跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 10:17 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 12:20 — 2026-11-08 12:20（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 10:17最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

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

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 33 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 10:15（北京时间）
版本更新 · v3arXiv:2507.19684

CoMPAS3D: A Dataset and Benchmark for Interactive Motion

Bermet Burkanova, Yasaman Etesam, Payam Jome Yazdian, Trinity Evans, Chuxuan Zhang, Zoe Stanley, Paige Tuttösí, Angelica Lim

原文摘要

Socially interactive humanoids aim to interact with humans through their bodies, adapting in real time to a partner's movement, intent, and abilities. This requires models that understand both how bodies move and what their movements mean. Yet, existing evaluation frameworks for interactive motion generation do not assess whether generated reactive motions are valid or appropriate within a shared movement vocabulary. Existing frameworks rely on kinematic metrics such as FID and beat alignment that cannot capture this semantic property, while improvised interaction datasets lack fine-grained move annotations. Inspired by computational evaluations of games such as Go and Chess, we propose Salsa as an embodied interaction evaluation domain. Salsa is interactive, dyadic, and governed by a move vocabulary and community-validated judging criteria covering timing, musicality, technique, difficulty, partnering, and originality. We present CoMPAS3D, a motion capture dataset of improvised partner salsa dance and an evaluation framework covering kinematic quality, two objective metrics (move legibility and proficiency appropriateness), and six competition-based subjective dimensions. The dataset comprises 3 hours of improvisation by 18 dancers spanning beginner, intermediate, and professional skill levels, with over 2,800 expert-annotated segments covering move types, execution errors, and stylistic elements. We define three benchmark tasks: move classification, proficiency estimation, and follower generation. Fine-tuned vision-language models perform well on ground-truth sequences and correlate with subjective expert judgments, suggesting their promise as measurement tools. Applied to Duolando and InterGen, our objective metrics reveal a large gap between ground-truth and generated dances, corroborated by expert human evaluations across six judging dimensions.

cs.LG · cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.13373

PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation

Chuxuan Huang, Zhanxiang Cao, Tianyue Zhan, Haoyang Li, Yang Zhang, Liyun Yan, Chenlin Ming, Keqi Zhu 等 17 位作者

原文摘要

Translating language into humanoid motion requires coordinating body parts, determining motion duration, and producing references suitable for robot execution. We introduce PartiGen, a part-aware latent diffusion framework that incorporates anatomical structure into a shared whole-body motion representation. Part-specific attention processes anatomically masked frame features, and its outputs are fused to combine local limb information with whole-body context. Conditioned on text and motion history, the model generates motion primitives autoregressively. Forward-kinematics supervision encourages kinematic consistency, while a learned end-of-sequence predictor selects a frame-level endpoint after generation. On HumanML3D retargeted to the Unitree G1, PartiGen achieves a segment-level FID of 3.165, a 16.8% reduction over TextOp, and improves R@1 by 1.4 percentage points. In the duration study with 16-frame primitives, endpoint prediction reduces mean absolute duration error from 12.471 to 3.080 frames compared with a fixed-length cutoff. We further evaluate robot execution using a pretrained, frozen GRIT tracker: 409 of 500 generated references (81.8%) pass the posture-based stability screen in MuJoCo. Following simulation screening and manual selection, 26 of 27 attempted motions are judged successful on the real G1.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.06113

Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback

Huaisong Zhang, Hao Yu, Yuxuan Zhang, Jiahe Wang, Xinrui Chen, Haoxiang Cao, Feng Lu, Wendong Zhang 等 10 位作者

原文摘要

Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality. While recent dense-feedback methods move beyond scalar supervision, their heatmap-centric representations still formulate diagnosis as pixel-field regression, making it difficult to localize variable-cardinality defects and bind semantic reasons to individual failures. To address this representation bottleneck, we propose Structured Defect Grounding (SDG), which casts T2I diagnosis as structured set prediction by modeling each defect as a (location, type, reason, importance) tuple. To make this formulation trainable and measurable, we introduce SDG-30K, a 30K-image dataset with box-grounded annotations across four modern T2I generators, together with a dedicated evaluation protocol, SDG-Eval. Building on this structured representation, we further present a diagnosis-to-alignment framework in which a Vision-Language Model (VLM) serves as the SDG detector, and BoxFlow-GRPO converts predicted defect sets into box-derived, importance-weighted spatial rewards for diffusion model alignment. Extensive experiments show that our SDG detector outperforms leading proprietary VLMs on structured defect grounding, while SDG-guided rewards consistently improve T2I alignment and support localized image refinement. These results establish SDG as a unified, instance-level interface for diagnosing, evaluating, and enhancing modern generative models.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07473

Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting

Zheng Wang, Kaixuan Zhang, Xiaonan Lu, Wanfang Chen

原文摘要

In time-series forecasting, rollout errors are not merely one-step fitting discrepancies: once fed back into the evolving state, they can perturb future predictions. We formalize this effect through local rollout consistency, which compares the next prediction produced under teacher forcing with that produced under free running. In principle, this consistency can be enforced directly by tracking the residual-induced perturbation of the next state. In practice, however, the residual-to-state alignment operator is often difficult to design when the input state and output block have different dimensions, heterogeneous components, or architecture-dependent layouts. We therefore use a first-order local surrogate that penalizes the Jacobian-vector product of the predictor along the actual feedback perturbation, suppressing precisely the directions through which self-generated errors remain visible to future predictions. We further give the same loss a geometric interpretation near a predictive manifold: by controlling residual-induced directions that probe the normal bundle, the objective yields theoretical conditions under which free-running trajectories remain inside a stability tube around the manifold. Experiments on time series forecasting tasks support this view, showing that the proposed regularization improves predictive accuracy. More broadly, our results suggest a training principle for time-series forecasters and sequential predictors: a model should not only make small one-step errors, but also learn not to let its own errors echo into the future. Code is available at https://github.com/Wangzzzzzzzz/Echoes-Of-Error.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07149

FastAFD: When Does Attention-FFN Disaggregation Pay on Rack-Scale NVLink?

Yichao Fu, Yuxuan Zhang, Minshen Zhang, Ruitian Wang, Junda Chen, Hao Zhang

原文摘要

Attention-FFN disaggregation (AFD) separates attention from the experts of a mixture-of-experts (MoE) model and has been reported to raise decode throughput over colocated serving. Whether this advantage holds on rack-scale NVLink systems such as GB200 NVL72 remains unclear: prior results were obtained on other hardware, against narrower colocated baselines, or with analytical models, whereas production engines serve large MoE models on these systems with wide expert parallelism (wide EP). We build and tune FastAFD, an AFD engine for GB200 NVL72 that overlaps the MoE of one microbatch with the attention of the other, and compare it against the best vLLM wide EP setting. Experiments show that AFD has a throughput advantage of up to 1.17x over wide EP on Qwen3 and 1.16x on Qwen3.5, and matches it on MiniMax-M2.5. We derive an analytical model that predicts AFD throughput within 3% using only profiles of colocated vLLM, telling whether switching to AFD would pay off before deploying it. The model yields a concise insight: AFD's speedup factors into a batch gain (larger batches, since attention GPUs hold no expert weights), an overlap gain (shorter steps, since the MoE runs on the expert GPUs behind attention), and a disaggregation cost (the GPUs given to experts). AFD has the advantage when the two gains outweigh the cost. This view explains which models benefit from AFD, and shows that speculative decoding helps light-expert models most, where the enlarged overlap gain outweighs the larger disaggregation cost and adds a further 8% to AFD's advantage over wide EP. Looking ahead, serving the experts on accelerators that keep their weights in on-chip SRAM, such as the Groq LPX accelerators paired with Vera Rubin NVL72, would remove most of the disaggregation cost, raising the ideal speedup to 2.48x with speculative decoding. FastAFD is open source at https://github.com/hao-ai-lab/FastAFD.

cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07081

Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving

Kaixuan Zhang, Zhipeng Xiong, Minxian Li, Mingwu Ren, Xiatian Zhu

原文摘要

Multi-perspective-camera systems are widely adopted since they provide broad visual coverage for autonomous driving, motivating the synthesis of a unified wide view from spatially separated observations. In this work, we formulate wide view synthesis (WVS), which aims to synthesize a geometrically consistent wide view at a specified virtual viewpoint from multiple perspective cameras. Unlike conventional image stitching, WVS requires reasoning about 3D geometry and visibility to handle depth-dependent parallax and occlusions arising from spatially separated camera centers. While vanilla 3D Gaussian Splatting (3DGS) enables high-fidelity view synthesis, its reliance on per-scene optimization limits its applicability to driving scenes. Furthermore, WVS introduces additional challenges, *e.g.*, peripheral stretching under perspective projection and photometric inconsistencies across cameras. To address these challenges, we propose **Wide-View Gaussian Splatting (WV-GS)**, a feed-forward Gaussian-splatting framework that synthesizes wide views without per-scene optimization. Specifically, we introduce Piecewise Perspective Rendering (PPR) to mitigate peripheral stretching through local perspective projections sharing a common camera center, and Spatial Affine Photometric Modeling (SAPM) to account for camera-dependent photometric variations during training. We further introduce **WideDrive**, a synthetic benchmark providing dense ground-truth wide views and adapt a LiDAR-projected sparse-reference protocol to real-world datasets. Extensive experiments on multiple datasets demonstrate the effectiveness of WV-GS for WVS. Dataset and code will be publicly released.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06856

LongBanana：面向长上下文多参考图像合成的专家验证基准

LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis

Haoxiang Cao, Yuxuan Zhang, Penghui Du, Bo Li, Jiajiong Cao, Yingying Fan, Zimeng Wu, Yifu Luo 等 19 位作者

AI 速读 基于摘要

作者提出 LongBanana，一个由专家设计并验证的长上下文多参考图像合成基准，并配套 LongBanana-Gen 智能体框架来评测和提升这类生成任务。

cs.CV · cs.CL

arXiv ↗PDF ↗
查看原文摘要

We introduce LongBanana, to our knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation. The task requires retrieving dispersed visual evidence, rejecting distractors, binding entities and relations, and composing one coherent final image from multiple references. LongBanana contains 90 carefully designed tasks organized by a 3-by-3 taxonomy; each task includes about 32 reference images, 20 constraints, and 50 evaluation items, yielding 4,670 expert-specified atomic evaluation items in total. Its graph-grounded evaluation design instantiates each task with reference images and an entity-relation graph, then converts node, edge, and whole-graph obligations into checklist items for Content Fidelity, Relational Binding, and Global Constraint Satisfaction. Reviewed expert labels include a 15% double-labeled subset with 89.4% exact agreement and 0.83 quadratic weighted kappa. We further introduce LongBanana-Gen, an agent-harness framework for long-horizon image generation; experiments show that minimal agent harnesses improve over direct generation, while a ReAct-Plan-Exec-Reflect (RPR) workflow yields harness-dependent gains by strengthening evidence grounding and repair. Together, LongBanana provides an auditable testbed for measuring dense visual evidence use and a shared target for developing stronger agent-driven image-generation systems. Code and data are available at the project page: https://long-banana.com/.

版本更新 · v3arXiv:2602.12575

Discovering Semantic Structures in Psychological Scales: A Response-Free Front-End to Efficient Simplification

Bo Wang, Yuxuan Zhang, Yueqin Hu, Hanchao Hou, Kaiping Peng, Shiguang Ni

原文摘要

Psychological scale refinement traditionally relies on response-based methods such as factor analysis, item response theory, and network psychometrics to uncover latent constructs and optimize item composition. Although rigorous, these approaches require large samples and may be constrained by data availability and cross-cultural comparability. Recent advances in natural language processing suggest that the wording of scale items contains construct-relevant semantic organization, offering a complementary response-free perspective. We introduce a topic-modeling framework that operationalizes item-level semantic structure for systematic scale simplification. Items are encoded using contextual sentence embeddings and grouped through density-based clustering to identify semantic topics without predefining their number. Within each cluster, class-based term weighting identifies representative keywords that summarize each topic and support an interpretable semantic pre-structure of the item pool. Semantically related clusters are hierarchically merged, and representative items are selected using structure-aware membership criteria within an integrated reduction pipeline. We evaluated the framework on three widely used instruments: DASS, IPIP, and EPOCH, covering negative affect, personality traits, and well-being. Results showed that the identified semantic topics often formed factor-like groupings aligned with established constructs. Representative items selected through semantic membership probabilities reduced item counts by 60.5% on average while maintaining acceptable psychometric properties and preserving factor correlation patterns. Our framework formalizes semantic topic structure as an inspectable front-end for scale construction and simplification. To facilitate adoption, we provide a visualization-supported tool enabling one-click semantic analysis and structured simplification.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05951

Community Search under Member-Specific Tolerances

Yanghao Liu, Fangda Guo, Yuxuan Zhang, Xueqi Cheng

原文摘要

We study community search when each vertex has its own tolerance for differences in position. For positions such as opinions or homes, a latitude-consistent community (LCC) contains the query vertex, is connected, has minimum degree at least k, and bounds its diameter by the smallest member tolerance. Motivated by social judgment theory, the bound exactly characterizes persistent acceptance of every interaction in a closed group under bounded-confidence dynamics with arbitrary positive weights. It also prevents rejection under social-judgment dynamics, whereas natural relaxations preserve neither guarantee. Finding a maximum LCC is NP-hard even in the plane, and with unbounded dimension, deciding whether an LCC exists is NP-complete for every fixed k >= 2. LatSweep turns the coupled bound into a sweep over the smallest tolerance, yielding two feasible heuristics, a (1,2)-bicriteria approximation and an exact branch-and-bound algorithm. Across eight graphs with up to 1.8 billion edges, the exact algorithm proves optimality on all but 9 of 3,700 efficiency queries and usually certifies absence within microseconds when no LCC exists. Its branch-and-bound solver proves more queries than a reimplemented maximum-(k,r)-core algorithm, a mixed-integer program and CP-SAT. In simulations, uneven influence disrupts initially accepted interactions in pairwise groups. Outside ties invalidate the guarantee for many real groups. On two location-based networks, tolerance-agnostic groups often place another member's home beyond a member's estimated travel radius; comparisons with spatial communities of the same size detect no co-visit loss from enforcing every member's tolerance.

cs.SI · cs.CC · cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.35107

DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery

Yulong Li, Rong Xia, Yuxuan Zhang, Jianxu Chen, Xiwei Liu, Haochen Xue, Maosheng Li, Yuhang Liu 等 15 位作者

原文摘要

We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.

cs.AI · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04259

ReuseGR: Offline--Online Decoupled Generative Retrieval via Adaptive Prefix Reuse

Xujing Wang, Yufeng Chen, Boxuan Zhang, Chao Wei, Cai Xu, Jie Zhao, Weiru Zhang, Wei Zhao 等 9 位作者

原文摘要

Larger generative retrieval models can improve retrieval quality, but their decoding cost makes low-latency serving difficult. When different users submit the same query, generating complete Semantic IDs (SIDs) for every request repeats computation, while their interaction histories call for different results. The challenge is to reuse large-model computation across requests while keeping retrieval personalized. We propose \textbf{ReuseGR}, which separates query-level candidate planning from request-level personalized completion. A 7B offline planner generates SID prefix sets shared across requests with the same query. A 0.5B online model uses each request's history to select prefixes and generate the remaining tokens. ReuseCut chooses a cache depth for each query based on historical coverage, balancing computation reuse and candidate coverage. To strengthen online completion, we transfer 7B suffix-scoring knowledge to 0.5B through path-level knowledge distillation (Path KD). BudgetCut then selects scored branches to improve final top-100 recall under a fixed branch budget. Its selection policy is initialized by on-policy distillation (OPD) and refined through group-relative policy optimization (GRPO). On an industrial search-advertising dataset with approximately 2M query--item records and 3.38M catalog items, ReuseGR improves query-level HR@100 by 3.83 percentage points and reduces mean online latency by 38.9\% relative to an all-online 0.5B baseline when prefixes are prepared. It achieves HR@100 comparable to an all-online 7B baseline with 57.7\% lower online latency. A 14-day user-level online A/B test against the 0.5B baseline shows relative gains of 0.93\% in click-through rate and 1.05\% in revenue per thousand requests.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04241

AceAction-5M: Hierarchical Goals for Generalist Action Learning Across 3D Game Worlds

Kailing Li, Ruoxuan Zhang, Zheyuan Zhou, Boyang Chu, Yingshan Lei, Hongxia Xie, Liang Du, Zixun Sun

原文摘要

Video games provide a practical setting for collecting vision-language-action (VLA) data, whose acquisition in physical environments is costly. Existing datasets, however, remain limited by restricted game coverage, sparse language supervision, or temporal hierarchies that do not necessarily reflect changes in task objectives. We introduce AceAction, a dataset of human gameplay across multiple 3D games for learning skill composition and subgoal transitions. AceAction organizes demonstrations around complete tasks, linking overall instructions, ordered subgoals, and local skill instructions to temporally aligned visual observations and keyboard-and-mouse actions. To construct these annotations, we develop a vision-language model pipeline that identifies subgoals from changes in objectives or interaction targets, anchors navigation goals to visually recognizable waypoints, and composes adjacent subgoals into task instructions. The resulting demonstrations cover navigation, reconnaissance, combat, interaction, and recovery, with explicit stage boundaries that connect task progression to fine-grained control. We assess annotation quality through model-based verification and human inspection. An audit of 500 trajectories yields a 95.8% pass rate across independent reviewer assessments. AceAction provides a data foundation for studying how agents execute, combine, and switch skills to follow complex instructions in dynamic game environments.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03634

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

Zhaoyang Wang, Qianhui Wu, Boyu Gou, Demi Wang, Jiacheng Zhang, Peichun Hua, Qize Li, Shi Qiu 等 57 位作者

原文摘要

GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and dockerized website environments that faithfully reconstruct the visual interfaces, content, and functional workflows of real-world web services under deterministic control. We build WebHarbor through task-driven human-agent collaboration, where environments evolve as new tasks expand their functional scope, coding agents implement the required changes, and human contributors audit visual fidelity, functional correctness, and task validity. The resulting suite comprises 3,518 tasks spanning multi-step and post-authentication workflows, where existing works often fail to cover. Beyond reliable evaluation, WebHarbor provides high-fidelity synthetic web environments for cost-efficient reinforcement learning (RL). We demonstrate that a Qwen 4B-level GUI agent trained with RL in WebHarbor generalizes to unseen tasks and performs competitively with leading open-source GUI web agents across four benchmarks. The code and data are publicly available at https://github.com/aiming-lab/WebHarbor.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02816

Discovering hierarchical governing equations for community-structured complex network dynamics with LLM agents

Jinlei Zhang, Zixuan Zhang, Hao Qiu, Feng Chen, Jiateng Yin, Xiaoyong Yan, Xiaolei Ma, Hao Sun 等 11 位作者

原文摘要

Governing equations provide an interpretable description of the mechanisms underlying complex network dynamics, yet their discovery from observational data remains challenging when shared community-level dynamics coexist with individual-level variations and the relevant functional structures may be absent from the initial candidate library or not explicitly specified in advance. Here we formulate this task as a hierarchical law-discovery problem and introduce SAGE, a large language model-guided self-reflective agent framework for discovering community-shared governing laws and individual-specific dynamical variations. SAGE organizes equation discovery into an iterative Library-Discovery-Review process that first identifies shared community-level structures and then resolves node-specific residual dynamics, while adaptively refining the candidate space to introduce missing dynamical terms when needed. This hierarchical and interpretable formulation enables SAGE to distinguish shared community-level dynamics from individual-level variations and to reveal the mechanisms underlying complex network dynamics. Across two synthetic networks and four real-world networks spanning mobile communication, brain electrophysiology, power grids and urban rail transit, SAGE recovers compact and interpretable governing equations, reproduces observed system dynamics and outperforms representative equation-discovery baselines. The framework remains robust under incomplete observations and can transfer community-level governing laws to nodes with entirely missing observations. These results establish a hierarchical and adaptive approach for disentangling shared and individual dynamical mechanisms in community-structured complex networks.

physics.soc-ph · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.15659

Harnessing Plastic Deformation for Continuous Passive Stability in Soft Grippers

Junlong Xiao, Yaoqiang Pan, Xuan Zhang, Michael Yu Wang, Chao Chen

原文摘要

Soft robots offer compliance and adaptability for interacting with complex environments, but their low structural stiffness can compromise stability under dynamic disturbances. Here, we present a continuously stable structure through plastic deformation (CSSPD), a hybrid metal-elastomer architecture that enables passive shape retention without continuous energy input. By deliberately exploiting plastic deformation in a kirigami-patterned metal layer, CSSPD establishes new equilibrium configurations while increasing structural stiffness and resistance to dynamic disturbances. A theoretical model is developed to characterize the deformation and stability of the hybrid structure and guide the geometric design of the metal layer. We further introduce a bioinspired paw pad that provides top-side support for enhanced grasp stability and serves as an integrated sensing interface for rapid object acquisition. A telescopic soft pressing mechanism (TSPM) mechanically couples paw-pad motion with tendon actuation. Experiments demonstrate passive holding forces of up to 16 N without continuous energy input, comparable to pneumatic actuation at 0.3 MPa, and stable grasping under pulsed accelerations of up to 400 m/s^2 when combined with pneumatic actuation. Energy-free perching on tree branches further demonstrates the potential of the proposed composite architecture for stable and energy-efficient manipulation.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03743

EvoMemState: Evolving Memory State for Personal Agents

Zhishang Xiang, Yunbo Tang, Zhongqiao Liu, Junkai Chen, Zerui Chen, Qingguo Hu, Yuxuan Zhang, William Grant 等 10 位作者

原文摘要

Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process through fact extraction, organization, updating, and retrieval, but largely maintain memories as independent facts. This fact-centric paradigm may overlook how new facts update, constrain, or conflict with earlier ones, while leaving their applicability, role, and priority for the current request implicit. In this paper, we introduce EvoMemState, a state-centric framework that augments persistent facts with two complementary states: Relational States that capture how facts remain valid and relate to one another as memory evolves, and a Reasoning State that determines how these facts should be applied to the current request. Specifically, EvoMemState consists of three key components: (i) Ontology-Guided Memory State Induction extracts Persistent Facts and constructs Relational States that maintain their validity, scope, and evolving relations. (ii) RL-Based State Evolution internalizes memory-use experience into a policy through reinforcement learning to generate a request-specific Reasoning State. (iii) State-Aware Reasoning then combines the relevant facts with their Relational States and the generated Reasoning State to guide the personal agent. Extensive experiments on long-term dialogue and memory-use benchmarks demonstrate consistent improvements over existing memory systems in retrieval completeness and memory-grounded response accuracy. Our code and implementation details are available at https://github.com/XMUDeepLIT/EvoMemState.git.

cs.IR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02075

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

Lang Mo, Xingxuan Zhang, Qi Wang, Mingchao Hao, Hao Yuan, Chunjing Gan, Wang Lu, Peng Cui

原文摘要

Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner. Language models provide semantic representations of current and historical records, while a general-purpose conditional predictor predicts task-defined targets from the represented evidence. Pretraining supplies reusable inference capability; deployment evidence instantiates problem-specific predictions without updating either model's neural parameters. Tool judgments, candidate preferences, and reasoning assessments share an evidence-and-query interface, with predictions mapped to choices by a decision rule. This architecture establishes complementary sources of agent capability: semantic knowledge acquired through language pretraining and empirical inference acquired through structured-data pretraining. A single frozen LimiX-2 predictor serves all five task categories. With Qwen3.5-27B as the semantic encoder, DPDM raises mean accuracy across 50 benchmarks from 78.80% with few-shot prompting to 84.92% under their respective evaluated history budgets, and reaches 82.33% with identical histories and queries. On ToolPRMBench's BFCL and ToolSandbox tasks, absolute accuracy gains are 34.26% and 28.87%, respectively, at the methods' respective evaluated history budgets. Accuracy improves as history grows. With identical imbalanced histories, mean balanced accuracy improves by an absolute 14.51% across five reasoning-step assessment tasks and four encoders. DPDM makes learning from experience an independently improvable foundation-model capability, creating a shared route for advances in conditional prediction to improve decisions across agent tasks.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.24275

RePolicy: Learning to Select and Apply Safety Policies for Agent Safeguards

Houcheng Jiang, Boxuan Zhang, Qiyong Zhong, Junfeng Fang, Xiang Wang, Xiangnan He

原文摘要

Agent safeguards must determine whether an agent's behavior violates the safety rules of the current task, environment, and user. Because these rules vary across contexts, a safeguard needs to select the relevant policy before judging the behavior. Existing policy-aware safeguards can apply a supplied policy, but generally assume that the correct policy is already known. They therefore do not learn how to select a policy from a library, even though an incorrect choice can lead to an incorrect safety judgment. We introduce RePolicy, a safeguard that jointly learns policy selection and safety assessment. Given an agent trajectory and a set of candidate policies, RePolicy selects the policy that best matches the situation, applies its requirements, and predicts whether the behavior is safe. We construct PolicyTraj-20K, a dataset of more than 20,000 agent trajectories annotated with applicable policies, safety labels, and explanations. We train RePolicy with supervised demonstrations followed by reinforcement learning, while randomizing policy order, identifiers, and distractors to reduce shortcut learning. Across six agent-safety benchmarks and 19 baselines, RePolicy-4B achieves leading overall safety-detection performance and improves policy-selection accuracy. These results show that safeguards can learn which safety requirements to use for assessing agent behavior.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2609.01306

MeshSuite: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering

Kaixuan Zhang, Minxian Li, Mingwu Ren, Xiatian Zhu

原文摘要

Triangle- and mesh-based neural rendering seeks to bridge neural representations and graphics engines through triangle primitives compatible with standard rasterization. Yet existing methods were developed and evaluated under inconsistent settings, with few direct comparisons and little evaluation in graphics engines. We introduce MeshSuite, the first benchmark for systematic evaluation of engine deployment and Non-Engine Render in triangle- and mesh-based neural rendering. MeshSuite evaluates two deployment settings: Standard Deployment, using an opaque mesh pipeline with vertex colors and hardware Z-buffering; and Dedicated Deployment, using method-specific engine implementations to preserve appearance and compositing features. For mesh splatting, we also audit exported surfaces for topological and geometric integrity as downstream graphics assets. Our results show that engine deployment reduces image quality in both settings; among evaluated methods, MeshSplatting degrades least under Standard Deployment. Dedicated Deployment preserves most fidelity at roughly 5-33x the runtime of Standard Deployment across two deployment datasets. For mesh splatting, explicit connectivity and shared indexing remain limited: shared vertex indexing alone guarantees neither manifoldness nor global connectivity. These findings show that rasterizability is only part of graphics readiness and underscore the need to assess engine deployment. Project page: https://x-up-lab.github.io/research/meshsuite.

cs.GR · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38335

Learning a Prior-Data Fitted Network for Graph Foundation Models via Structural Causal Model Priors

Ziwei Zhang, Tianyin Liao, Chunyu Hu, Ge Lan, Nuo Xu, Yi Huang, Qingyun Sun, Xingxuan Zhang 等 10 位作者

原文摘要

Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for learning transferable representations across different graphs and domains. However, existing GFMs face notable limitations, including limited pre-training scale or reliance on aligning with textual information in Large Language Models (LLMs). To overcome these limitations, recent studies have drawn inspiration from prior-data fitted networks (PFNs), which learn from large synthetic datasets and support multi-domain prediction backed by causal learning. However, existing graph PFNs encounter severe difficulties in modeling causal relationships within and across node and edge sets, generating diverse graph structures, and designing suitable architectures that can learn from complex synthetic datasets. To address these challenges, we propose **GSCM-PFN** (Graph SCM-based Prior-Data Fitted Network), a graph PFN pre-trained on synthetic data generated from an SCM-based prior that jointly models nodes and graph topology. Specifically, we (1) design a joint feature-edge-label structural causal model (SCM) to guide synthetic graph generation and capture causal relationships within and across node and edge sets; (2) introduce prior-guided node-edge dependency modeling to instantiate diverse graph generation strategies, and prove that our SCM-based generation prior is more expressive than existing priors; and (3) propose a feature-permutation-invariant dual-path graph network with theoretical guarantees for learning from diverse synthetic graphs. Experiments on 23 real-world benchmarks show that GSCM-PFN outperforms both conventional GFMs and PFN-based GFMs, without utilizing real-world graph data for pre-training. Code: https://anonymous.4open.science/r/GSCM-PFN-A3A3/

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2403.15524

PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators

Renzhe Xu, Haotian Wang, Xingxuan Zhang, Bo Li, Peng Cui

原文摘要

In this paper, we present the Proportional Payoff Allocation Game (PPA-Game), which characterizes situations where agents compete for divisible resources. In the PPA-game, agents select from available resources, and their payoffs are proportionately determined based on heterogeneous weights attributed to them. Such dynamics simulate content creators on online recommender systems like YouTube and TikTok, who compete for finite consumer attention, with content exposure reliant on inherent and distinct quality. We first conduct a game-theoretical analysis of the PPA-Game. While the PPA-Game does not always guarantee the existence of a pure Nash equilibrium (PNE), we identify prevalent scenarios ensuring its existence. Simulated experiments further prove that the cases where PNE does not exist rarely happen. Beyond analyzing static payoffs, we further discuss the agents' online learning about resource payoffs by integrating a multi-player multi-armed bandit framework. We propose an online algorithm facilitating each agent's maximization of cumulative payoffs over $T$ rounds. Theoretically, we establish that the regret of any agent is bounded by $O(\log^{1 + η} T)$ for any $η> 0$. Empirical results further validate the effectiveness of our online learning approach.

cs.GT · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36077HF 社区推荐

The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang 等 20 位作者

原文摘要

Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34849

Physics-Informed and Data-Driven Composite Disturbance Separation and Predictive Control for Airborne Electro-Optical Gimbals with Multiple Constraints

Yaokun Lu, Yifan Li, Zhixuan Zhang, Enmei Wang, Hao Teng, Jianzhong Qiao

原文摘要

This paper studies the constrained pointing control problem of airborne electro-optical gimbals subjected to composite periodic and aperiodic disturbances. Under carrier vibration, input delay, and actuator constraints, achieving line-of-sight stabilization and tracking is challenging. A disturbance-separated model predictive control (MPC) scheme is proposed to compensate these heterogeneous disturbances according to their physical characteristics. An adaptive periodic observer predicts multi-harmonic vibrations over the MPC horizon using linear-regression frequency estimation. A linear observer estimates the aperiodic disturbance, and a bounded long short-term memory (LSTM) network predicts its change over the input delay. Embedding periodic predictions into the MPC model while applying aperiodic compensation outside the optimizer limits amplification of aperiodic estimation errors and improves pointing accuracy under frequency changes and parameter mismatch. On the stated headroom envelope, input-set tightening provides feasible commands within the prescribed limits, and a regional practical tracking bound is established under explicit input-sequence and predicted-state margin conditions. A UAV-mounted two-axis gimbal platform is assembled for comparative indoor hovering experiments, complemented by simulations under frequency changes and parameter mismatch. In the reported trials, the proposed method achieves yaw and pitch relative-angle root-mean-square errors (RMSEs) of 0.770 degrees and 0.350 degrees, reducing tracking errors by 25.1% and 45.9% compared with linear active disturbance rejection control.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34764

SLIDE: Search-to-List Item Distillation for Single-Rollout Generative Retrieval

Tianyu Zhan, Gui Ling, Ran Tao, Kunhai Lin, Tong Xiong, Wang Yang, Kaixuan Zhang, Zhihong Chen 等 12 位作者

原文摘要

Generative retrieval (GR) typically relies on item-level beam search to retrieve candidates, leaving cross-item dependencies unmodeled and limiting direct optimization of list-level objectives. A natural alternative is to generate the entire list within a single autoregressive trajectory. However, greedy decoding with directly trained list-wise models substantially underperforms beam search. We identify two contributing factors: the broader search space explored by beam search and the positional bias of scarce positive signals, which deprives later positions of adequate supervision. To address these challenges, we propose $\textbf{SLIDE}$, a search-to-list item distillation framework that decouples offline search from online list generation. A teacher model retrieves high-quality candidates through offline item-level beam search, providing additional conversion-relevant supervision beyond sparse behavioral labels. Their Semantic IDs (SIDs) are then concatenated in beam-score order to form list-wise distillation targets. This search-to-list conversion transforms candidates retrieved along separate search paths into sequential item-generation targets within a single trajectory. Trained on these targets, the student generates the Top-$K$ list in a single greedy pass, also decoupling teacher scaling from online deployment. Experiments on FORGE and Taobao Search show that SLIDE substantially improves retrieval quality under single greedy decoding and, with stronger offline teachers, surpasses the beam-search reference. Supplementary RL experiments support the effectiveness of list-level generation.

cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.11200

AmbientFM: A Foundation Model for Ambient Sensing

Guozhen Zhu, Yuqian Hu, Sakila Jayaweera, Weihang Gao, Wei-Hsiang Wang, Jiaxuan Zhang, Beibei Wang, Chenshu Wu 等 9 位作者

原文摘要

Ambient intelligence seeks to continuously understand human presence, activity, and physiology in physical spaces, enabling smart environments, health monitoring, and human-computer interaction. WiFi infrastructure offers a ubiquitous, always-on, and privacy-preserving sensing substrate across billions of IoT devices. Yet ambient sensing with WiFi remains largely fragmented, with most systems relying on task-specific models, labeled data collection, and customized training pipelines. We present AmbientFM, a foundation model for ambient sensing through ubiquitous WiFi signals. AmbientFM is pre-trained on 9.2 million unlabeled Channel State Information (CSI) samples collected over 439 days from 20 commercial device types deployed in real homes, the largest real-world WiFi CSI pre-training corpus reported to date. It learns transferable wireless representations through contrastive learning, masked reconstruction, and physics-informed objectives tailored to wireless signals. With lightweight adaptation, a single backbone transfers to 9 downstream tasks, achieving above 0.90 AUROC on all classification benchmarks and supporting dense spatial reconstruction. AmbientFM reduces the need for labeled data and task-specific design, enabling scalable ambient intelligence on existing wireless infrastructure.

cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1081ACL Anthology · ACL 2026

Instant Personalized Large Language Model Adaptation via Hypernetwork

Zhaoxuan Tan University of Notre Dame, Zixuan Zhang Amazon, Haoyang Wen Amazon, Zheng Li, Rongzhi Zhang Georgia Institute of Technology, Zhejiang University and Amazon, Pei Chen Amazon, Fengran Mo, Zheyuan Liu University of Notre Dame 等 11 位作者

原文摘要

Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the “One-PEFT-Per-User” (OPPU) paradigm, require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates. We introduce Profile-to-PEFT, a scalable framework that employs a hypernetwork, trained end-to-end, to map a user’s encoded profile directly to a full set of adapter parameters (e.g., LoRA), eliminating per-user training at deployment. This design enables instant adaptation, generalization to unseen users, and privacy-preserving local deployment. Experimental results demonstrate that our method outperforms both prompt-based personalization and OPPU while using substantially fewer computational resources at deployment. The framework exhibits strong generalization to out-of-distribution users and maintains robustness across varying user activity levels and different embedding backbones. The proposed Profile-to-PEFT framework enables efficient, scalable, and adaptive LLM personalization suitable for large-scale applications.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1249ACL Anthology · ACL 2026

DR-Arena: an Automated Evaluation Framework for Deep Research Agents

Yiwen Gao National University of Singapore, Ruochen Zhao Singapore University of Technology and Design, Yang Deng Singapore Management University, Wenxuan Zhang Singapore University of Technology and Design

原文摘要

As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, reliable evaluation of their task performance has become a critical bottleneck. Current benchmarks predominantly rely on static datasets, which suffer from several limitations: limited task generality, temporal misalignment, and data contamination. To address these, we introduce DR-Arena, a fully automated evaluation framework that pushes DR agents to their capability limits through dynamic investigation. DR-Arena constructs real-time Information Trees from fresh web trends to ensure the evaluation rubric is synchronized with the live world state, and employs an automated Examiner to generate structured tasks testing two orthogonal capabilities: Deep reasoning and Wide coverage. DR-Arena further adopts Adaptive Evolvement Loop, a state-machine controller that dynamically escalates task complexity based on real-time performance, demanding deeper deduction or wider aggregation until a decisive capability boundary emerges. Experiments with six advanced DR agents demonstrate that DR-Arena achieves a Spearman correlation of 0.94 with the LMSYS Search Arena leaderboard. This represents state-of-the-art alignment with human preferences without any manual efforts, validating DR-Arena as a reliable alternative for costly human adjudication.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1637ACL Anthology · ACL 2026

ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization

Yuxuan Zhang

原文摘要

Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow stable linguistic patterns across users, indicating that more informative supervisory signals can be extracted from free-form feedback. Building on this insight, we introduce Adaptive Reward-Following (ARF), which converts natural feedback into continuous preference trajectories and optimizes them using the novel TraceBias algorithm. Across diverse LLMs and preference domains, ARF consistently outperforms PPO and DPO, improving alignment by up to 7.6%. Our results demonstrate that continuous reward modeling provides a scalable path toward personalized and theoretically grounded RLHF.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.266ACL Anthology · ACL 2026

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving

Xinyu Zhang Xi'an Jiaotong University, Yuchen Wan, Boxuan Zhang, Zesheng Yang, Lingling Zhang Xi'an Jiaotong University, Bifan Wei Xi'an Jiaotong University, Jun Liu Xi'an Jiaotong University

原文摘要

Large Language Models (LLMs) often struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation. To address this, we propose Dual-Cluster Memory Agent (DCM-Agent) to enhance performance by leveraging historical solutions in a training-free manner. Central to this is Dual-Cluster Memory Construction. This agent assigns historical solutions to modeling and coding clusters, then distills each cluster’s content into three structured types: Approach, Checklist, and Pitfall. This process derives generalizable guidance knowledge. Furthermore, this agent introduces Memory-augmented Inference to dynamically navigate solution paths, detect and repair errors, and adaptively switch reasoning paths with structured knowledge. The experiments across seven optimization benchmarks demonstrate that DCM-Agent achieves an average performance improvement of 11%- 21%. Notably, our analysis reveals a “knowledge inheritance” phenomenon: memory constructed by larger models can guide smaller models toward superior performance, highlighting the framework’s scalability and efficiency.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.493ACL Anthology · ACL 2026

Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores

Congren Dai, Yue Yang, Krinos Li, Huichi Zhou University College London, University of London, Shijie Liang, Bo Zhang, Enyang Liu, Ge Jin 等 15 位作者

原文摘要

Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of Large Language Models and Vision–Language Models to interpret full musical notation remains insufficiently examined.We introduce Musical Score Understanding Benchmark (MSU-Bench), a human-curated benchmark for score-level musical understanding across textual (ABC notation) and visual (PDF) modalities. MSU-Bench contains 1,800 generative question–answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others, organised into four levels of increasing difficulty, ranging from onset information to texture and form. Evaluations of more than fifteen state-of-the-art models, in both zero-shot and fine-tuned settings, reveal pronounced modality gaps, unstable level-wise performance, and challenges in maintaining multilevel correctness. Fine-tuning substantially improves results across modalities while preserving general knowledge, positioning MSU-Bench as a robust foundation for future research in multimodal reasoning. The benchmark and code are available at https://github.com/Congren-Dai/MSU-Bench.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表