语言大模型 / LLM

VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills

Erik M. Lintunen

专题命中 评测与基准 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 17 pages including appendices, full paper at the Scaling Environments for Agents workshop at NeurIPS 2025

Precise Mobile Manipulation of Small Everyday Objects

Arjun Gupta, Rishik Sathua, Saurabh Gupta

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 评测与基准 ：foundation model(abstract)；分类 cs.AI、cs.LG

Comments Project webpage: https://arjung128.github.io/svm

AbBiBench: A Benchmark for Antibody Binding Affinity Maturation and Design

Xinyan Zhao, Yi-Ching Tang, Akshita Singh, Victor J Cantu, KwanHo An, Junseok Lee, Adam E Stogsdill, Ibraheem M Hamdi, Ashwin Kumar Ramesh, Zhiqiang An, Xiaoqian Jiang, Yejin Kim

机构 * McWilliams School of Biomedical Informatics, UTHealth Houston（麦威廉生物医学信息学学院，UT健康科学中心休斯顿分校） ； University of Texas Health Science Center（德克萨斯大学健康科学中心） ； Korea Advanced Institute of Science and Technology（韩国科学技术院） ； Texas Therapeutics Institute（德克萨斯疗法研究所） ； Brown Foundation Institute of Molecular Medicine, UTHealth Houston（布朗基金会分子医学研究所，UT健康科学中心休斯顿分校） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.AI、cs.LG

Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies

Zirui Song, Yuan Huang, Junchang Liu, Haozhe Luo, Chenxi Wang, Lang Gao, Zixiang Xu, Mingfei Han, Xiaojun Chang, Xiuying Chen

机构 * Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.CL

Comments 34 pages, 32figures

WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent

Tao Li, Jinlong Hu, Yang Wang, Junfeng Liu, Xuejun Liu

机构 * College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学） ； Hong Kong Baptist University（香港 Baptist 大学） ； SKLCCSE Lab, Beihang University（SKLCCSE 实验室，北京航空航天大学） ； Pengcheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.CL

Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem

Muhammad Maaz, Liam DeVoe, Zac Hatfield-Dodds, Nicholas Carlini

机构 * MATS, Anthropic（MATS，Anthropic） ； Northeastern University（东北大学） ； Anthropic 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.AI

Comments 4 pages (main), NeurIPS 2025, The 4th Deep Learning for Code Workshop

Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft

Eray Yapağcı, Yavuz Alp Sencer Öztürk, Eray Tüzün

机构 * Electronics Engineering Department Bilkent University Ankara, Turkey（电子工程系比尔肯特大学安卡拉土耳其） ； Computer Engineering Department Bilkent University Ankara, Turkey（计算机工程系比尔肯特大学安卡拉土耳其） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.AI

Comments Accepted into ASE'25 (Automated Software Engineering). https://conf.researchr.org/details/ase-2025/ase-2025-papers/244/Agents-in-the-Sandbox-End-to-End-Crash-Bug-Reproduction-for-Minecraft

InfiniHuman: Infinite 3D Human Creation with Precise Control

Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll

机构 * University of Tübingen, Tübingen AI Center（图宾根大学，图宾根人工智能中心） ； University of Tübingen, Tübingen AI Center, MPI for Informatics, SIC（图宾根大学，图宾根人工智能中心，马克斯·普朗克信息研究所，SIC） ； University of Tübingen（图宾根大学） 纠错

专题命中 评测与基准 ：foundation model(abstract)

Comments Accepted to ACM SIGGRAPH Asia 2025. Project website: https://yuxuan-xue.com/infini-human

InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition

Yijie Zheng, Weijie Wu, Qingyun Li, Xuehui Wang, Xu Zhou, Aiai Ren, Jun Shen, Long Zhao, Guoqing Li, Xue Yang

机构 * Aerospace Information Research Institute, Chinese Academy of Sciences（航天信息研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Wollongong（沃林戈大学） ； SAIS, Shanghai Jiao Tong University（上海交通大学国际关系学院） 纠错

