语言大模型 / LLM

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression

Te Zhang, Yuheng Li, Junxiang Wang, Lujun Li

机构 * University of Michigan（密歇根大学） ； Johns Hopkins University（约翰霍普金斯大学） ； Central South university（中南大学） ； HKGAI 纠错

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

Comments 6 pages

Efficient and Scalable Agentic AI with Heterogeneous Systems

Zain Asgar, Michelle Nguyen, Sachin Katti

机构 * Stanford University（斯坦福大学） ； Gimlet Labs Inc.（Gimlet实验室） ； Intel（英特尔） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI、cs.LG

Comments Early access preprint

Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps: An Interpretation and Potential Improvements

Aditya Ravuri, Neil D. Lawrence

机构 * University of Cambridge（剑桥大学） 纠错

专题命中 效率与部署 ：language model(abstract)；分类 cs.LG

Comments Initial version

PhaseNAS: Language-Model Driven Architecture Search with Dynamic Phase Adaptation

Fei Kong, Xiaohan Shan, Yanwei Hu, Jianmin Li

专题命中 效率与部署 ：LLM(abstract)；分类 cs.LG

Comments 14pages

TAPS : Frustratingly Simple Test Time Active Learning for VLMs

Dhruv Sarkar, Aprameyo Chakrabartty, Bibhudatta Bhanja

机构 * IIT Kharagpur（印度理工学院Kharagpur分校） 纠错

专题命中 效率与部署 ：language model(abstract)；分类 cs.AI

GNSP: Gradient Null Space Projection for Preserving Cross-Modal Alignment in VLMs Continual Learning

Tiantian Peng, Yuyang Liu, Shuo Yang, Qiuhe Hong, YongHong Tian

专题命中 效率与部署 ：pretraining(abstract)；分类 cs.LG

Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environments

Shitong Zhu, Chenhao Fang, Derek Larson, Neel Reddy Pochareddy, Rajeev Rao, Sophie Zeng, Yanqing Peng, Wendy Summer, Alex Goncalves, Arya Pudota, Hervé Robert

机构 * Meta 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI

Robotic Visual Instruction

Yanbang Li, Ziyang Gong, Haoyang Li, Xiaoqi Huang, Haolan Kang, Guangping Bai, Xianzheng Ma

机构 * Imperial College London（伦敦帝国理工学院） ； Shanghai AI Laboratory（上海人工智能实验室） ； UC San Diego（加州大学圣地亚哥分校） ； VIVO ； South China University of Technology（华南理工大学） 纠错

专题命中 效率与部署 ：language model(abstract)；分类 cs.AI

Comments Project website: https://robotic-visual-instruction.github.io/

AI as a deliberative partner fosters intercultural empathy for Americans but fails for Latin American participants

Isabel Villanueva, Tara Bobinac, Binwei Yao, Junjie Hu, Kaiping Chen

专题命中 效率与部署 ：prompting(abstract)；分类 cs.CL

Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling

Mouyang Cheng, Weiliang Luo, Hao Tang, Bowen Yu, Yongqiang Cheng, Weiwei Xie, Ju Li, Heather J. Kulik, Mingda Li

机构 * Quantum Measurement Group, MIT（麻省理工学院量子测量组） ； Department of Materials Science and Engineering, MIT（麻省理工学院材料科学与工程系） ； Department of Chemistry, MIT（麻省理工学院化学系） ； Neutron Scattering Division, Oak Ridge National Laboratory（橡树岭国家实验室中子散射部） ； Department of Chemistry, Michigan State University（密歇根州立大学化学系） ； Department of Nuclear Science and Engineering, MIT（麻省理工学院核科学与工程系） 纠错

专题命中 效率与部署 ：language model(abstract)；分类 cs.LG

Comments 13 pages, 4 figures

ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

Yuying Ge, Yixiao Ge, Chen Li, Teng Wang, Junfu Pu, Yizhuo Li, Lu Qiu, Jin Ma, Lisheng Duan, Xinyu Zuo, Jinwen Luo, Weibo Gu, Zexuan Li, Xiaojing Zhang, Yangyu Tao, Han Hu, Di Wang, Ying Shan

机构 * ARC Lab, Tencent PCG（腾讯PCG ARC实验室） ； Search Application Department, Tencent CSIG（腾讯CSIG搜索应用部门） ； Tencent Hunyuan（腾讯文生视频） ； Big Data Platform Department, Tencent PCG（腾讯PCG大数据平台部门） 纠错

专题命中 效率与部署 ：post-training(abstract)

Comments Project Page: https://tencentarc.github.io/posts/arc-video-announcement/

Efficient Vision-based Vehicle Speed Estimation

Andrej Macko, Lukáš Gajdošech, Viktor Kocur

机构 * Photoneo, s.r.o.（Photoneo公司） ； Faculty of Mathematics, Physics and Informatics, Comenius University Bratislava（布拉迪斯拉瓦康门ius大学数学、物理与信息学学院） 纠错

专题命中 效率与部署 ：post-training(abstract)

Comments Submitted to Journal of Real-Time Image Processing (JRTIP)

SparseLoc: Sparse Open-Set Landmark-based Global Localization for Autonomous Navigation

Pranjal Paul, Vineeth Bhat, Tejas Salian, Mohammad Omama, Krishna Murthy Jatavallabhula, Naveen Arulselvan, K. Madhava Krishna

专题命中 效率与部署 ：foundation model(abstract)

FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation

Samiran Gode, Abhijeet Nayak, Débora N. P. Oliveira, Michael Krawez, Cordelia Schmid, Wolfram Burgard

机构 * Artificial Intelligence and Robotics Lab, Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg（人工智能与机器人实验室，计算机科学与人工智能系，图腾大学） ； Inria, Ecole Normale Supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所，巴黎高等师范学校，国家科学研究中心，巴黎综合理工研究学院） 纠错

专题命中 效率与部署 ：foundation model(abstract)

Comments Accepted to IROS'25. Previous version accepted at CoRL 2024 workshop on Learning Effective Abstractions for Planning (LEAP) and workshop on Differentiable Optimization Everywhere: Simulation, Estimation, Learning, and Control

LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes

Juliette Marrie, Romain Menegaux, Michael Arbel, Diane Larlus, Julien Mairal

机构 * Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK（格勒诺布尔阿尔卑斯大学、法国国家科学研究中心、格勒诺布尔INP、LJK） 纠错

专题命中 效率与部署 ：foundation model(abstract)

Comments Published at ICCV 2025. Project page: https://juliettemarrie.github.io/ludvig

LowKeyEMG: Electromyographic typing with a reduced keyset

Johannes Y. Lee, Derek Xiao, Shreyas Kaasyap, Nima R. Hadidi, John L. Zhou, Jacob Cunningham, Rakshith R. Gore, Deniz O. Eren, Jonathan C. Kao

专题命中 效率与部署 ：language model(abstract)

Comments 11+3 pages, 5 main figures, 2 supplementary tables, 4 supplementary figures

Juru: Legal Brazilian Large Language Model from Reputable Sources

Roseval Malaquias Junior, Ramon Pires, Roseli Romero, Rodrigo Nogueira

机构 * Computer Science Department, University of São Paulo（圣保罗大学计算机科学系） ； Maritaca AI 纠错

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI

Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models

Shamus Sim, Tyrone Chen

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 25 pages, 7 figures, 3 tables. Conceptualization, both authors. formal analysis, both authors. funding acquisition, both authors. investigation, both authors. resources, both authors. supervision, T.C.. validation, both authors. visualization, both authors. writing original draft, both authors. writing review and editing, both authors

Improving the Performance of Sequential Recommendation Systems with an Extended Large Language Model

Sinnyum Choi, Woong Kim

机构 * Department of AI Convergence Software（人工智能融合软件系） ； Dong-Seoul University（东首尔大学） 纠错

专题命中 领域大模型 ：language model(title,abstract)；large language model(title)；LLM(abstract)；分类 cs.CL、cs.AI

Differentiating hype from practical applications of large language models in medicine -- a primer for healthcare professionals

Elisha D. O. Roberson

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

Comments 7 pages main document text, 2 figures. A basic primer on the potential and dangers of AI generally and LLMs specifically in the medical care system. Targeted to *non-expert* healthcare workers without experience in AI or LLMs

Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models

Jun-Peng Zhu, Boyan Niu, Peng Cai, Zheming Ni, Jianwei Wan, Kai Xu, Jiajun Huang, Shengbo Ma, Bing Wang, Xuan Zhou, Guanglei Bao, Donghui Zhang, Liu Tang, Qi Liu

机构 * East China Normal University \& PingCAP, China ； East China Normal University, China 纠错

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

Comments 14 pages, 10 figures

Journal ref Proceedings of the VLDB Endowment, Vol. 18, No. 12, pp. 5086 - 5099, 2025

Navigating the Risks of Using Large Language Models for Text Annotation in Social Science Research

Hao Lin, Yongjun Zhang

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data

Leonardo Castro-Gonzalez, Yi-Ling Chung, Hannak Rose Kirk, John Francis, Angus R. Williams, Pica Johansson, Jonathan Bright

机构 * Public Policy Programme, The Alan Turing Institute, British Library（公共政策计划、艾伦·图灵研究所、大英图书馆） ； School of Geographical Sciences, University of Bristol（地理科学学院、布里斯托尔大学） ； Oxford Internet Institute, University of Oxford（牛津大学网络研究所） ； Zug Institute for Blockchain Research, University of Lucerne（祖格区块链研究所、卢塞恩大学） 纠错

专题命中 领域大模型 ：language model(title,abstract)；large language model(abstract)；prompting(abstract)；分类 cs.CL

Comments 46 pages, 17 figures, 6 tables

Integrating LLM-Derived Multi-Semantic Intent into Graph Model for Session-based Recommendation

Shuo Zhang, Xiao Li, Jiayi Wu, Fan Yang, Xiang Li, Ming Gao

专题命中 领域大模型 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Heterogeneous User Modeling for LLM-based Recommendation

Honghui Bao, Wenjie Wang, Xinyu Lin, Fengbin Zhu, Teng Sun, Fuli Feng, Tat-Seng Chua

专题命中 领域大模型 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments Accepted by RecSys 2025

SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence

Jie Jiang, Haining Xie, Siqi Shen, Yu Shen, Zihan Zhang, Meng Lei, Yifeng Zheng, Yang Li, Chunyou Li, Danqing Huang, Yinjun Wu, Wentao Zhang, Xiaofeng Yang, Bin Cui, Peng Chen

专题命中 领域大模型 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 14 pages, 8 figures

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

Keyan Ding, Jing Yu, Junjie Huang, Yuchen Yang, Qiang Zhang, Huajun Chen

机构 * College of Computer Science and Technology（计算机科学与技术学院） ； Zhejiang University（浙江大学） ； Zhejiang Key Laboratory of Intelligent Manufacturing for Functional Chemicals（功能化学品智能制造重点实验室） ； ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙大杭州国际科学技术创新中心） ； ZJU-UIUC Institute（浙大UIUC研究院） ； The Polytechnic Institute（技术学院） ； State Key Laboratory of Ocean Sensing（海洋感知国家重点实验室） 纠错

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 21 pages, 6 figures

Modeling Professionalism in Expert Questioning through Linguistic Differentiation

Giulia D'Agostino, Chung-Chi Chen

机构 * Università della Svizzera italiana（瑞士联邦理工学院） ； National Institute of Advanced Industrial Science and Technology（国家先进工业科学与技术研究院） 纠错

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

ChatMyopia: An AI Agent for Pre-consultation Education in Primary Eye Care Settings

Yue Wu, Xiaolan Chen, Weiyi Zhang, Shunming Liu, Wing Man Rita Sum, Xinyuan Wu, Xianwen Shang, Chea-su Kee, Mingguang He, Danli Shi

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 35 pages, 4 figures, 1 table

Risks & Benefits of LLMs & GenAI for Platform Integrity, Healthcare Diagnostics, Financial Trust and Compliance, Cybersecurity, Privacy & AI Safety: A Comprehensive Survey, Roadmap & Implementation Blueprint

Kiarash Ahi

专题命中 领域大模型 ：LLM(abstract)；large language model(abstract)；language model(abstract)