探索全球前沿学术脉络

01.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14383

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

作者:

Haonan Qi↗Jin Cao↗Yongqi Zhang↗Xintong Wang↗Weidong Tang↗Bin Chen↗Chengfu Huo↗Haojun Pan↗Hengyu You↗Jing Li↗Yingde Wang↗Liang Ding↗…

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction – recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86–94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15–34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20092

EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

作者:

Ganlin Yang↗Zhangzheng Tu↗Yuqiang Yang↗Sitong Mao↗Junyi Dong↗Tianxing Chen↗Jiaqi Peng↗Jing Xiong↗Jiafei Cao↗Jifeng Dai↗Wengang Zhou↗Yao Mu↗…

Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard Vision-Language-Action (VLA) policies often fail when task-relevant cues become occluded or unobservable over time. While existing memory-augmented methods utilize historical context, they either suffer from severe information bottlenecks, incur high latency via decoupled dual systems, or rely on unselective buffers that accumulate massive visual redundancies. To address these limitations, we introduce EventVLA, an end-to-end framework founded on the concept of sparse visual evidence memory that comprises two core components: foundational visual anchors to retain initial and short-term contexts, and a dynamic Keyframe Evidence Memory (KEM) module. Specifically, KEM directly predicts future keyframe probabilities from the VLA's latent embeddings to autonomously capture and store sparse, task-critical visual events. This foresight-driven mechanism empowers the policy to dynamically evaluate the future causal utility of current observations, preserving transient visual evidence before it becomes unobservable. Furthermore, we propose RoboTwin-MeM, a diagnostic benchmark specifically designed to evaluate non-Markovian manipulation tasks with interactive visual evidence. Extensive evaluations show that across 17 memory-requiring simulation tasks and 4 real-world bimanual tasks, EventVLA achieves an average success rate improvement of +40% over state-of-the-art memory-augmented VLAs.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12871

DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks

作者:

Jingxuan Han↗Wei Liu↗Mingyang Zhu↗Youpeng Wang↗Ziwen Wang↗Lin Qiu↗Xuezhi Cao↗Xunliang Cai↗Zheren Fu↗Licheng Zhang↗Zhendong Mao↗

arXiv:2606.12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses. For SAs evaluation, prior benchmarks mainly focus on specialized tasks that are unlikely to arise in real-world user scenarios. Moreover, their reliance on coarse task-level rubrics often limits evaluation interpretability. To bridge this gap, we introduce DailyReport, an open-ended benchmark to evaluate SA capabilities on daily search tasks. It contains 150 open-ended tasks with 3,546 associated rubrics, capturing widely discussed and timely information demands of real-world users. Each task is decomposed into subtasks and evaluated with cascade rubrics across disentangled dimensions. Through cascade performance attribution and user-centric aggregation, we derive highly interpretable scores for each dimension, along with a user preference score. Our results on 17 agentic systems show that current systems still fall short of users' expectations. To facilitate future research, our dataset and code are made publicly available at https://github.com/AGI-Eval-Official/DailyReport.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2511.20302

CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation

作者:

Shilei Cao↗Ziyang Gong↗Hehai Lin↗Yang Liu↗Jiashun Cheng↗Xiaoxing Hu↗Haoyuan Liang↗Guowen Li↗Chengwei Qin↗Hong Cheng↗Xue Yang↗Juepeng Zheng↗…

In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (e.g., spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance on 16 out of 18 cross-domain benchmarks for RS semantic segmentation.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2511.15645

FDIO: Frequency Decomposed Inertial Odometry

作者:

Shanshan Zhang↗Liqin Wu↗Wenying Cao↗Lingxiang Zheng↗Yu Yang↗

Pedestrian inertial odometry (PIO) estimates autonomous pedestrian motion using only acceleration and angular velocity measurements collected by an inertial measurement unit (IMU), making it highly valuable for consumer level localization applications. However, under a dual device acquisition setting, IMU signals collected by a freely carried mobile device are inherently composite signals in which the global motion of the human torso is coupled with perturbations induced by local limb motion. This coupling makes accurate human motion modeling more challenging. To address this issue, this paper proposes frequency decomposed inertial odometry (FDIO). The proposed method first decomposes input IMU signals into low frequency and high frequency components using a Laplacian pyramid. It then adopts a Mamba module to model long range motion information from the low frequency component and uses a multi scale convolution module to extract fine grained local dynamic features from the high frequency component. Experiments on five public PIO datasets show that FDIO achieves an average absolute trajectory error of 3.221~m and an average relative trajectory error of 2.550~m, reducing the errors by 33.3\% and 16.7\% compared with the RoNIN ResNet baseline, respectively. These results validate the effectiveness of the proposed frequency decomposition strategy. To the best of our knowledge, this work is among the first efforts to introduce Mamba and a frequency decomposition architecture into inertial odometry.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2505.04021

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

作者:

Shan Yu↗Yifan Qiao↗Mingyuan Ma↗Yangmin Li↗Shuo Yang↗Xinyuan Tong↗Yang Wang↗Zhiqiang Xie↗Yuwei An↗Shiyi Cao↗Ke Bao↗Deepak Vij↗…

arXiv:2505.04021v3 Announce Type: replace-cross Abstract: Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Analysis of production traces reveals a dynamic bursty-group pattern in which sets of models become active together and shift over time; existing space- and time-sharing approaches lack principled mechanisms to adapt to this variability, forcing trade-offs between SLO adherence and efficiency. We observe that elastic memory allocation can unify spatial and temporal sharing. Based on this insight, we have developed Prism, a memory-centric LLM co-serving framework that applies memory ballooning to reclaim memory across models and support both forms of sharing under a single scheme. Prism's balloon driver, referred to as kvcached, has been open-sourced at https://github.com/ovg-project/kvcached, and deployed in production environments across 10K+ GPUs.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.19215

GUMP-Net: An interpretable model-data-driven intelligent algorithm for multi-class pelvic segmentation

作者:

Liheng Wang↗Yinghui Zhang↗Licheng Zhang↗Hailin Xu↗Qiyong Cao↗Chong Chen↗

Pelvic segmentation is one of the most important and fundamental research problems in precise and intelligent diagnosis and treatment, as well as surgical planning and navigation for pelvic fractures. By combining an improved geodesic active contour model with deep neural networks, we propose GUMP-Net, an interpretable model-data-driven intelligent algorithm for multi-class pelvic segmentation, in which three network modules are designed to constitute the overall segmentation framework together: the object detection module for automatic level set initialization, the edge detector module for learning an anatomy-aware edge detector function and the iteration module for deep level set evolution. Leveraging the advantages of level set representation and deep learning, GUMP-Net shows more accurate, robust and consistent segmentation performance, especially in small training data situation, compared to the state-of-the-art methods. Extensive experiments on pelvic datasets demonstrate the rationality and effectiveness of the proposed algorithm. Further experiments extended to ankle dataset indicate broader applications to other anatomies. The proposed algorithm not only provides an efficient segmentation method for complex fracture reduction, but also gives an interpretable geometric perspective for understanding deep learning segmentation.

阅读与讨论 → 访问原文 →

08.

bioRxiv (Bioinfo) 2026-06-15 DOI: HASH:57ad698aa1778174477aea7bcbed9451

RepGene: Toward a Unified Gene Representation Space Robust to Missing Biological Views

作者:

Hou↗Xia↗Hu↗Qin↗Zhang↗Li↗Fang↗Cao↗

Genes can be described through multiple heterogeneous biological views, including genomic sequence, transcript sequence, protein sequence, textual knowledge, and single-cell expression context, yet existing gene embeddings remain largely modality-specific and difficult to compare or reuse when many views are unavailable. We study a narrower but practically important question: whether pretrained embeddings from these distinct sources can be organized into a shared gene representation interface that remains usable under severe missing-modality conditions. To investigate this question, we introduce RepGene, a lightweight single-branch framework that combines modality adapters, a shared encoder, presence-aware fusion, and self-supervised cross-view objectives to map five biological views into one latent space. Our goal is not to claim a new multimodal learning principle or to establish superiority over all simpler fusion strategies, but to provide an initial technical instantiation for testing whether such a shared interface is feasible in a fixed-feature setting. Under a two-stage protocol in which RepGene is trained self-supervised on frozen upstream embeddings and evaluated by downstream linear probing, we find preliminary evidence that the learned representation is broadly competitive in the full-modality setting and remains informative when only partial modality subsets are observed at inference time. The strongest signal in our study is robustness under missing views: average performance changes are often limited when one modality is removed, and even single-view inference remains non-trivial in the evaluated benchmark regime.These results do not resolve unified biological representation learning, and they should be interpreted in light of incomplete simple-fusion baselines, limited architectural ablation, benchmark dependence, and possible upstream feature exposure. We therefore position RepGene as a feasibility study and a starting point for stronger comparisons, broader benchmarks, and leakage-aware validation.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2408.12099

Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing

作者:

Duoxun Tang↗Yuxin Cao↗Xi Xiao↗Derui Wang↗Sheng Wen↗Tianqing Zhu↗

In service computing, video classification has become fundamental to many intelligent applications. While Deep Neural Networks (DNNs) have demonstrated excellent performance in recognizing video content, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Thus, understanding adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global colors, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks remain relatively underexplored. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three stages. The first stage involves building a style reference set for logos, which can not only make the generated examples more natural, but also carry more target class features in targeted attacks. Then, Reinforcement Learning is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbations are optimized in a step-by-step manner so as to improve the fooling rate. Experimental results indicate that SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods. We believe SLA can raise awareness among the security community about the reliability and security of video classification systems and serve as a memorandum of possible attack methods.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2603.24596

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

作者:

Di Cao↗Dongjie Fu↗Hai Yu↗Siqi Zheng↗Xu Tan↗Tao Jin↗

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capabilities of Speech LLMs to their text-based counterparts. X-OPD enables the Speech LLM to explore its own distribution via on-policy rollouts, where a text-based teacher model evaluates these trajectories and provides token-level feedback, effectively distilling teacher's capabilities into student's multi-modal representations. Extensive experiments across multiple benchmarks demonstrate that X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14691

CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment

作者:

Jiayue Cao↗Zhicong Lu↗Xuehan Sun↗Wei Jia↗Hongling Zheng↗Changyuan Tian↗Zichuan Lin↗Wenqian Lv↗Nayu Liu↗

Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenarios. Existing methods primarily focus on improving the visual coverage of reasoning traces and mitigating visual hallucinations, but underestimate the semantic inconsistency between the reasoning process and the final answer. In this paper, we delve into thinking-answer inconsistency in RLVR for large vision-language models (LVLMs), showing thorough analyses of rollouts collected throughout Group Relative Policy Optimization (GRPO) training process and post-RLVR evaluation outputs that this issue persists during training and remains present during inference. Motivated by the analysis, we propose Consistency-Oriented Reasoning Alignment (CORA), which introduces thinking-answer semantic consistency into RLVR through a lightweight plug-and-play consistency reward model, and further incorporates Hybrid Reward Advantage Splitting (HRAS) to stably coordinate task and consistency optimization. Extensive experiments across representative multimodal reasoning benchmarks and mainstream LVLMs show that CORA improves task performance while effectively mitigating thinking-answer inconsistency, leading to more faithful reasoning traces.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19348

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

作者:

DeepSeek-AI↗Anyi Xu↗Bangcai Lin↗Bing Xue↗Bingxuan Wang↗Bingzheng Xu↗Bochao Wu↗Bowei Zhang↗Chaofan Lin↗Chen Dong↗Chenchen Ling↗Chengda Lu↗…

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models – DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) – both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2602.14211

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

作者:

Xiaojun Jia↗Jie Liao↗Simeng Qin↗Jindong Gu↗Wenqi Ren↗Xiaochun Cao↗Yang Liu↗Philip Torr↗

arXiv:2602.14211v3 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface. A malicious or compromised skill can be repeatedly loaded as trusted guidance and steer downstream tool use. Existing skill-based prompt-injection attacks are often manual and brittle, because explicit malicious instructions are rejected or ignored when they are not aligned with the original workflow. We propose SkillJect, the first automated framework for generating poisoned skills against skill-enabled agent systems. SkillJect uses two coordinated channels. In the artifact channel, it hides the payload inside an auxiliary helper script. In the instruction channel, it rewrites SKILL.md with a front-loaded inducement strategy, placing injected content at the beginning and framing the helper script as a mandatory prerequisite or initialization step. The rewritten instruction explicitly references the helper-script path and provides an executable example command, making the helper appear to be a legitimate setup step before normal skill operations. SkillJect further adopts a closed-loop multi-agent process to improve attack effectiveness. An Attack Agent generates poisoned skills, a Victim Agent executes downstream tasks with the poisoned skill, and an Evaluate Agent inspects execution traces to determine whether the hidden payload was executed. The Attack Agent then uses this feedback to diagnose failure causes and rewrite SKILL.md, while keeping the payload fixed. Experiments across skill-enabled platforms, backend LLMs, and attack categories show that SkillJect substantially outperforms naive direct injection and prior manual skill-injection attacks, highlighting poisoned skills as a persistent threat in reusable skill ecosystems.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11874

AutoMine Solution for AV2 2026 Scenario Mining Challenge

作者:

Songliang Cao↗Jiele Zhao↗Yuru Wang↗Hao Li↗Daqi Liu↗Zehan Zhang↗Fangzhen Li↗Yu Wang↗Yue Zhang↗Bing Wang↗Guang Chen↗Hao Lu↗…

arXiv:2606.11874v1 Announce Type: new Abstract: With the development of autonomous driving systems, mining high-value, safety-critical, and planning-relevant scenarios from large-scale driving logs has become essential for data-driven evaluation. In this paper, we propose AutoMine, a robust self-refining scenario mining method based on LLMs and VLMs. AutoMine uses semantics-preserving prompt augmentation to reduce LLM prompt sensitivity, combines robust trajectory atomic functions with VLM-based functions to handle perception noise and open-world visual cues, and refines generated code through execution feedback from real logs. In the Argoverse 2 Scenario Mining Competition at CVPR 2026, AutoMine achieves a HOTA-Temporal score of 36.38 and a Timestamp BA score of 77.21.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14048

WAM4D: Fast 4D World Action Model via Spatial Register Tokens

作者:

Ying Li↗Xiaobao Wei↗Jiajun Cao↗Hao Wang↗Xiaowei Chi↗Chengyu Bai↗Qianpu Sun↗Jiajun Li↗Xiaojie Zhang↗Jian Tang↗Sirui Han↗Shanghang Zhang↗…

World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video or latent spaces, where visually plausible rollouts miss the 3D spatial constraints and occluded contact geometry required for precise manipulation. While geometric foundation models offer strong priors for recovering dense 3D structure and motion from visual observations, forcing WAMs to predict the dense 4D representation introduces costly geometric decoding and slows down causal action generation. To address the trade-off, we present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts to transfer pretrained geometric priors into a causal video-action transformer, then removes the register branch for lightweight action inference. To prevent non-causal shortcuts, we further design causal mixture attention for the Mixture-of-Transformers (MoT) WAM backbone, defining modality-specific visibility among video, action, and geometry tokens. Comprehensive experiments on RoboTwin 2.0 and challenging real-world manipulation tasks show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11042

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

作者:

Liya Zhu↗Jingzhe Ding↗Jian Zhang↗Jianbo Xue↗Shihao Liang↗Ge Zhang↗Yi Zhu↗Duju Zeng↗Xiang Gao↗Qingshui Gu↗Mailun Gao↗Huimin Che↗…

arXiv:2606.11042v2 Announce Type: replace Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.07591

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

作者:

Wanghan Xu↗Shuo Li↗Tianlin Ye↗Qinglong Cao↗Yixin Chen↗Hengjian Gao↗Yiheng Wang↗Qi Li↗Kun Li↗Sheng Xu↗Shengdu Chai↗Fangchen Yu↗…

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15088

When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting

作者:

Yu Liu↗Zhiwei Yang↗Wenxiao Zhang↗Cong Cao↗Fangfang Yuan↗Kun Peng↗Haimei Qin↗Lei Jiang↗Jin B. Hong↗Hao Peng↗Yanbing Liu↗

A model can learn that the piano piece Für Elise is calm and reflective by listening to the audio or by reading a text description, but does it matter which route that knowledge took when it is later at risk of being forgotten? Forgetting research in multimodal models measures what knowledge is lost under adaptation, yet has not asked whether acquisition route affects how easily that knowledge is forgotten. We call this untested premise the Pathway-Invariant Assumption. Music understanding enables a clean test because a music clip and a canonical text description can be aligned to the same perceptual content, allowing the same knowledge unit to enter a model through listening or reading while the target remains fixed. Across multiple architecturally distinct audio-language models, we observe a consistent asymmetry: text-pathway knowledge is forgotten more than matched audio-pathway knowledge under identical adaptation pressure. To attribute this effect to route rather than confounds, we introduce the Paired Pathway Controlled Protocol (PPCP), a three-phase design that establishes matched pathway baselines, activates both pathways under symmetric supervision on the same knowledge pool, and applies identical forgetting pressure to both pathways. The gap is stable across models and gain-controlled analyses, persists when contradictory overwrite is replaced by correct-label cross-domain learning, remains under single-modality pressure, and is not removed by lightweight replay. Two independent routing-depth controls confirm that the effect is not explained by architectural depth, pointing to input representation as the dominant factor. Under PPCP, our results demonstrate that forgetting is highly route-dependent, establishing acquisition route as a new analytical dimension for forgetting research and multimodal system design.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2603.10444

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

作者:

Hengjie Cao↗Zhendong Huang↗Mengyi Chen↗Yifeng Yang↗Fang Dong↗Anrui Chen↗Ruijun Huang↗Xin Zhang↗Mingzhi Dong↗Yujiang Wang↗Jinlong Hou↗Qin Lv↗…

arXiv:2603.10444v2 Announce Type: replace-cross Abstract: FP4 training promises substantial memory and compute savings for large language models, but remains fragile because blockwise quantization is dictated by extreme activation magnitudes, which inflate dynamic range and compress long-tail signals. We identify a counterintuitive source of this failure: dominant activation outliers are not merely arbitrary sparse events, but are largely induced by a coherent rank-one mean bias, whose direction aligns with the leading anisotropic spectral component. This mean component strengthens during training, is amplified and reshaped by attention and FFN operators, and increasingly dominates top activation magnitudes. Crucially, this discovery reveals that a seemingly complex outlier-suppression problem admits a truly simple solution: isolate the coherent mean before quantization. We therefore propose Averis, a mean-residual splitting quantization method that separates the mean component using only reductions and elementwise subtractions before FP4 quantization. Across Qwen3 0.6B Dense trained on 100B tokens and Qwen3 7B A1.5B MoE trained on 50B tokens, Averis enables robust W4A4G4 FP4 training, reducing BF16 loss gaps to 1.19%/0.81% versus 2.05%/1.10% for NVIDIA's recently released Hadamard-based outlier-smoothing method, while limiting downstream gaps to 0.89/0.71 points. With only 2.20% end-to-end overhead over vanilla NVFP4, about 30% of NVIDIA's Hadamard-based design, Averis provides a hardware-efficient path to stable low-bit LLM training. Complementary to Hadamard, Averis further reduces the Qwen3-0.6B loss and downstream gaps to 0.94% and 0.73 points when combined. Code is available at: https://anonymous.4open.science/r/averis-504D.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2507.15104

AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI

作者:

Qiufeng Li↗Shu Hong↗Tian Lan↗Weidong Cao↗

arXiv:2507.15104v2 Announce Type: replace-cross Abstract: Recent advances in generative AI (GenAI) have shown transformative potential for modern hardware design. However, existing GenAI-driven approaches fall short of enabling large-scale electronic design automation (EDA) due to the proprietary and siloed nature of hardware datasets, which cannot be centralized for model training. Achieving at-scale GenAI-driven EDA, therefore, requires a novel privacy-preserving framework that can leverage distributed data without compromising confidentiality. This work introduces AnalogFed, the first privacy-preserving framework for large-scale analog circuit topology discovery using federated learning (FedL) and GenAI. AnalogFed establishes the feasibility of collaborative analog topology design while addressing key security challenges: it mitigates membership inference attacks (MIAs) through a novel input perturbation strategy based on dummy token injection, and defends against model inversion attacks with customized, efficient homomorphic encryption. Extensive experiments demonstrate AnalogFed's effectiveness and efficiency, achieving strong privacy protection without degrading model utility. This framework lays the foundation for scalable, multi-party collaboration in next-generation hardware design automation with GenAI.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19836

World Engine: Towards the Era of Post-Training for Autonomous Driving

作者:

Tianyu Li↗Li Chen↗Caojun Wang↗Haochen Liu↗Kashyap Chitta↗Zhenjie Yang↗Yuhang Lu↗Naisheng Ye↗Yihang Qiu↗Yufei Wang↗Luoxi Zou↗Jiaxin Peng↗…

Autonomous vehicles must operate safely in the real world, where errors can have severe consequences. Although modern end-to-end driving policies excel in routine scenarios, their reliability is limited by the scarcity of safety-critical ``long-tail'' events in real driving datasets. These rare interactions define the practical safety boundary of the learned policy, yet they are difficult to collect at scale in the real world. Here we show that this fundamental limitation can be addressed by post-training pre-trained driving models on synthesized high-stakes interactions. We introduce World Engine, a generative framework that reconstructs high-fidelity interactive environments from real-world logs and systematically extrapolates them into realistic safety-critical variations. This paradigm enables reinforcement-based post-training to align policies with safety constraints, circumventing the physical risks inherent in real-world exploration. On a public benchmark built on nuPlan, World Engine substantially reduces failures in rare safety-critical scenarios and yields significantly larger gains than scaling pre-training data alone. Furthermore, when deployed on a production-scale autonomous driving system, the resulting policy reduces simulated collisions and demonstrates measurable improvements in on-road testing, showing that post-training on synthesized, safety-critical interactions offers a scalable and effective pathway to safer autonomous driving. The full codebase suite, including training, is released to the public.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15079

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

作者:

Ang Li↗Ben Liu↗Bin Han↗Bin Hu↗Bin Jing↗Binbin Hu↗Bing Li↗Cai Chen↗Caizhi Tang↗Changxin Tian↗Chao Huang↗Chao Zhang↗…

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2509.22020

Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models

作者:

Shilei Cao↗Hehai Lin↗Jiashun Cheng↗Yang Liu↗Guowen Li↗Xuehe Wang↗Juepeng Zheng↗Haoyuan Liang↗Meng Jin↗Chengwei Qin↗Hong Cheng↗Haohuan Fu↗…

arXiv:2509.22020v2 Announce Type: replace Abstract: While recent advances in machine learning have equipped Weather Foundation Models (WFMs) with substantial generalization capabilities across diverse downstream tasks, the escalating computational requirements associated with their expanding scale increasingly hinder practical deployment. Current Parameter-Efficient Fine-Tuning (PEFT) methods, designed for vision or language tasks, fail to address the unique challenges of weather downstream tasks, such as variable heterogeneity, resolution diversity, and spatiotemporal coverage variations, leading to suboptimal performance when applied to WFMs. To bridge this gap, we introduce WeatherPEFT, a novel PEFT framework for WFMs incorporating two synergistic innovations. First, during the forward pass, Task-Adaptive Dynamic Prompting (TADP) dynamically injects the embedding weights within the encoder to the input tokens of the pre-trained backbone via internal and external pattern extraction, enabling context-aware feature recalibration for specific downstream tasks. Furthermore, during backpropagation, Stochastic Fisher-Guided Adaptive Selection (SFAS) not only leverages Fisher information to identify and update the most task-critical parameters, thereby preserving invariant pre-trained knowledge, but also introduces randomness to stabilize the selection. We demonstrate the effectiveness and efficiency of WeatherPEFT on three downstream tasks, where existing PEFT methods show significant gaps versus Full-Tuning, and WeatherPEFT achieves performance parity with Full-Tuning using fewer trainable parameters. The code of this work is available at https://github.com/ShileiCao/WeatherPEFT.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12370

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

作者:

Yucheng Li↗Huiqiang Jiang↗Yang Xu↗Jianxin Yang↗Yi Zhang↗Yizhong Cao↗Yuhao Shen↗Fan Zhou↗Rui Men↗Jianwei Zhang↗An Yang↗Bowen Yu↗…

Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance. To address this bottleneck, we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines. First, we reveal that the MTP acceptance rate is fundamentally bounded by the fluctuation of model entropy, which demonstrates a clear negative linear relationship with the rise of entropy in the RL stage. Second, we show that probabilistic rejection sampling largely alleviates the disturbance introduced by entropy in RL compared to greedy draft sampling. We further identify that the conventional MTP training objectives (cross-entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes multi-step rejection sampling acceptance rate, yielding ~10% acceptance rate improvements, achieving up to 95% acceptance rates and up to 25% extra inference throughput gains across mathematical reasoning, code generation, and agentic tasks. Third, we test various online MTP training strategies during RL and show that pre-RL MTP training with e2e TV loss and rejection sampling achieves a consistent acceptance rate and speedup throughout the entire RL, eliminating the need for costly online MTP updating. We provide extensive experiments and analysis that validate our findings. Experimental results show our method achieves up to 1.8x end-to-end acceleration in async RL training of Qwen3.5, Qwen3.6, and Qwen3.7 models.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.18208

Looped World Models

作者:

Hongyuan Adam Lu↗Z. L. Victor Wei↗Qun Zhang↗Jinrui Zeng↗Bowen Cao↗Lingwei Meng↗Mocheng Li↗Zezhong Wang↗Haonan Yin↗Naifu Xue↗Minyu Chen↗Cenyuan Zhang↗…

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world modelling. Our method iteratively refines latent environment states through a parameter-shared transformer block. This yield up to 100x parameter efficiency over conventional approaches with adaptive computation that automatically scales depth to match the complexity of each prediction step. Orthogonal to scaling model size and training data, LoopWM establishes iterative latent depth as a new scaling axis for world simulation, which might significantly push the community forward.

阅读与讨论 → 访问原文 →