专题命中 评测与基准 ：language model(abstract)

Comments Accepted to NeurIPS 2025

Saudi Sign Language Translation Using T5

Ali Alhejab, Tomas Zelezny, Lamya Alkanhal, Ivan Gruber, Yazeed Alharbi, Jakub Straka, Vaclav Javorek, Marek Hruz, Badriah Alkalifah, Ahmed Ali

机构 * HUMAIN, Riyadh, Saudi Arabia Department of Cybernetics ； New Technologies for the Information Society, University of West Bohemia, Pilsen, Czech Republic Saudi Data \& AI Authority , Riyadh, Saudi Arabia 纠错

专题命中 评测与基准 ：language model(abstract)

Comments 11 pages, supplementary, SPECOM 2025

Journal ref Speech and Computer (SPECOM 2025), Lecture Notes in Computer Science, vol. 16188, pp. 331-343, Springer, Cham (2025)

Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts

Yanning Hou, Ke Xu, Junfa Li, Yanran Ruan, Jianfeng Qiu

机构 * School of Artificial Intelligence, Anhui University, Hefei, China（人工智能学院，安徽大学，合肥，中国） ； Anhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University（安徽省安全人工智能重点实验室，安徽大学） ； Anhui Provincial Engineering Research Center for Unmanned System（安徽省无人系统与智能技术工程研究中心） 纠错

专题命中 评测与基准 ：foundation model(abstract)

Comments Accepted by PRCV

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales

Zhaofang Qian, Hardy Chen, Zeyu Wang, Li Zhang, Zijun Wang, Xiaoke Huang, Hui Liu, Xianfeng Tang, Zeyu Zheng, Haoqin Tu, Cihang Xie, Yuyin Zhou

机构 * University of Central Florida（中央佛罗里达大学） ； University of California, Santa Cruz（加州大学圣克鲁兹分校） ； Columbia University（哥伦比亚大学） ； Amazon Research（亚马逊研究） ； University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 评测与基准 ：language model(abstract)

Post-TIPS Prediction via Multimodal Interaction: A Multi-Center Dataset and Framework for Survival, Complication, and Portal Pressure Assessment

Junhao Dong, Dejia Liu, Ruiqi Ding, Zongxing Chen, Yingjie Huang, Zhu Meng, Jianbo Zhao, Zhicheng Zhao, Fei Su

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Division of Vascular and Interventional Radiology, Department of General Surgery, Nanfang Hospital, Southern Medical University（南方医科大学普外科血管介入放射科） ； Beijing Key Laboratory of Network System and Network Culture（北京网络系统与网络文化重点实验室） 纠错

专题命中 评测与基准 ：foundation model(abstract)

Comments 81 pages, 13 figures

FormCoach: Lift Smarter, Not Harder

Xiaoye Zuo, Nikos Athanasiou, Ginger Delmas, Yiming Huang, Xingyu Fu, Lingjie Liu

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） 纠错

专题命中 评测与基准 ：language model(abstract)

A Mathematics-Guided Approach to Floating-Point Error Detection

Youshuai Tan, Zhanwei Zhang, Zishuo Ding, Lianyu Zheng, Jinfu Chen, Weiyi Shang

专题命中 评测与基准 ：prompting(abstract)

Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models

Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang

机构 * University of California-Santa Barbara（加州大学圣巴巴拉分校） ； Amazon（亚马逊） 纠错

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；post-training(title,abstract)；pretraining(abstract)

Comments Accepted to EMNLP 2025

Equivalent Linear Mappings of Large Language Models

James R. Golden

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments title changed; major revisions; code available at https://github.com/jamesgolden1/equivalent-linear-LLMs/; published at https://openreview.net/forum?id=oDWbJsIuEp

Journal ref Transactions on Machine Learning Research (TMLR) (10/2025)

Self-ensemble: Mitigating Confidence Mis-calibration for Large Language Models

Zicheng Xu, Guanchu Wang, Guangyao Zheng, Yu-Neng Chuang, Alexander Szalay, Xia Hu, Vladimir Braverman

