探索全球前沿学术脉络

01.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13239

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm

作者:

Jiaxin Ai↗Tao Hu↗Xuemeng Yang↗Shu Zou↗Hairong Zhang↗Daocheng Fu↗Yu Yang↗Hongbin Zhou↗Nianchen Deng↗Pinlong Cai↗Zhongyuan Wang↗Botian Shi↗…

Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12106

MSUE: Multi-Modal Soccer Understanding Expert

作者:

Litao Li↗Yibo Yu↗Yufeng Hu↗Zhuo Yang↗Jiali Wen↗Yixin Chen↗Yixi Zhou↗

This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Language Model (VLM), which systematically restructures raw domain data into diverse VQA samples, including concise answers and long-form responses. Second, we propose MSUE, a multi-expert question answering architecture that employs a Large Language Model (LLM) to dynamically dispatch questions to text, image, and video experts. These experts are instantiated as a strong text baseline Gemini3-Flash, a fine-tuned Qwen3-VL, and an external knowledge base, respectively, working collaboratively to enhance VQA performance. MSUE achieves an accuracy of 0.95 on the challenge benchmark, securing third place in the leaderboard.

阅读与讨论 → 访问原文 →

03.

medRxiv (Medicine) 2026-06-16 DOI: HASH:f1aaaf4ad8054e3c3ee69e3819ca6254

Efficacy of Ergothioneine Supplementation on Postpartum Fatigue, Sleep Quality, and Quality of Life: A Randomized, Double-Blind, Placebo-Controlled Trial

作者:

Liu↗Guo↗Ding↗Cao↗Tong↗Zhou↗Shao↗Xiao↗

Background: Postpartum asthenia, characterized by severe fatigue, sleep disturbances, and physiological stress, lacks effective targeted interventions. Ergothioneine (EGT) is a unique, naturally occurring antioxidant that actively accumulates in mitochondria, offering a compelling therapeutic rationale for systemic recovery. This study aimed to evaluate the efficacy of EGT in accelerating postpartum functional restoration and alleviating fatigue. Methods: This single-center, randomized, double-blind, placebo-controlled trial enrolled 40 postpartum women (SF-36 total score [≤] 70) who had ceased breastfeeding. Participants were randomized (1:1) to receive either 120 mg/day of EGT or a matched placebo for 30 days. Efficacy was assessed using the SF-36, Pittsburgh Sleep Quality Index (PSQI), Fatigue Scale-14 (FS-14), and Traditional Chinese Medicine (TCM) asthenia scale. To rigorously evaluate the treatment effects, advanced statistical modeling, including Linear Mixed-Effects Models (LMM) and Analysis of Covariance (ANCOVA) adjusted for baseline covariates, was employed. Results: All 40 participants completed the trial. The EGT group demonstrated robust and accelerated functional recovery. Notably, significant improvements in sleep quality (p = 0.0361) and systemic fatigue (p = 0.0059) were observed as early as Day 15. Importantly, EGT yielded a statistically significant between-group superiority in alleviating mental fatigue compared to placebo at Day 15 (p = 0.0313). By Day 30, the EGT cohort exhibited substantial within-group improvements across all primary metrics, including SF-36 (+35.94%, p = 0.0006) and FS-14 (-27.78%, p = 0.0011). Furthermore, as an additional physiological benefit, EGT induced a selective and significant reduction in hepatic transaminases (ALT: -30.42%; AST: -17.44%) within normal limits, a trend not observed in the placebo group. EGT was exceptionally well-tolerated with no treatment-related adverse events. Conclusions: EGT supplementation (120 mg/day) safely accelerates postpartum functional recovery, offering rapid relief from mental fatigue and sleep disturbances within 15 days, while concurrently optimizing hepatic physiological status. These preliminary clinical signals warrant confirmation in larger, adequately powered cohorts. Trial Registration: ChiCTR2500114171; Prospectively registered on 2025-12-08.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19776

Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding

作者:

Jianing Li↗Zhou Fang↗Yijiang Liu↗Li Du↗

Recently, vision-language models (VLMs) have made significant progress in 3D scene understanding, driving advances in applications such as embodied intelligence and robotic vision. However, existing approaches typically either rely directly on explicit 3D inputs (e.g., point clouds or RGB-D sequences), or introduce an additional 3D geometry encoder to derive 3D-aware visual tokens from 2D images. Such designs structurally decouple 3D geometric perception from the rich 2D semantics learned via vision-language pre-training, hindering the development of a unified 3D vision-language representation. In this work, we propose Occ-VLM, a novel framework for 3D scene understanding that operates purely on posed RGB images and employs a single 2D vision encoder. Specifically, Occ-VLM reconstructs 3D scene occupancy as an auxiliary geometric prior, which is utilized to spatially associate foreground 2D tokens with 3D space. These tokens are then decoded by a Large Language Model (LLM) for unified scene understanding. Extensive experiments demonstrate that Occ-VLM achieves both accurate geometric perception and robust vision-language reasoning: it attains state-of-the-art performance on multi-view occupancy prediction, while performing on par with 3D-input VLMs on 3D Visual Question Answering (VQA) and 3D dense captioning benchmarks.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11531

Measuring language complexity from hierarchical reuse of recurring patterns

作者:

Junyi Zhou↗Rui Liu↗Pengyu Liu↗Yu Liu↗

We introduce the ladderpath index as a measure of language complexity grounded in algorithmic information theory. It counts the minimum steps needed to reconstruct a sequence through hierarchical reuse of repeated substructures, capturing an exactly computable but constrained form of algorithmic compressibility related to, but distinct from, Kolmogorov complexity. We apply the ladderpath approach to 21 parallel corpora from the Parallel Universal Dependencies dataset. The ladderpath index is approximately invariant across the languages, and varies much less than the corpus length. This is more pronounced when all corpora are mapped to a unified binary representation, providing evidence for the equi-complexity hypothesis from a representation-independent perspective. We also observe trade-offs between character inventory size and corpus length, and between vocabulary-level and corpus-level reconstruction complexity, supporting the trade-off hypothesis that total complexity is conserved and redistributed across linguistic levels. The reusable substructures identified by the ladderpath approach, without any linguistic input, overlap with words and morphological components attested in the natural vocabulary. The hierarchical reuse captured by the ladderpath approach parallels the chunking mechanisms proposed in cognitive science, where the human cognitive system compresses linguistic input into nested, reusable units under shared memory and processing constraints. This connection between cognitive chunking and the ladderpath approach provides a new interpretation for the equi-complexity and trade-off hypotheses, grounding both in the shared cognitive architecture that underlies language processing across human languages.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15104

Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

作者:

Huan Kang↗Hui Li↗Tianyang Xu↗Tao Zhou↗Xiao-Jun Wu↗Josef Kittler↗

Infrared and visible image fusion aims to integrate complementary modalities, while existing Euclidean methods impose rigid distance metrics that distort multi-modal interactions and parent-to-child semantic hierarchies. To overcome these limitations, we introduce a text-driven fusion framework empowered by hyperbolic manifold learning. During training, BLIP-extracted text prompts serve as topological anchors within the hyperbolic space, guiding vision-attribute alignment through hyperbolic embeddings that naturally accommodate varying semantic granularities. By exploiting the exponential volume growth dictated by the Poincaré ball's negative curvature, this approach seamlessly embeds hierarchical trees to encode coarse-to-fine semantics without metric saturation, while the vast peripheral space prevents texture distortion during cross-modal fusion. At inference, the fusion process autonomously adapts to input content using the learned text-attribute priors, completely eliminating the need for textual input. Experimental results show our method outperforms state-of-the-art approaches on benchmark datasets, with code available at https://github.com/Shaoyun2023/TEDFusion.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12809

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

作者:

He Li↗Haoang Chi↗Qizhou Wang↗Yunxin Mao↗Zhiheng Zhang↗Jie Tan↗Tongliang Liu↗Wenjing Yang↗Bo Han↗

arXiv:2606.12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often arrive sequentially over time, giving rise to the challenging problem of MLLM Lifelong Unlearning. However, most existing benchmarks are limited in scale and scope, failing to capture the complexities of MLLM lifelong unlearning. To fill this gap, we introduce the MLUBench, a large-scale and comprehensive benchmark featuring 127 entities across 9 classes under lifelong unlearning requests. We perform extensive experiments using MLUBench and reveal that existing unlearning methods suffer from severe, cumulative degradation. More critically, we further identify the unique challenge of this problem: unlike in unimodal models, MLLM lifelong unlearning is constrained by the need to preserve multimodal alignment. Continually unlearning from one modality could degrade the entire model. To alleviate this challenge, we propose LUMoE, an effective method. Experiments demonstrate that LUMoE significantly mitigates the degradation problem faced by baselines. The source code and the MLUBench dataset are open-sourced in https://github.com/lihe-maxsize/Lifelong_Unlearning_main.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2505.14418

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents

作者:

Pengzhou Cheng↗Haowen Hu↗Zheng Wu↗Zongru Wu↗Tianjie Ju↗Zhuosheng Zhang↗Gongshen Liu↗

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs offered by AI providers, which introduces a critical but underexplored supply chain threat: backdoor attacks. In this work, we first unveil that MLLM-powered GUI agents naturally expose multiple interaction-level triggers, such as historical steps, environment states, and task progress. Based on this observation, we introduce AgentGhost, an effective and stealthy framework for red-teaming backdoor attacks. Specifically, we first construct composite triggers by combining goal and interaction levels, allowing GUI agents to unintentionally activate backdoors while ensuring task utility. Then, we formulate backdoor injection as a Min-Max optimization problem that uses supervised contrastive learning to maximize the feature difference across sample classes at the representation space, improving flexibility of the backdoor. Meanwhile, it adopts supervised fine-tuning to minimize the discrepancy between backdoor and clean behavior generation, enhancing effectiveness and utility. Extensive evaluations of various agent models in two established mobile benchmarks show that AgentGhost is effective and generic, with attack accuracy that reaches 99.7\% on three attack objectives, and shows stealthiness with only 1\% utility degradation. Furthermore, we tailor a defense method against AgentGhost that reduces the attack accuracy to 22.1\%. Our code is available at \texttt{anonymous}.

阅读与讨论 → 访问原文 →

09.

medRxiv (Medicine) 2026-06-10 DOI: HASH:61f43e95c5927be5711a1bbc6d0c06b9

Human genetic evidence links serine biosynthesis to diabetic peripheral neuropathy

作者:

Fridman↗Kakar↗Jensen↗Van de Vondel↗Wheeler↗Phillips↗L. S↗Zhou↗Zuchner↗Reusch↗Raghavan↗

Diabetic peripheral neuropathy (DPN) is a common and disabling condition for which no disease-modifying therapies are available. Glycemic and metabolic drivers do not fully explain why only a subset of individuals with diabetes develop DPN, and genetic contributors remain poorly defined. We aimed to perform a multi-population genome-wide association study (GWAS) of DPN to highlight potential new etiological pathways and therapeutic targets. Methods We performed a multi-population GWAS of neuropathy in people with and without diabetes using the VA Million Veteran Program and UK Biobank, followed by replication in the All of Us Research Program (AoU), and gene-based and gene-set analyses to identify implicated pathways. Causal relationships between circulating serine levels and DPN were further tested using two sample Mendelian randomization. To further evaluate pathogenic potential, we analyzed rare, high impact variants in GWAS implicated genes among individuals with unresolved inherited neuropathies using the GENESIS platform. Findings Among individuals with type 2 diabetes, we identified seven genome wide significant loci (p

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.02800

Cosmos 3: Omnimodal World Models for Physical AI

作者:

NVIDIA↗Aditi↗Niket Agarwal↗Arslan Ali↗Jon Allen↗Martin Antolini↗Adeline Aubame↗Alisson Azzolini↗Junjie Bai↗Maciej Bala↗Yogesh Balaji↗Josh Bapst↗…

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI – effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2604.09698

Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation

作者:

Jiazhou Liang↗Yifan Simon Liu↗David Guo↗Minqi Sun↗Yilun Jiang↗Scott Sanner↗

arXiv:2604.09698v2 Announce Type: replace-cross Abstract: The growing ubiquity of Extended Reality (XR) is driving Conversational Recommendation Systems (CRS) toward visually immersive experiences. We formalize this paradigm as Immersive CRS (ICRS), where recommended items are highlighted directly in the user's scene-based visual environment and augmented with in-situ labels. While item recommendation has been widely studied, the problem of how to select and evaluate which information to present as immersive labels remains an open problem. To this end, we introduce a principled categorization of information needs into explicit intent satisfaction and proactive information needs and use these to define novel evaluation metrics for item label selection. We benchmark IR-, LLM-, and VLM-based methods across three datasets and ICRS scenarios: fashion, movie recommendation, and retail shopping. Our evaluation reveals three important limitations of existing methods: (1) they fail to leverage scenario-specific information modalities (e.g., visual cues for fashion, meta-data for retail), (2) they present redundant information that is visually inferable, and (3) they poorly anticipate users' proactive information needs from explicit dialogue alone. In summary, this work provides both a novel evaluation paradigm for in-situ item labeling in ICRS and highlights key challenges for future work.

阅读与讨论 → 访问原文 →

12.

medRxiv (Medicine) 2026-06-18 DOI: HASH:c6acb7a5e78a07e3443ec97e2f7a725b

Personalizing Suicide Risk Assessment: Machine Learning Extraction of Cross-Modal Interactions Between Psychosocial and Demographic Factors in Veterans

作者:

Levis↗M. E↗Shiner↗Dimambro↗Rozema↗Ayandeh↗Diallo↗A. B↗Zhou↗Li↗Wu↗Gui↗…

Background: Veterans face an elevated risk of suicide compared to the general population, motivating national efforts to develop predictive models that can guide proactive care. Current models used by the U.S. Department of Veterans Affairs (VA) rely primarily on structured electronic health record (EHR) data, though clinical notes contain rich contextual information that can be quantified using natural language processing (NLP) to derive psychosocial variables that may improve risk detection. Machine learning methods, particularly classification and regression trees (CART), can also uncover interactions between clinical and psychosocial variables, enabling identification of patient characteristics that modify suicide risk factors. However, integrating structured and unstructured data presents challenges because NLP features often greatly outnumber traditional clinical variables, potentially biasing interaction discovery. In prior work, we addressed this imbalance by introducing a weighted CART framework that balances structured variables with NLP-derived psychosocial features from semantic lexicons (SEANCE). While effective, semantic approaches summarize language into predefined constructs and may overlook important lexical variation present in clinical narratives. Methods: In this study, we extend that framework by replacing semantic features with a high-dimensional bag-of-words (BoW) representation of clinical notes and by evaluating models across cohorts defined by structured suicide risk stratification (low, medium, high) and varying temporal lookback windows. Using a cohort of 27,241 veterans, we analyzed clinical documentation collected up to 30, 90, or 270 days prior to death (or a matched index date for controls), enabling temporally flexible risk modeling. XGBoost models were trained to balance structured and unstructured features and identify cross-modal interactions between textual and clinical variables. Results: When incorporated into generalized linear models, these interactions improved predictive performance, particularly among low- and medium-risk patients, and substantially reduced the performance gap between interpretable and more complex models. Notably, the BoW representation outperformed our prior semantic index-based approach. Discussion and Conclusions: Together, these findings demonstrate the utility of interpretable NLP methods for uncovering clinically meaningful interactions between psychosocial and demographic factors in suicide risk and establish a strong benchmark for future deep learning approaches aimed at capturing richer contextual and temporal information from clinical narratives.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15390

Not All Skills Help: Measuring and Repairing Agent Knowledge

作者:

Yixuan Wang↗Yiyang Zhou↗Yiming Liang↗Congyu Zhang↗Fuxiao Liu↗Jiawei Zhou↗Huaxiu Yao↗

LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone. We argue that this conflates two distinct roles: generating a skill from experience is a creative act that judgment handles well, while deciding whether that skill actually helps requires empirical evidence across many tasks. Measuring per-skill causal contributions via randomized masking, we find that skill libraries exhibit pervasive causal heterogeneity: individual skills routinely help on some task types while hurting on others, yet their opposing effects cancel in aggregate, making them invisible to global curation methods. We propose ASSAY, a framework that separates generation from curation: it computes a per-skill causal attribution on a small development set, restructures the library offline, and suppresses skills with negative predicted effect for each test task. Across seven base models spanning four providers and two benchmarks (AppWorld and tau-bench), ASSAY consistently improves over prior skill-curation approaches. On AppWorld's hardest split, DeepSeek-V3 achieves 69.3% task-goal completion (47.4% relative improvement), a new state of the art among all published methods including weight-tuned approaches. On tau-bench retail, GPT-4.1 improves by 8.7% relative, advancing past o4-mini, o1, and GPT-4.5 on the public leaderboard without any weight modification. Ablation traces the dominant gain to per-task masking, confirming that the bottleneck is matching skills to tasks at inference time, not removing bad skills globally. Code is available at https://github.com/aiming-lab/assay.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11285

EventRadar: Long-Range Visual UAV Discovery through Spatiotemporal Event Sensing

作者:

Zhiting Zhou↗Xingchen Liu↗Xinglin Yu↗Jiashen Chen↗Haoyang Wang↗Jingao Xu↗Yunhao Liu↗Xinlei Chen↗

Unauthorized unmanned aerial vehicle (UAV) activity around airports, public venues, and other sensitive sites has made protected-airspace monitoring increasingly important. A practical sensing system must search a wide angular region, find small long-range targets, and return both bearing support and UAV-specific evidence before a restricted perimeter is breached. Existing UAV detection paths often rely on spatially organized evidence, such as body extent, silhouette, or track continuity. At long range, however, these cues become difficult to preserve and verify as the target footprint weakens and its image-plane support shrinks. EventRadar follows a complementary cue: propeller-induced temporal periodicity, which recent event-camera sensing studies have shown can reveal UAV-specific motion after appearance becomes weak. We extend this cue to kilometer-scale active sensing with an event-camera prototype. Scene-Anchored Geometry Evidence (SAGE) fuses scanning events with IMU pose to maintain a bearing-indexed scene memory, separating transient candidate support from persistent background clutter. Comb-guided Harmonic-Group Learned Iterative Shrinkage and Thresholding Algorithm (CHG) then treats each candidate as a weak high-rate timing signal and recovers phase-insensitive harmonic evidence with fixed compute. Compared with related event-camera baselines on 700-1500 m UAV event recordings, EventRadar achieves 0.990 mAP$_{.3}$ and 0.949 F1$_{.3}$, reduces FN$_{.3}$ to 0.009, and shows real-time feasibility in prototype profiling.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12940

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

作者:

Xiang Li↗Yixuan Zhou↗Jingran Xie↗Zhiyong Wu↗Hui Wang↗

arXiv:2606.12940v1 Announce Type: cross Abstract: Neural speech codecs based on Vector-Quantized VAEs (VQ-VAEs) are core audio tokenizers for speech LLMs, yet their reconstruction fidelity is bottlenecked by quantization error. Modifying the quantizer or increasing model capacity are common fixes, but they complicate downstream language modeling. Our core idea is to align the decoder's internal feature manifolds when processing both the quantized tokens and their original continuous embeddings, using a lightweight feature-mapping loss. This requires minimal training overhead and no inference-time changes. Applied to XCodec2, self-guidance improves all reconstruction metrics, achieving state-of-the-art low-bitrate performance. Notably, it enables a 4x codebook reduction without fidelity loss, which downstream TTS experiments show significantly improves LLM-based synthesis by simplifying the token modeling space. Multiple statistical observations and visualizations corroborate the enhanced internal manifold alignment in the decoder. Extensive experiments confirm its generality across various inductive biases. Self-guidance thus establishes an efficient, broadly applicable method for high-fidelity neural audio coding.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-25 DOI: arXiv:2606.25964

WinDOM: Self-Family Distillation for Small-Model GUI Grounding

作者:

Chengheng Li-Chen↗Zhiqian Zhou↗Hao Chen↗Nicolas Chauvin↗

arXiv:2606.25964v1 Announce Type: new Abstract: Small ($\sim$2B) GUI-grounding agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face two open recipe questions: how to obtain bounding-box training data without expensive human annotation, and how to combine supervised fine-tuning with reinforcement learning. We address both, with the explicit goal of pushing small-model performance rather than scaling up. WinDOM is a $54{,}425$-record grounding corpus harvested by driving an open-source Windows 11 web reimplementation under headless Playwright, with bounding boxes read directly off the DOM and no OCR or human annotation. Self-Family Distillation (SFD) is a single rejection-sampling cold-start parameterised only by the teacher choice: either an EMA of the student (no external model) or a frozen larger same-family teacher. We then treat the saturation depth of the SFD cold-start as an explicit GRPO hyperparameter. On a Qwen3.5-2B student, the under-saturated cold-start is a better GRPO initialiser than the converged one: SFD-4B with Early-init RL gains $+5.4$ OOD-mean ($+3.5$ ScreenSpot-Pro, $+7.0$ OSWorld-G, $+5.8$ ScreenSpot-V2) over the base. The same-size EMA mode lands within roughly one OOD-mean point of the cross-size $4$B variant ($65.2$ vs $66.3$) without an external teacher.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.12670

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

作者:

Xiangyi Li↗Yimin Liu↗Wenbo Chen↗Bingran You↗Zonglin Di↗Yifeng He↗Shenghan Zheng↗Kyoung Whan Choe↗Jiankai Sun↗Shuyi Wang↗Chujun Tao↗Binxu Li↗…

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12033

SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection

作者:

Min Yang↗Mi Zhou↗Limin Wang↗

Video understanding is a crucial part of computer vision, with numerous application scenarios. With the increasing popularity of mobile devices, an increasing number of efforts are trying to deploy video understanding models on them. However, existing video understanding models are difficult to deploy due to their large size and prohibitive power consumption. Spiking Neural Networks (SNNs) have shown bioplausibility and low power advantages over Artificial Neural Networks (ANNs), especially on neuromorphic chips which are regarded as essential components of future mobile devices. However, excessively long conversion time-steps and severe performance degradation problems limit their application. To solve the problems above, we explore the application of SNNs on temporal action detection (TAD), which is an important task in video understanding, and propose the first SNN-based end-to-end TAD architecture coined as SpikeTAD. While maintaining extremely low power consumption, SpikeTAD achieves an average mAP of 67.2% in THUMOS14 and 37.42% in ActivityNet-1.3, demonstrating the feasibility of a low-power TAD model. Our code is available at https://github.com/MCG-NJU/SpikeTAD.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.01602

Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks

作者:

Haoji Hu↗Huaqing Mao↗Yijun Lin↗Xiaowei Jia↗Jinwei Zhou↗Minoh Jeong↗Yao-Yi Chiang↗

arXiv:2606.01602v2 Announce Type: replace-cross Abstract: Pairwise dependence measures such as correlation and causality are fundamental to temporal data mining, yet there is still no principled and robust way to quantify dependence between heterogeneous data types, especially between continuous time series and discrete temporal event sequences. Existing approaches rely on ad hoc transformations or mutual-information estimators that are highly sensitive to quantization, repeated values, and event redundancy, leading to biased or unstable results in practice. We propose a nonparametric mutual information estimator that directly measures the dependence between time series and event sequences without data transformation, learning, or ad hoc discretization. Our method models the continuous-discrete duality of real-world time series to handle quantization and repeated-value artifacts and introduces a latent event clustering strategy to mitigate bias from event co-occurrence and redundancy. Together, these yield a robust and unified framework that bridges discrete and continuous mutual information. We evaluate the proposed estimator on four representative tasks: discrete-continuous time-delayed mutual information for causality analysis, global and local temporal repetition discovery, discrete covariate selection for time series forecasting, and continuous feature selection for classification. Experiments on synthetic and real-world datasets show consistent improvements over existing methods in accuracy, robustness, and interpretability, positioning our approach as a general-purpose dependence operator for heterogeneous temporal data, similar to Pearson correlation for homogeneous time series. Code available at: https://github.com/HaojiHu/Multimodal-Temporal-Data-Quantification

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11562

GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

作者:

Zhuoyi Peng↗Jingzhou Jiang↗Hanlin Gu↗Lixin Fan↗Yi Yang↗

Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and scientific theme are all inferred from a node together with its neighbourhood. We introduce GraphInfer-Bench, a benchmark for whether LLMs can perform this graph inference: producing an open-ended answer that no single node supports and no path retrieves. Existing graph-QA protocols cannot test this capability: algorithm simulation, node classification, single-node description, KG-QA, and GraphRAG all admit answers retrievable from one node or along a path. GraphInfer-Bench defines five tasks along Description (what a region is) and Comparison (how regions differ), each constructed so the ground truth lives in no single node. The release contains 42,000 samples across six real-world graphs, produced automatically and screened by a four-layer quality-control protocol. We evaluate four method families against the same tasks: graph-token alignment models, zero-shot frontier closed-source LLMs, Graph2Text supervised fine-tuning, and plain GNNs as a structural reference. No method family closes the gap. Graph-token alignment partially handles description tasks (relational, theme) but collapses on comparison tasks. Frontier LLMs lead on outlier detection and community partition among LLM-based methods but lag on masked-node prediction. Graph2Text SFT is the strongest LLM-based method on the description side yet falls behind frontier LLMs on comparison. Across every task, plain GNNs match or beat the strongest LLM-based row, with the largest margin on community detection. GraphInfer-Bench surfaces graph inference as an open capability gap rather than a property of any one architecture.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14199

OdysSim: Building Foundation Models for Human Behavior Simulation

作者:

Xuhui Zhou↗Weiwei Sun↗Weihua Du↗Jiarui Liu↗Haojia Sun↗Qianou Ma↗Tongshuang Wu↗Yiming Yang↗Maarten Sap↗

Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation. Yet helpfulness-driven post-training pulls them toward a homogeneous, overly agreeable assistant register, creating a behavioral Sim2Real gap. We present OdysSim, the largest open systematic investigation of behavioral foundation models, i.e., models trained to simulate human behavior at scale. We propose SOUL, a taxonomy of five capability axes (CONV, SS, COG, ROLE, EVAL) that unifies 62 datasets and 23 benchmark tasks under one framework. Specifically, we curate the OdysSim corpus (21.4M interactions, 10B tokens, retrofitted with back-generated social contexts), construct the SOUL-Index benchmark, and develop an end-to-end training recipe combining midtraining, task-specific RL, and expert distillation. The resulting open 8B OSim model ranks first or tied-first on 8 of 23 tasks, outperforming any individual frontier model by this count, with the strongest gains on conversational and social tasks. Its outputs are also more human-like in length, formatting, and word choice, and it transfers zero-shot to out-of-distribution user simulation on $\tau$-bench, nearly matching real users on reaction alignment (93.2 vs. 93.5). We further show that LLM-as-judge RL induces reward-hacking patterns, and that our detectors can mitigate them during post-training. Together, our findings suggest that behavioral foundation models require rethinking the LLM training paradigm. We release all artifacts to support future research.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13782

MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis

作者:

Lushi Pu↗Weiming Zhang↗Xinheng Xie↗Zixuan Fu↗Bingxiang He↗Hongya Lyu↗Xin Li↗Jie Zhou↗Yudong Wang↗

arXiv:2606.13782v1 Announce Type: new Abstract: Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Most are concentrated in areas that are easier to formalize, such as algebra and elementary number theory, and provide limited coverage of subfields that require deeper reasoning, including mathematical analysis. To address this gap, we introduce MA-ProofBench, to the best of our knowledge, the first formal theorem-proving benchmark dedicated to Mathematical Analysis. The benchmark contains 200 formalized theorems covering 6 core topics and 27 subcategories, including measure and integration theory, complex analysis, and functional analysis. The problems are divided into two difficulty levels, an undergraduate level (Level I, 100 problems) and a Ph.D. qualifying level (Level II, 100 problems), to evaluate how well LLMs perform formal reasoning at different mathematical depths. Each problem is constructed through a human-led, LLM-assisted formalization pipeline followed by independent expert review, ensuring that the formal statements remain faithful to the original mathematics. We evaluate a range of recent general-purpose reasoning models and formal theorem provers on MA-ProofBench. However, most models perform poorly: even the best-performing model, GPT-5.5, achieves only 16% Pass@8 on Level I and 5% on Level II, while most models stay close to 0% on Level II. Further analysis identifies Mathlib hallucinations and incomplete proofs as the two dominant failure modes, while an evaluation on the natural-language version of the benchmark exposes a clear gap between informal and formal reasoning. MA-ProofBench is intended to serve as a reliable reference for tracking progress in formal mathematical reasoning in advanced domains.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13709

LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models

作者:

Yan Hong↗Kedong Xiu↗Wei Li↗Jun Lan↗Huijia Zhu↗Shuheng Zhou↗Zhongcai Lyu↗Weiqiang Wang↗Jianfu Zhang↗

arXiv:2606.13709v1 Announce Type: cross Abstract: We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving general capability under a compact intervention footprint. Existing broad direction-based edits can perturb general-purpose computation, whereas support-only expert edits often lack sufficient capacity to correct heterogeneous refusal representations. To address this limitation, we introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework that follows a support-then-correction execution order: it first identifies a compact edit support, then aggregates prototype correction directions into layer-wise correction directions, and finally applies rank-one layer-wise correction only within the selected support. By using the edit support as a structural gating constraint, LoMC increases correction capacity without expanding the intervention scope. Experiments on text-only and multimodal safety benchmarks across four routed backbones show that LoMC substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18402

Deep-Learning-Based Pixelated Microwave Filter Design and Characterization using Electro-Optical Electric-Field Measurements

作者:

Han Zhou↗Richard Bannister↗Caspar Pierce↗Haojie Chang↗David Widen↗Ludvig Fornstedt↗Gabriel Melin↗Alexander Bohlin↗Pontus Lindeberg Fredriksson↗Dilbagh Singh↗Christian Fager↗Koen Buisman↗…

arXiv:2606.18402v1 Announce Type: cross Abstract: Traditional microwave filter design typically relies on iterative parameter tuning and predefined topologies, which limits design space and increases development time. This study uses a deep learning approach combining convolutional neural networks with genetic algorithms to automate pixelated microwave filter synthesis. To validate the approach experimentally, both S-parameter and spatial electric-field measurements were analyzed. The synthesized low-pass filter demonstrated excellent agreement between simulated and measured performance, achieving a 7 GHz passband with over 20 dB suppression beyond 9.5 GHz. Electro-optical measurements, for the first time, revealed electric field patterns that resemble coupled transmission-lines or stub structures, providing insight into the emergent characteristics of AI-generated designs.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.01476

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

作者:

Yuhang Zhou↗Lizhu Zhang↗Yifan Wu↗Mingyi Wang↗Bo Peng↗Jiayi Liu↗Xiangjun Fan↗Zhuokai Zhao↗

On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy distribution shift of Supervised Fine-Tuning (SFT) and the sparse credit assignment of Reinforcement Learning (RL). However, standard OPD faces two coupled limitations. First, it requires direct access to the teacher's token-level logits, excluding a broad class of capable proprietary models from serving as teachers. Second, the token-level logit signal itself is brittle, depending on a narrow overlap of plausible next tokens between teacher and student, and prone to amplifying degenerate patterns such as repetition loops. In this paper, we introduce OmniOPD, a novel framework that addresses both limitations through a logit-free, chunk-level supervision signal. OmniOPD replaces deterministic logit matching with Monte Carlo rollouts that approximate the teacher's local preferences through a continuous semantic similarity metric over multi-token chunks, and concentrates this supervision via a peak-entropy scheduler that audits the student only at its high-uncertainty reasoning forks. A Dirichlet-Multinomial Bayesian prior and a base-model KL anchor further bound the variance of discrete sampling and prevent policy collapse across unaudited tokens. Across competitive benchmarks, OmniOPD surpasses the standard OPD approach by up to +28.64% on math, confirming that chunk-level semantic verification extracts a more reliable learning signal than token-level logit matching, whose high information density is offset by significant noise and brittleness. Furthermore, when paired with stronger black-box teachers such as Claude-4.5-Haiku and Gemini-2.5-Flash, OmniOPD achieves an additional +9.54% relative on math over its open-weight teacher counterpart, advancing the student past the performance of self-exploratory RL.

阅读与讨论 → 访问原文 →