for large-scale, dynamic environments, highlighting the urgent need for intelligent and automated safety monitoring. In this paper, we present MonitorVLM, a novel vision--language framework designed to detect safety violations directly from surveillance video streams. MonitorVLM introduces three key innovations: (1) a domain-specific violation dataset comprising 9,000 vision--question--answer (VQA) samples across 40 high-frequency mining regulations, enriched with augmentation and auxiliary detection cues; (2) a clause filter (CF) module that dynamically selects the Top-$K$ most relevant clauses, reducing inference latency by 13.56% while maintaining accuracy; and (3) a behavior magnifier (BM) module that enhances worker regions to improve fine-grained action recognition, yielding additional gains of 3.45% in precision and 8.62% in recall. Experimental results demonstrate that MonitorVLM significantly outperforms baseline vision--language models, achieving improvements of 22.01% in precision, 34.22\% in recall, and 28.37% in F1 score over the 72B unfine-tuned baseline. A lightweight web-based interface further integrates MonitorVLM into practical workflows, enabling automatic violation reporting with video timestamping. This study highlights the potential of multimodal large models to enhance occupational safety monitoring in mining and beyond.

cs.CV · cs.AI

版本更新 · v4arXiv:2501.07744

CBS with Continuous-Time Revisit

Andy Li, Zhe Chen, Danial Harabor, Mor Vered

原文摘要

Multi-Agent Path Finding in Continuous Time (\mapfr) extends the classical MAPF problem by allowing agents to operate in continuous time. Conflict-Based Search with Continuous Time (CCBS) is a foundational algorithm for solving \mapfr optimally. In this paper, we revisit the theoretical claims of CCBS and show the algorithm is incomplete, due to an uncountably infinite state space created by continuous wait durations. Through theoretical analysis and counter-examples, we examine the inherent challenges of extending existing MAPF solvers to address \mapfr while preserving optimality guarantees. By restricting waiting duration to fixed amounts, we identify a related sub-problem on graphs, \mapfrdt which we show is optimally solvable, including by CCBS. It remains an open question whether similar models exist for \mapfrct, a generalised version of \mapfrdt that allows arbitrary wait times, and \mapfrcs, which further allows arbitrary movements in continuous space.

cs.MA

新论文 · v1arXiv:2611.23685

Measuring the Conservatism of Latent Safety Filters for World Models

Johannes Mootz, Mani Amani, Reza Akhavian

原文摘要

A latent safety filter decides from the latent of a world model whether a planned action is safe. Conformal calibration sets the threshold of the filter so that it accepts an unsafe action only with a small probability. However, the filter can still be conservative and refuse many safe actions, depending on the latent. To measure the conservatism that a latent forces on the filter, we group similar latents and actions into cells. A filter that gives one decision per cell can refuse the unsafe transitions of a cell only by refusing the safe ones in it as well. We call the share of safe transitions that lie in such cells the overlap. We prove that the overlap is the minimum share of safe transitions that such a filter has to refuse in order to accept no unsafe transition in the data. Both the overlap and the conformal calibration can be applied to any latent. We use this to compare three existing designs, in which the safety labels train a classifier on top of the world model, the world model itself, or a separate encoder beside it. In a visual navigation task, the separate encoder has the lowest overlap, and at the same conformal level its filter refuses the fewest safe actions and lets the planner reach the most goals of the three.

cs.RO · cs.LG · eess.SY

新论文 · v1arXiv:2611.23684

Variable Length Diffuse Everything: Arbitrary Length Generative Modeling on Arbitrary State Spaces

Kevin Rojas, Felix X. -F. Ye, Molei Tao

原文摘要

Diffusion and flow-based generative models have achieved remarkable results across diverse applications, but most assume data of fixed-dimension/length. Meanwhile, real-world problems such as layout generation often involve variable-length, multimodal data, such as continuous bounding box coordinates paired with discrete types. Existing methods typically address variable length by padding data to a fixed size or by introducing specialized objectives to model lengths explicitly, adding complexity and limiting generality. We propose Variable Length Diffuse Everything (VL-DE), a simple and general framework for variable-length multimodal generation on arbitrary state spaces. Instead of padding, VL-DE handles variable length through an insertion-based mechanism grounded in a principled theoretical framework, yielding a tractable training objective. In addition, by utilizing the fact that VL-DE is based on a generator with an additive form, we develop a higher-order sampler by appropriately handling the time dependence. Extensive experiments on layout and molecule generation demonstrate the effectiveness of our approach.

cs.LG · stat.ML

新论文 · v1arXiv:2611.23680

Structured Extraction of Diffraction Data from Covalent Organic Frameworks

Shenghan Gao, Zhiling Zheng

原文摘要

Powder X-ray diffraction (PXRD) is the primary structural evidence for covalent organic frameworks (COFs) and many other materials. Yet decades of measured patterns exist only as images in published figures. Automatic recovery is difficult, because PXRD figures vary widely in format, from a single curve to crowded stacks with labels, insets, and neighboring plots that challenge traditional computer vision. This work presents a pipeline in which a vision large language model (LLM) interprets the layout of each figure, locating the diffraction plot and its curves and sketching a coarse trace of each, while classical computer vision (CV) refines every trace to pixel-level accuracy. Applied to 3,954 COF articles, the pipeline produces 11,445 calibrated diffraction curves, released in the open database COF-PEAK. Compared with a hand digitization of 60 panels, extracted peak positions differ by a median of only 0.07 degrees. Whereas papers usually report only a few peak angles, which limits further analysis, the digitized curves enable tracking how peak prominence, a possible marker of crystallinity, changes with synthesis conditions. Vision LLMs and classical CV can thus turn such figures into reusable experimental data.

cs.CV · cond-mat.mtrl-sci · cs.AI

版本更新 · v2arXiv:2605.14045

PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow

Wei Dong, Han Zhou, Terry Ji, Guanhua Zhao, Shahab Asoodeh, Yulun Zhang, Guangtao Zhai, Jun Chen 等 9 位作者

原文摘要

Adverse weather removal (AWR) in real-world images remains challenging due to heterogeneous and unseen degradations, while distortion-driven training often yields overly smooth results. We propose PVRF, a unified framework that integrates zero-shot soft weather perceptions with velocity-constrained rectified-flow refinement. PVRF introduces an AWR-specific question answering module (AWR-QA) that uses frozen vision--language models (VLMs) to estimate soft probabilities of weather types and low-level attribute scores. These perceptions condition restoration networks via attribute-modulated normalization (AMN) and weather-weighted adapters (WWA), producing an anchor estimate for refinement. We then learn a terminal-consistent residual rectified flow with perception-adaptive source perturbation and a terminal-consistent velocity parameterization to stabilize learning near the terminal regime. Extensive experiments show that PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations. Code will be released at https://github.com/dongw22/PVRF.

cs.CV

版本更新 · v2arXiv:2611.21102

Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery

Yunchan Jeon, SooGon Kim, Seungwook Kim, CheolWon Lee, Jongmin Lee

原文摘要

Recovering 3D pose and shape of birds from single images is bottlenecked by the long tail of avian diversity: out of ~10,000 species, only a few dozen have 3D-labeled training data, and in-the-wild test sets routinely contain species never seen at training. Generalizing across clades is therefore a central problem. The current state of the art, AniMer+, mitigates it with a family-level contrastive loss that conveys only a binary same-family indicator per pair and discards the continuous structure of the species tree. We propose a taxonomic Ornstein-Uhlenbeck prior on the shape code of the AVES parametric bird mesh model: a multivariate Gaussian whose covariance decays exponentially with Linnaean rank distance, with a learnable selection strength and noise scale. The prior generalizes family contrastive into a continuous, generative form, exposing the graded cross- and within-family similarity that a binary indicator cannot, and brings continuous comparative phylogenetics in as a biology-grounded inductive bias for the long tail. Our method improves over AniMer+ on both metrics of the unseen-species CowBird benchmark and on CtrlAVES3D, while remaining comparable on seen-species CUB. A permutation ablation isolates taxonomic structure from generic Gaussian smoothing, and a rank-granularity ablation identifies cross-order distinctions (the structure beyond a family-vs-not indicator) as the dominant source of the unseen-species gain.

cs.CV

新论文 · v1arXiv:2611.23678

Evaluating Governed LLM-Driven ML Experimentation: Lifecycle, Provenance, and Failure Metrics

Dowling Wong

原文摘要

Autonomous agents that run ML experiments are usually judged by the best score they reach. That score says nothing about how it was reached: whether the agent stayed within the files it was allowed to edit, whether failed trials were kept or silently dropped, and whether each keep or discard decision can be traced to its evidence. We propose evaluating such systems on their experimental process as well as their outcome, and we build a governed harness that makes this possible. A control plane, not the LLM that proposes changes, owns each trial's lifecycle, checks its edit scope, decides keep or discard, and appends one record per trial to an append-only ledger. Governance metrics such as the invalid-action rate, the repeated-bad rate and provenance completeness are computed from that ledger. Across six ML tasks, from synthetic logistic regression to language-model training, and 1,445 trials, the same contract applied unchanged. The ledger exposed failures that a task score hides: a no-memory arm in which all 120 trials failed, a benchmark adapter whose bounded proposals ran out, and a reset failure that reproducibility hashes revealed, after which the affected campaigns were rerun. In a matched counterfactual, a loop that logs only successful trials left no record of 43 of 50 trials, while the governed ledger recorded all 50. Memory ablations show that memory's effect on repeated bad proposals depends on the task. We release the ledgers of all 1,445 trials, so that every number reported for them can be recomputed.

cs.AI · cs.LG · cs.SE

新论文 · v1arXiv:2611.23677

Simpler Tiny Recursive Models

Torben Glass, Zhengxi Zhang, Paul Swoboda

原文摘要

Small models that execute deep looped computational graphs have shown great experimental results on puzzle-like problems like Sudoku, finding shortest paths through mazes, etc. The most well-known one is TRM (tiny recursive model), a simplification of HRM (hierarchical reasoning model). However, the underlying recursion is complicated and involves a high-level and a low-level state, a nested loop recursion, and the network calls with different input and output signatures depending on where we are in the loops. These mechanisms are needed to avoid memorization and overfitting. We propose STRM, a simplified design with a single state and a uniform update. STRM does not sacrifice generalization, improves training speed and final performance. Our key architectural choices that allow our simpler recursion to work are exponential moving updates on the states with varying rates that are jittered during training and readout of the solution on slow-updating channels only. We test STRM on Sudoku-Extreme, PPBench and Maze-Hard with the same data, parameters and compute as TRM: we improve over TRM by $3.8$ points on Sudoku-Extreme and $8.4$ points on PPBench and match it on Maze-Hard. On ARC-AGI-1 and ARC-AGI-2, STRM improves over the published TRM results by $5.4$ and $0.5$ points. We will release our code upon acceptance of the paper.

cs.LG

新论文 · v1arXiv:2611.23676

Finetuning VLAs for Dexterous Manipulation: The Right Checkpoint Is All You Need

Artur Kuramshin, Charlotte Cloutier, Michael Przystupa, Kirsty Ellis, Mohammad S. Akhter, Glen Berseth

原文摘要

Vision-Language-Action models have demonstrated strong manipulation capabilities. A limitation of VLA models is that most manipulation datasets focus on parallel-jaw gripper systems, making transfer to multi-finger hands challenging, particularly as teleoperation datasets are harder to collect with multi-fingered robots. In this work, we study how to best adapt VLAs to dexterous hands by pairing supervised fine-tuning (SFT) with diffusion-steering reinforcement learning (DSRL). Using $π_{0.5}$ and a LEAP hand, we evaluate five fine-tuning recipes across two simulation tasks using only a handful of demonstrations. Our empirical analysis yields three key insights: (1) SFT success is poorly correlated with post-DSRL success, meaning the best SFT checkpoint is rarely the most effective to steer; (2) freezing the vision-language model (VLM) and tuning only the action expert produces the most steerable policy for both training and out-of-distribution placements; and (3) low-rank adaptation (LoRA) is the least steerable approach. Consequently, we recommend an adaptation recipe that freezes the VLM, fully trains the action expert, and eschews SFT rollout success as a checkpoint selection metric.

cs.RO · cs.LG