机构 * Rice University（里士大学） ； University of North Carolina at Charlotte（北卡罗来纳州立大学） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.LG

An Explorative Study on Distributed Computing Techniques in Training and Inference of Large Language Models

Sheikh Azizul Hakim, Saem Hasan

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications

Zhixiong Chen, Hyundong Shin, Arumugam Nallanathan, Jonathon Chambers

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 14 pages, 13 figures

Language Surgery in Multilingual Large Language Models

Joanito Agili Lopo, Muhammad Ravi Shulthan Habibi, Tack Hwa Wong, Muhammad Ilham Ghozali, Fajri Koto, Genta Indra Winata, Peerat Limkonchotiwat, Alham Fikri Aji, Samuel Cahyawijaya

机构 * SEACrowd ； Kreasof AI ； Universitas Indonesia（印度尼西亚大学） ； MBZUAI ； Capital One ； AI Singapore（AI新加坡） ； Cohere 纠错

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

LineBreaker: Finding Token-Inconsistency Bugs with Large Language Models

Hongbo Chen, Yifan Zhang, Xing Han, Tianhao Mao, Huanyao Rong, Yuheng Zhang, XiaoFeng Wang, Luyi Xing, Xun Chen, Hang Zhang

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)

Comments ASE 2025 Accepted, with Appendix added

Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization

Bowei He, Lihao Yin, Huiling Zhen, Shuqi Liu, Han Wu, Xiaokun Zhang, Mingxuan Yuan, Chen Ma

机构 * Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） ； Huawei（华为） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

Comments Accepted by NeurIPS 2025

PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models

Lancheng Zou, Shuo Yin, Zehua Pei, Tsung-Yi Ho, Farzan Farnia, Bei Yu

机构 * The Chinese University of Hong Kong（香港中文大学） 纠错

专题命中 效率与部署 ：large language model(title)；language model(title)；post-training(abstract)；分类 cs.AI、cs.LG

Comments Accepted by NeurIPS 2025

Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights

Yanxi Chen, Yaliang Li, Bolin Ding, Jingren Zhou

机构 * Alibaba Group（阿里巴巴集团） 纠错

专题命中 效率与部署 ：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments TMLR camera-ready version

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

Yuhang Li, Chenchen Zhang, Ruilin Lv, Ao Liu, Ken Deng, Yuanxing Zhang, Jiaheng Liu, Wiggin Zhou, Bo Zhou

机构 * LLM Department, Tencent（腾讯大语言模型部门） ； Peking University（北京大学） ； Nanjing University（南京大学） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications

Shivani Shukla, Himanshu Joshi

机构 * University of San Francisco（旧金山大学） ； Vector Institute for Artificial Intelligence（人工智能向量研究所） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments Peer-reviewed and accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) DynaFront 2025 Workshop (https://sites.google.com/view/dynafrontneurips25)

RL in the Wild: Characterizing RLVR Training in LLM Deployment

Jiecheng Zhou, Qinghao Hu, Yuyang Jin, Zerui Wang, Peng Sun, Yuzhe Gu, Wenwei Zhang, Mingshu Zhai, Xingcheng Zhang, Weiming Zhang

机构 * USTC（中国科学技术大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； NTU（国立台湾大学） ； Tsinghua University（清华大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 28 figures

Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking

Tuowei Wang, Ruwen Fan, Minxing Huang, Zixu Hao, Kun Li, Ting Cao, Youyou Lu, Yaoxue Zhang, Ju Ren

机构 * Tsinghua University（清华大学） ； Tianjin University（天津大学） ； Microsoft Research（微软研究院） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Journal ref Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Vol. 3, Rotterdam, Netherlands, 2025, pp. 147-162

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers

Shivam Patel, Neharika Jali, Ankur Mallick, Gauri Joshi

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Microsoft（微软公司） 纠错

专题命中 效率与部署 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG