语言大模型 / LLM

ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding

Kimihiro Hasegawa, Wiradee Imrattanatrai, Zhi-Qi Cheng, Masaki Asada, Susan Holm, Yuran Wang, Ken Fukuda, Teruko Mitamura

机构 * Language Technologies Institute, Carnegie Mellon University（语言技术研究所，卡内基梅隆大学） ； National Institute of Advanced Industrial Science and Technology (AIST)（国家先进工业科学与技术研究院） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.CL

Comments NAACL2025, Code and Data: https://github.com/kimihiroh/promqa

Text-VQA Aug: Pipelined Harnessing of Large Multimodal Models for Automated Synthesis

Soham Joshi, Shwet Kamal Mishra, Viswanath Gopalakrishnan

机构 * International Institute of Information Technology Bangalore（国际信息科技学院班加罗尔） 纠错

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

Comments First two authors contributed equally

iFlyBot-VLA Technical Report

Yuan Zhang, Chenyu Xue, Wenjie Xu, Chao Ji, Jiajia wu, Jia Pan

机构 * iFlyTek Reasearch and Development Group（iFlyTek 研发部） 纠错

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

MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving

Aishan Liu, Jiakai Wang, Tianyuan Zhang, Hainan Li, Jiangfan Liu, Siyuan Liang, Yilong Ren, Xianglong Liu, Dacheng Tao

机构 * Beihang University, Beijing, China（北航大学，北京，中国） ； Zhongguancun Laboratory, Beijing, China（中关村实验室，北京，中国） ； Institute of Dataspace, Hefei, China（数据空间研究所，合肥，中国） ； Nanyang Technological University, Singapore, Singapore（南洋理工大学，新加坡，新加坡） 纠错

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

Comments ACM MM 2025 Most Popular Demo Award

Consistency of Responses and Continuations Generated by Large Language Models on Social Media

Wentao Xu, Wenlu Fan, Yuqi Zhu, Bin Wang

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

Comments This paper has been accepted by the 20th International AAAI Conference on Web and Social Media (ICWSM 2026), sunny Los Angeles, California, U.S

Knowledge Graph-enhanced Large Language Model for Incremental Game PlayTesting

Enhong Mu, Jinyu Cai, Yijun Lu, Mingyue Zhang, Kenji Tei, Jialong Li

机构 * Southwest University（西南大学） ； Waseda University（早稻田大学） ； Institute of Science Tokyo（东京科学研究院） 纠错

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

IG-Pruning: Input-Guided Block Pruning for Large Language Models

Kangyu Qiao, Shaolei Zhang, Yang Feng

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（智能信息处理重点实验室，计算技术研究所，中国科学院） ； Key Laboratory of AI Safety, Chinese Academy of Sciences（人工智能安全重点实验室，中国科学院） ； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国） 纠错

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

Comments Accepted to EMNLP 2025. Code is available at https://github.com/ictnlp/IG-Pruning

Journal ref https://aclanthology.org/2025.emnlp-main.537/

Federated Attention: A Distributed Paradigm for Collaborative LLM Inference over Edge Networks

Xiumei Deng, Zehui Xiong, Binbin Chen, Dong In Kim, Merouane Debbah, H. Vincent Poor

机构 * Pillar of Information Systems Technology and Design, Singapore University of Technology and Design（信息系统技术与设计学院，新加坡南洋理工大学） ； School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast（电子、电气与计算机科学学院，女王大学贝尔法斯特分校） ； Department of Electrical and Computer Engineering, Sungkyunkwan University（电气与计算机工程系，成均馆大学） ； KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University（6G研究中心，计算机与信息工程系，哈利法大学） ； CentraleSupelec, University of Paris-Saclay（中央超导研究所，巴黎萨克雷大学） ； Department of Electrical and Computer Engineering, Princeton University（电气与计算机工程系，普林斯顿大学） 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

Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning

Bowen Jin, TJ Collins, Donghan Yu, Mert Cemri, Shenao Zhang, Mengyu Li, Jay Tang, Tian Qin, Zhiyang Xu, Jiarui Lu, Guoli Yin, Jiawei Han, Zirui Wang

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Apple（苹果公司） ； University of California, Berkeley（加州大学伯克利分校） ； Northwestern University（西北大学） ； Harvard University（哈佛大学） ； Virginia Tech（弗吉尼亚理工大学） 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

Comments 14 pages

EdgeReasoning: Characterizing Reasoning LLM Deployment on Edge GPUs

Benjamin Kubwimana, Qijing Huang

机构 * NVIDIA 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

Comments Published in the Proceedings of the 2025 IEEE International Symposium on Workload Characterization (IISWC 2025)

Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes

Mohammadsajad Alipour, Mohammad Mohammadi Amiri

机构 * Department of Computer Science Rensselaer Polytechnic Institute（计算机科学系罗切斯特理工学院） 纠错

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

Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents

Brennen Hill

机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系威斯康星大学麦迪逊分校） 纠错

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

Comments In the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Embodied World Models for Decision Making (EWM)

Training Language Models to Reason Efficiently

Daman Arora, Andrea Zanette

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

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

Comments NeurIPS 2025

Visual Program Distillation with Template-Based Augmentation

Michal Shlapentokh-Rothman, Yu-Xiong Wang, Derek Hoiem

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 效率与部署 ：large language model(abstract)；language model(abstract)；small language model(abstract)；prompting(abstract)

Comments EMNLP Camera Ready

Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation

Wongyu Kim, Hochang Lee, Sanghak Lee, Yoonsung Kim, Jaehyun Park

机构 * NC AI（NC人工智能） 纠错

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

Comments Accepted to MMGenSR Workshop (CIKM 2025)

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning

Chaofan Lin, Jiaming Tang, Shuo Yang, Hanshuo Wang, Tian Tang, Boyu Tian, Ion Stoica, Song Han, Mingyu Gao

机构 * Tsinghua University（清华大学） ； Massachusetts Institute of Technology（麻省理工学院） ； University of California, Berkeley（加州大学伯克利分校） 纠错

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

Comments To appear on NeurIPS 2025 (spotlight)

Can Foundation Models Revolutionize Mobile AR Sparse Sensing?

Yiqin Zhao, Tian Guo

机构 * Rochester Institute of Technology（罗切斯特理工学院） ； Worcester Polytechnic Institute（沃思利理工学院） 纠错

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

SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding

Jameson Sandler, Jacob K. Christopher, Thomas Hartvigsen, Ferdinando Fioretto

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

TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance

Jingxian Xu, Mengyu Zhou, Weichang Liu, Hanbing Liu, Shi Han, Dongmei Zhang

机构 * Nankai University（南开大学） ； BeijingJiaoTong University（北京交通大学） ； Tsinghua University（清华大学） ； Microsoft Research（微软研究院） 纠错

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

Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs

Octavian Alexandru Trifan, Karthik Sangaiah, Muhammad Awad, Muhammad Osama, Sumanth Gudaparthi, Alexandru Nicolau, Alexander Veidenbaum, Ganesh Dasika

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

Apriel-H1: Towards Efficient Enterprise Reasoning Models

Oleksiy Ostapenko, Luke Kumar, Raymond Li, Denis Kocetkov, Joel Lamy-Poirier, Shruthan Radhakrishna, Soham Parikh, Shambhavi Mishra, Sebastien Paquet, Srinivas Sunkara, Valérie Bécaert, Sathwik Tejaswi Madhusudhan, Torsten Scholak

机构 * SLAM Lab（SLAM实验室） ； ServiceNow 纠错

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

ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search

Vincenzo Collura, Karim Tit, Laura Bussi, Eleonora Giunchiglia, Maxime Cordy

机构 * University of Luxembourg（卢森堡大学） ； Imperial College London（伦敦帝国学院） 纠错

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

Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs

Jiace Zhu, Yuanzhe Huang, Yingtao Shen, Jie Zhao, An Zou

机构 * Shanghai Jiao Tong University（上海交通大学） ； Microsoft Corporation（微软公司） 纠错

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

LGCC: Enhancing Flow Matching Based Text-Guided Image Editing with Local Gaussian Coupling and Context Consistency

Fangbing Liu, Pengfei Duan, Wen Li, Yi He

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

Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue

Keara Schaaij, Roel Boumans, Tibor Bosse, Iris Hendrickx

机构 * Centre for Language Studies, Centre for Language and Speech Technology, Radboud University,Nijmegen, The Netherlands（语言研究所以及语言与语音技术中心，拉德堡德大学，尼姆egen，荷兰） ； Behavioural Science Institute, Radboud University, Nijmegen, The Netherlands（行为科学研究所，拉德堡德大学，尼姆egen，荷兰） 纠错

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

Comments This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in TSD 2025. Lecture Notes in Computer Science, vol 16029

Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

Sophie Li, Nicholas Huang, Nayan Saxena, Nina Luo, Vincent Lin, Kevin Zhu, Sunishchal Dev

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

Comments Accepted by NeurIPS 2025 Workshop on Efficient Reasoning

Resource-efficient Automatic Refinement of Segmentations via Weak Supervision from Light Feedback

Alix de Langlais, Benjamin Billot, Théo Aguilar Vidal, Marc-Olivier Gauci, Hervé Delingette

机构 * Inria（法国国家信息与自动化技术研究所） ； Université Côte d'Azur（蔚蓝海岸大学） ； Inserm U1091（法国国家医学研究院 U1091 机构） ； Institut Universitaire Locomoteur et du Sport（运动与体育大学研究所） ； Centre Hospitalier Universitaire（大学医院中心） 纠错

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

The Pervasive Blind Spot: Benchmarking VLM Inference Risks on Everyday Personal Videos

Shuning Zhang, Zhaoxin Li, Changxi Wen, Ying Ma, Simin Li, Gengrui Zhang, Ziyi Zhang, Yibo Meng, Hantao Zhao, Xin Yi, Hewu Li

专题命中 效率与部署 ：language model(abstract)；prompting(abstract)

CAT-ID$^2$: Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce

Xiaoyu Liu, Fuwei Zhang, Yiqing Wu, Xinyu Jia, Zenghua Xia, Fuzhen Zhuang, Zhao Zhang, Fei Jiang, Wei Lin

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

Comments Accepted by WSDM'26

Reflections from Research Roundtables at the Conference on Health, Inference, and Learning (CHIL) 2025

Emily Alsentzer, Marie-Laure Charpignon, Bill Chen, Niharika D'Souza, Jason Fries, Yixing Jiang, Aparajita Kashyap, Chanwoo Kim, Simon Lee, Aishwarya Mandyam, Ashery Mbilinyi, Nikita Mehandru, Nitish Nagesh, Brighton Nuwagira, Emma Pierson, Arvind Pillai, Akane Sano, Tanveer Syeda-Mahmood, Shashank Yadav, Elias Adhanom, Muhammad Umar Afza, Amelia Archer, Suhana Bedi, Vasiliki Bikia, Trenton Chang, George H. Chen, Winston Chen, Erica Chiang, Edward Choi, Octavia Ciora, Paz Dozie-Nnamah, Shaza Elsharief, Matthew Engelhard, Ali Eshragh, Jean Feng, Josh Fessel, Scott Fleming, Kei Sen Fong, Thomas Frost, Soham Gadgil, Judy Gichoya, Leeor Hershkovich, Sujeong Im, Bhavya Jain, Vincent Jeanselme, Furong Jia, Qixuan Jin, Yuxuan Jin, Daniel Kapash, Geetika Kapoor, Behdokht Kiafar, Matthias Kleiner, Stefan Kraft, Annika Kumar, Daeun Kyung, Zhongyuan Liang, Joanna Lin, Qianchu Liu, Chang Liu, Hongzhou Luan, Chris Lunt, Leopoldo Julían Lechuga López, Matthew B. A. McDermott, Shahriar Noroozizadeh, Connor O'Brien, YongKyung Oh, Mixail Ota, Stephen Pfohl, Meagan Pi, Tanmoy Sarkar Pias, Emma Rocheteau, Avishaan Sethi, Toru Shirakawa, Anita Silver, Neha Simha, Kamile Stankeviciute, Max Sunog, Peter Szolovits, Shengpu Tang, Jialu Tang, Aaron Tierney, John Valdovinos, Byron Wallace, Will Ke Wang, Peter Washington, Jeremy Weiss, Daniel Wolfe, Emily Wong, Hye Sun Yun, Xiaoman Zhang, Xiao Yu Cindy Zhang, Hayoung Jeong, Kaveri A. Thakoor

机构 * IBM 纠错

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