论文广场 - AcademicHub

01.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2606.17960

Average entropy of Bogoliubov-Kubo-Mori random state ensemble

作者:

arXiv:2606.17960v1 Announce Type: cross Abstract: Random states play a foundational role in different branches of modern quantum science. In this work, we study a recently proposed random state ensemble induced from von Neumann entropy through the Bogoliubov-Kubo-Mori (BKM) metric. In particular, we derive an exact yet explicit formula of average entanglement entropy over BKM ensemble. In obtaining the formula, we only make use of properties of normalization constant of the ensemble in the absence of its correlation kernel, contrary to average entropy computation of other ensembles. This new framework paves the way for calculating higher-order cumulants of BKM ensemble beyond the average.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2508.02721

Blueprint First, Model Second: A Framework for Deterministic LLM Workflow

作者:

Libin Qiu ↗Yuhang Ye ↗Zhirong Gao ↗Xide Zou ↗Junfu Chen ↗Ziming Gui ↗Weizhi Huang ↗Xiaobo Xue ↗Wenkai Qiu ↗Kun Zhao ↗

arXiv:2508.02721v2 Announce Type: replace-cross Abstract: While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements. This limitation stems from current architectures that conflate probabilistic, high-level planning with low-level action execution within a single generative process. To address this, we introduce the \textsc{Source Code Agent} framework, a new paradigm built on the ``Blueprint First, Model Second'' philosophy that decouples workflow logic from the generative model. An expert-defined operational procedure is first codified into a source code-based Execution Blueprint, which is then executed by a deterministic engine. The LLM is strategically invoked as a specialized tool to handle bounded, complex sub-tasks within the workflow, but never to decide the workflow's path. We evaluate on the TravelPlanner benchmark for constraint-aware travel planning. The \textsc{Source Code Agent} achieves a 35.56\% final pass rate, a 97.6\% improvement over the state-of-the-art ATLAS baseline (18.00\%) on the same Claude-Sonnet-4 backbone. Critically, it reduces constraint violations by 96.0\% (11 vs 275) while improving execution efficiency by 27.1\% (10.2$\pm$0.7 steps vs 14.0). Two production incident-diagnosis deployments and additional results on ScienceWorld and ALFWorld confirm that the architecture transfers beyond travel planning to procedurally well-defined, constraint-intensive workflows. Our work enables the verifiable and reliable deployment of autonomous agents in applications governed by strict procedural logic.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15123

Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

作者:

Yiwei Chen ↗Lichi Li ↗Kai Cheung ↗Vinny Parla ↗Ganesh Sundaram ↗

arXiv:2606.15123v1 Announce Type: cross Abstract: We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We adopt a data-centric approach, constructing a high-quality dataset via multi-stage preprocessing and introducing a scalable evaluation framework with LLM-as-judge and fine-grained rubrics. Under this unified setup, we benchmark 17 large language models across 8 evaluation criteria, providing systematic insights into their zero-shot capabilities. We further show that a compact 8B open-weight model, when fine-tuned on curated data, achieves over 42.5% improvement in exploit quality and rivals some proprietary models when combined with simple test-time rejection strategies. Our results highlight the importance of data quality, structured supervision, and evaluation design for reliable exploit generation, suggesting that these factors can be as critical as model scale in adapting LLMs to cybersecurity tasks.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12281

CCKS: Consensus-based Communication and Knowledge Sharing

作者:

Jinyuan Zu ↗Xiaowei Lv ↗Yongcai Wang ↗Deying Li ↗Yunjun Han ↗Wenping Chen ↗Fengyi Zhang ↗Naiqi Wu ↗

arXiv:2606.12281v1 Announce Type: cross Abstract: In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among agents. However, current action advising approaches often adhere too much to the teacher's guidance without evaluating teacher-student compatibility, which causes excessive advising, suboptimal stability, and degraded performance. To overcome these challenges, this paper presents a Consensus-based Communication and Knowledge Sharing (CCKS) framework, which allows agents to adopt recommendations based on consensus-derived constraints and to follow the teacher's instructions more smartly. This mechanism enables agents to balance exploration and learning from experienced teachers, improving overall performance. The key is the consensus model construction, for which we propose to employ contrastive learning to construct consensus models based on local observations in the agents' training phase. In action selection, agents score and choose actions based on consensus and shared knowledge. Designed as a plug-and-play solution, CCKS integrates seamlessly with existing DTDE algorithms. Experiments conducted in the Google Research Football environment and the complex StarCraft II Multi-Agent Challenge demonstrate that the integration with CCKS significantly improves cooperation efficiency, learning speed, and overall performance compared with current DTDE baselines. The code is available at https://github.com/yuanxpy/CCKS.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2604.13416

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

作者:

Cheng-You Lu ↗Yi-Shan Hung ↗Wei-Ling Chi ↗Hao-Ping Wang ↗Charlie Li-Ting Tsai ↗Yu-Cheng Chang ↗Yu-Lun Liu ↗Thomas Do ↗Chin-Teng Lin ↗

arXiv:2604.13416v2 Announce Type: replace-cross Abstract: Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a large-scale dataset with clean and cluttered images per scene remains lacking, limiting the development. To address this gap, we introduce DF3DV-1K, a large-scale real-world dataset comprising 1,048 scenes, each providing clean and cluttered image sets for benchmarking. In total, the dataset contains 89,924 images captured using consumer cameras to mimic casual capture, spanning 128 distractor types and 161 scene themes across indoor and outdoor environments. A curated subset of 41 scenes, DF3DV-41, is systematically designed to evaluate the robustness of distractor-free radiance field methods under challenging scenarios. Using DF3DV-1K, we benchmark nine recent distractor-free radiance field methods and 3D Gaussian Splatting, identifying the most robust methods and the most challenging scenarios. Beyond benchmarking, we demonstrate an application of DF3DV-1K by fine-tuning a diffusion-based 2D enhancer to improve radiance field methods, achieving average improvements of 0.96 dB PSNR and 0.057 LPIPS on the held-out set (e.g., DF3DV-41) and the On-the-go dataset. We hope DF3DV-1K facilitates the development of distractor-free vision and promotes progress beyond scene-specific approaches. The dataset and leaderboard are available at https://johnnylu305.github.io/df3dv1k_web/.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12983

Structured Testbench Generation for LLM-Driven HDL Design and Verification-Oriented Data Curation

作者:

En-Ming Huang ↗Yu-Hung Kao ↗Ren-Hao Deng ↗Wei-Po Hsin ↗Yao-Ting Hsieh ↗Cheng Liang ↗Hsiang-Yu Tsou ↗Mu-Chi Chen ↗Yu-Kai Hung ↗Shao-Chun Ho ↗Po-Hsuang Huang ↗Shih-Hao Hung ↗…

arXiv:2606.12983v1 Announce Type: new Abstract: Automated testbench generation has become a critical bottleneck in large language model (LLM)-driven Register Transfer Level (RTL) workflows, where large numbers of candidate designs must be verified rapidly and reliably. Existing prompt-based approaches treat testbench generation as unconstrained code synthesis, yielding stochastic outputs with high token cost, low reproducibility, and insufficient coverage. To address this gap, we present STG, a Structured Testbench Generation framework that exploits the inherent structure of hardware designs to generate deterministic testbenches. As a direct verification tool, STG runs 720x faster than an iterative LLM-based testbench generation flow and higher rate of successful compilation, achieves higher coverage, and reduces false-pass verdicts on incorrect DUTs. STG also helps identify errors in RTL generation benchmarks by exposing faulty benchmark testbenches. As a data curation engine, it is 11x faster than LLM-based filtering on a single CPU core with 127x less energy, and the resulting distilled models provide state-of-the-art performance in our multi-benchmark evaluation. As a test-time scaling oracle, it reduces node count by 14-47\%. Our models are available at https://huggingface.co/collections/AS-SiliconMind/siliconmind-v12.

阅读与讨论 → 访问原文 →

07.

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 →

08.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2605.00873

BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios

作者:

Advait Tilak ↗Jiwon Choi ↗Nazifa Mouli ↗Wei Le ↗

The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods. Existing benchmarks largely overlooked implausible scenarios and do not measure audio-visual alignment. We introduce BRITE, the first framework that unifies (1) implausible prompting, (2) fine-grained assessment of audio-visual consistency, and (3) QA-based interpretable evaluation into a comprehensive T2V benchmark. Unlike fully automated Multimodal LLM-based pipelines, which are prone to hallucination and prompt ambiguity, BRITE guarantees reliability through a rigorous human-in-the-loop protocol for benchmark creation. Evaluating five state-of-the-art models (Sora 2, Veo 3.1, Runway Gen4.5, Pixverse V5.5, and Qwen3Max), we reveal a critical performance gap: while models excel at static object composition, they exhibit significant degradation in object-action binding and audio-visual synchronization. Our framework offers the community a reliable, interpretable benchmark and evaluation framework that can detect and locate limitations in the next generation of T2V models, especially for off-manifold prompts

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12407

How Seemingly Inconsequential Design Choices Dictate Performance of LLMs in Pathology

作者:

Kian R. Weihrauch ↗Thomas A. Buckley ↗William Lotter ↗Arjun K. Manrai ↗

General-purpose large language models (LLMs) are routinely used as baselines when evaluating specialized pathology models on whole-slide images (WSIs). Because WSIs exceed contemporary model context limits, LLM baselines routinely use small, high-magnification patches processed independently via majority voting, without systematic evaluation of seemingly inconsequential design choices such as patch size, patch count, and magnification. Generalist LLMs have consistently underperformed specialized systems, reinforcing the perception that domain-specific training or architectural adaptation is necessary for pathology tasks involving WSIs. Here, we conduct a systematic factorial analysis of four input design factors: inference mode, patch size, magnification, and patch count. We demonstrate that prior studies have overstated the gap between specialized models and general-purpose LLMs by choosing non-optimized input configurations. On the MultiPathQA benchmark, switching to a single balanced configuration (large patches at lower magnification, processed jointly) raises GPT-5 from 15.1% to 39.5% on cancer-type classification (TCGA) and from 38.1% to 62.9% on organ classification (GTEx). Per-task optimization yields further gains up to 43.9% (TCGA) and 71.6% (GTEx). The same configuration generalizes to two other models and to a fully held-out CPTAC cohort, where it improves Gemini 3 Flash by 23.4 percentage points without any task-specific tuning.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12708

AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages

作者:

Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies (SUD) framework, our community-led effort provides high-quality, native-speaker verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2603.00610

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

作者:

Yinghao Ma ↗Haiwen Xia ↗Hewei Gao ↗Weixiong Chen ↗Yuxin Ye ↗Yuchen Yang ↗Sungkyun Chang ↗Mingshuo Ding ↗Yizhi Li ↗Ruibin Yuan ↗Simon Dixon ↗Emmanouil Benetos ↗…

arXiv:2603.00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgment scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. Code is available at GitHub (https://github.com/Haiwen-Xia/CMI-RewardBench). Model weights: CMI-RM (https://huggingface.co/HaiwenXia/CMI-RM). Datasets: CMI-Pref-Pseudo (https://huggingface.co/datasets/HaiwenXia/cmi-pref-pseudo) and CMI-Pref (https://huggingface.co/datasets/HaiwenXia/cmi-pref)

阅读与讨论 → 访问原文 →

12.

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 →

13.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18837

Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems

作者:

Hehai Lin ↗Qi Yang ↗Chengwei Qin ↗

arXiv:2606.18837v1 Announce Type: cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention. Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience. Conversely, Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models, and is hard to scale to large frontier LLMs. To bridge this gap, we propose Skill-MAS, a novel third path that decouples experience retention from parametric updates by conceptualizing the high-level orchestration capability as an evolvable Meta-Skill. Skill-MAS refines this architectural knowledge through a closed optimization loop: (1) Multi-Trajectory Rollout samples a behavioral distribution for each task under the current Meta-Skill; and (2) Selective Reflection adaptively selects priority tasks and applies hierarchical contrastive analysis to distill systemic experience into generalizable, strategy-level principles. Extensive experiments across four complex benchmarks and four distinct LLMs demonstrate that Skill-MAS not only achieves remarkable performance gains but also maintains a favorable cost-performance trade-off. Further analysis reveals that the evolved Meta-Skills are highly robust and exhibit strong transferability across unseen tasks and different LLMs.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12736

Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

作者:

Tianyu Liu ↗Allen Xin Wang ↗Antonia Panescu ↗Lisa Xinyi Chen ↗Wenxin Long ↗Xinyu Wei ↗Yueqian Jing ↗Ziyao Zeng ↗Jihang Chen ↗Sihan Jiang ↗Ziqing Wang ↗Siyi Gu ↗…

arXiv:2606.12736v1 Announce Type: new Abstract: AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchmarks for AI agents rarely capture the complexity, heterogeneity, and extended reasoning required by scientific work, whereas benchmarks for scientific tasks often reduce research to static, direct problems and provide limited support for interactive evaluation. Here, we introduce SciAgentArena, a systematic benchmark for evaluating AI agents in real-world scientific research scenarios drawn from emerging needs across multiple domains. SciAgentArena comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents. Using this benchmark, we find that current agents can contribute effectively to well-specified data-analysis workflows, particularly when the task structure and evaluation criteria are clear. However, their performance remains uneven across scientific contexts: agents struggle to generate genuinely novel insights, sustain self-directed exploration, and formulate robust solutions for open-ended research questions. We further characterize common failure modes across agents and identify opportunities for improving their reliability, autonomy, and scientific reasoning. Together, SciAgentArena provides a practical framework for measuring progress in AI agents for science and for guiding the design of future agents capable of addressing complex scientific challenges. Full codes, tasks, and datasets can be accessed via this link: https://sciagentarena.github.io/.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2508.09459

RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization

作者:

Wen Huang ↗Jiarui Yang ↗Tao Dai ↗Jiawei Li ↗Shaoxiong Zhan ↗Bin Wang ↗Shu-Tao Xia ↗

Visual manipulation localization (VML) aims to identify tampered regions in images and videos, a task that has become increasingly challenging with the rise of advanced editing tools. Existing methods face two central issues. The first is resolution diversity. Resizing or padding can distort subtle forensic cues and introduce unnecessary computational cost. The second is the difficulty of extending spatial models for images to spatio-temporal inputs in videos, which often results in maintaining separate architectures for the two data types. To address these challenges, we propose RelayFormer, a unified framework that adapts to varying resolutions and naturally handles both static and temporal visual data. RelayFormer partitions inputs into fixed-size sub-images and introduces Global Local Relay (GLR) tokens that propagate structured context through a relay-based attention mechanism. This design enables efficient exchange of global cues, such as semantic or temporal consistency, while preserving fine-grained manipulation artifacts. Unlike prior approaches that depend on uniform resizing or sparse attention, RelayFormer scales to variable resolutions and video sequences with minimal overhead. Experiments across diverse benchmarks demonstrate superior performance and strong efficiency, combining resolution adaptivity without interpolation or excessive padding, unified processing for images and videos, and a favorable balance between accuracy and computational cost. Code is available at~\href{https://github.com/WenOOI/RelayFormer}{https://github.com/WenOOI/RelayFormer}.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18672

scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering

作者:

Jinke Wu ↗Yifan Wang ↗Siyu Yi ↗Caiyang Yu ↗Ziyue Qiao ↗Nan Yin ↗Jiancheng Lv ↗Wei Ju ↗

arXiv:2606.18672v1 Announce Type: cross Abstract: Single-cell RNA sequencing (scRNA-seq) serves a pivotal role in characterizing gene expression at the cellular level, enabling the identification of cell types and advancing the understanding of cellular heterogeneity. Despite the significant progress in scRNA-seq data clustering, we argue that current methods always ignore the sparsity and noise, as well as the complex intercellular structural information inherent in scRNA-seq data. Toward this end, in this paper, we propose a novel single-cell RNA-seq clustering framework via deep Siamese Graph Transformer Network (termed scGTN), which explicitly integrates gene expression profile and intercellular structural dependencies for cell clustering. In particular, we formulate scRNA-seq data as a graph and construct two augmented graph views that serve as dual views to capture complementary intercellular information. Then, a Siamese graph transformer network is employed to explicitly incorporate shortest-path information and node-wise distances for capturing richer structural relationships between cells. Finally, we employ an optimal transport strategy to guide the cell clustering in a self-supervised manner. Extensive experiments on multiple benchmark scRNA-seq datasets demonstrate that our scGTN consistently outperforms existing methods. Our code is available at https://github.com/W-RMSL/scGTN.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15734

Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift

作者:

Weihang Su ↗Jiacheng Kang ↗Jingyan Xu ↗Qingyao Ai ↗Jianming Long ↗Hanwen Zhang ↗Bangde Du ↗Xinyuan Cao ↗Min Zhang ↗Yiqun Liu ↗

Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities. Retrieval-augmented generation avoids such parameter drift, yet often lacks the depth of parametric knowledge integration. In this paper, we propose ReGrad (Retrievable Gradients), a new paradigm that treats gradients as retrievable units of knowledge. ReGrad pre-computes document-specific gradients offline, stores them in an indexed Gradient Bank, and retrieves only query-relevant gradients at inference time for temporary weight adaptation. However, raw language-modeling gradients are optimized for token-level document reconstruction rather than for query-driven knowledge use. We therefore introduce a bi-level meta-learning objective that reshapes document-derived gradients into generalizable adaptation signals for downstream tasks. Experiments across general and domain-specific settings show that \textsc{ReGrad} outperforms CPT and RAG baselines, enabling scalable and reversible parametric knowledge injection without accumulating weight drift.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13473

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

作者:

Jiacheng Chen ↗Xinyu Zhang ↗Shunkai Zhang ↗Yanmohan Wang ↗Lin Li ↗Tiancheng Qin ↗Qin Wang ↗Zhengmao Zhu ↗Tianle Li ↗Jingyang Li ↗Zehan Li ↗Binyang Jiang ↗…

We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities – proof generation, proof verification, and critique-conditioned proof repair – using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.10862

LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination

作者:

Taishan Li ↗Jiwen Zhang ↗Siyuan Wang ↗Xuanjing Huang ↗Zhongyu Wei ↗

Vision-Language-Action (VLA) models achieve strong performance on standard manipulation benchmarks, but most evaluations assume that task-relevant objects are fully visible. This assumption often fails in realistic settings, where occlusion makes manipulation partially observable. In this paper, we study scene-induced occlusion as a fundamental challenge for VLA models and introduce LIBERO-Occ, an occlusion-oriented extension of LIBERO. Experiments show that state-of-the-art VLAs suffer substantial performance degradation under occlusion. To address this issue, we propose Viewpoint Imagination (VIM), which generates a complementary view from an occluded primary observation and conditions action prediction on both observed and imagined evidence. VIM improves robustness across task suites, occlusion types, and severity levels without requiring additional cameras at deployment time, suggesting that viewpoint imagination is an promising mechanism for perception completion in partially observable manipulation. Our benchmark and corresponding code are available at: \href{https://github.com/litsh/Libero-Occ}{https://github.com/litsh/Libero-Occ}.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16939

Scalable Circuit Learning for Interpreting Large Language Models

作者:

Naiyu Yin ↗Dennis Wei ↗Tian Gao ↗Amit Dhurandhar ↗Karthikeyan Natesan Ramamurthy ↗Yue Yu ↗

arXiv:2606.16939v1 Announce Type: cross Abstract: A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circuits hard to interpret. Sparse autoencoder (SAE) features alleviate this, but their high dimensionality makes existing intervention-based circuit learning methods computationally prohibitive. We propose CircuitLasso, a scalable circuit-learning approach based on sparse linear regression. CircuitLasso recovers circuits whose structural accuracy matches that of state-of-the-art intervention-based methods on the benchmark data, at a fraction of the computational cost. For interpretability, CircuitLasso efficiently uncovers relationships among SAE features, showing how human-interpretable semantic features propagate through the model and influence its predictions. Finally, we validate the utility of our learned circuits by leveraging their insights to achieve comparable performance at substantially lower cost on a domain-generalization task.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2601.21570

From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence

作者:

Zixing Lei ↗Genjia Liu ↗Yuanshuo Zhang ↗Qipeng Liu ↗Yuzhu Cai ↗Sixiang Chen ↗Jixian Wu ↗Yunhong Wang ↗Weixin Li ↗Chuan Wen ↗Bo Zhao ↗Shanghang Zhang ↗…

arXiv:2601.21570v2 Announce Type: replace Abstract: The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a reliance on labor-intensive manual oversight from intricate reward shaping to hyperparameter tuning across heterogeneous backends. Inspired by LLMs' success in software automation and science discovery, we introduce \textsc{EmboCoach-Bench}, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies. Spanning 32 expert-curated RL and IL tasks, our framework posits executable code as the universal interface. We move beyond static generation to assess a dynamic closed-loop workflow, where agents leverage environment feedback to iteratively draft, debug, and optimize solutions, spanning improvements from physics-informed reward design to policy architectures such as diffusion policies. Extensive evaluations yield three critical insights: (1) autonomous agents can qualitatively surpass human-engineered baselines by 26.5\% in average success rate; (2) agentic workflow with environment feedback effectively strengthens policy development and substantially narrows the performance gap between open-source and proprietary models; and (3) agents exhibit self-correction capabilities for pathological engineering cases, successfully resurrecting task performance from near-total failures through iterative simulation-in-the-loop debugging. Ultimately, this work establishes a foundation for self-evolving embodied intelligence, accelerating the paradigm shift from labor-intensive manual tuning to scalable, autonomous engineering in embodied AI field.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2605.18313

Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering

作者:

Luca Hagen ↗Johanna P. M\"uller ↗Weitong Zhang ↗Mengyun Qiao ↗Bernhard Kainz ↗

Small vision-language models (2-8B) are well-suited for clinical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on-premise inference. However, their limited capacity exacerbates the generation of plausible but incorrect outputs. We extend game-theoretic decoding, previously restricted to text-only, closed-ended NLP tasks, to vision-language models for open-ended Medical VQA. We introduce a semantically aware Wasserstein stopping criterion that replaces lexical order matching, enabling convergence based on semantic consensus among near-synonymous candidate answers and avoiding unnecessary iterations caused by clinically equivalent ranking swaps. On VQA-RAD and PathVQA, we obtain consistent, statistically significant improvements over greedy and discriminative baselines. On VQA-RAD, we improve Qwen3-VL-2B by +3.5 percentage points (p < 0.01), surpassing the greedy 4B model, with similar trends at larger scales. On PathVQA, Gemma-3-4B with BDG matches MedGemma-4B under greedy decoding despite no domain-specific fine-tuning. At accuracy parity with classic BDG, the Wasserstein criterion reduces average convergence iterations by approximately 20%, improving inference efficiency while preserving the game-theoretic equilibrium behaviour. Code is available at https://github.com/luca-hagen/ Wasserstein-BDG-medical-VQA.

阅读与讨论 → 访问原文 →

23.

medRxiv (Medicine) 2026-06-15 DOI: HASH:09934c3d6b0d32a1f47cd32b933431d5

Excitation-Inhibition Balance in Schizophrenia Spectrum Disorders: EEG Criticality Reflects Frontal Metabolites and a Potential Compensatory Mechanism

作者:

Hasanaj ↗Kallweit ↗M. S ↗Karsli ↗Meisinger ↗Boudriot ↗Roell ↗Melcher ↗Vural ↗Schulz ↗Klimas ↗Schmoelz ↗…

Background The excitation-inhibition (E-I) balance is essential for normal brain functioning, while deviations from this balance have been implicated in several psychiatric disorders. However, the extent to which electroencephalography (EEG) and proton magnetic resonance spectroscopy (1H-MRS) E-I markers are altered in schizophrenia spectrum disorders (SSD), how they converge across modalities, and how they relate to cognitive performance and clinical symptoms remain insufficiently characterized. Methods We recruited 111 healthy controls (HC) and 113 individuals with SSD. All participants underwent resting-state EEG and 1H-MRS. Metabolites were measured either in the anterior cingulate cortex (ACC; NSSD = 63, NHC = 58) or in the left dorsolateral prefrontal cortex (lDLPFC; NSSD = 50, NHC = 53), from which gamma-aminobutyric acid (GABA), glutamate + glutamine (Glx), and the Glx/GABA ratio were extracted. Extracted EEG E-I markers included oscillatory activity, aperiodic activity, functional E-I, microstates, multiscale entropy, and neuronal avalanche criticality. Results MRS results showed no group differences in GABA, Glx, or the Glx/GABA ratio. In contrast, most EEG-derived E-I markers indicated increased cortical inhibition in SSD, including steeper aperiodic exponents, prolonged microstate durations, and greater prevalence of subcritical states. However, functional E-I showed a divergent pattern, suggesting balanced dynamics in SSD and relatively inhibition-weighted dynamics in HC. Across groups, higher ACC and lDLPFC GABA predicted a lower kappa index, whereas a higher lDLPFC Glx/GABA ratio was associated with a higher kappa index. In SSD, reduced avalanche criticality was associated with better cognition and less severe symptoms. Conclusion Several EEG-derived E-I proxies, but not MRS measures, indicate an increased cortical inhibition in SSD. Criticality indices best capture frontal neurochemical metabolites and improvements in clinical symptoms, potentially reflecting inhibitory compensation mechanisms in SSD.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2604.28185

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

作者:

Keming Wu ↗Zuhao Yang ↗Kaichen Zhang ↗Shizun Wang ↗Haowei Zhu ↗Sicong Leng ↗Zhongyu Yang ↗Qijie Wang ↗Sudong Wang ↗Ziting Wang ↗Zili Wang ↗Hui Zhang ↗…

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appearance synthesis toward intelligent visual generation: plausible visuals grounded in structure, dynamics, domain knowledge, and causal relations. To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. We analyze key technical drivers, including flow matching, unified understanding-and-generation models, improved visual representations, post-training, reward modeling, data curation, synthetic data distillation, and sampling acceleration. We further show that current evaluations often overestimate progress by emphasizing perceptual quality while missing structural, temporal, and causal failures. By combining benchmark review, in-the-wild stress tests, and expert-constrained case studies, this roadmap offers a capability-centered lens for understanding, evaluating, and advancing the next generation of intelligent visual generation systems.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12199

Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation

作者:

Zhen Ye ↗Xu Tan ↗Yiming Li ↗Guangyan Zhang ↗Chimin Chan ↗Haohe Liu ↗Zhengxi Liu ↗Hongzhan Lin ↗Zheqi Dai ↗Xinshen Zhang ↗Peiwen Sun ↗Qiuqiang Kong ↗…

Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute part of this modality gap to a temporal-granularity mismatch: speech tokens are temporally redundant and far longer than text under matched semantics, diluting per-token semantic density and weakening text-native reasoning dynamics. We study speech token design as a representation selection problem and sweep frame rates under a frozen LLM backbone with a fixed information rate. To make low frame rates feasible, we introduce factorized FSQ and a lightweight non-autoregressive audio LM head, scaling capacity to nearly 300\,bits/frame without sacrificing efficient prediction. With the bottleneck removed, we sweep frame rates (50$\rightarrow$2.08\,Hz) and alignment depth, and observe a consistent best regime for speech QA at 4.17\,Hz with intermediate-layer representation alignment.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络