语言大模型 / LLM

Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model

Biao Zhang, Yong Cheng, Siamak Shakeri, Xinyi Wang, Min Ma, Orhan Firat

机构 * Google DeepMind（谷歌DeepMind） 纠错

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

Comments The scaling study inspiring T5Gemma

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives

Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang

机构 * State Key Laboratory for Multimedia Information Processing, School of Computer Science, PKU-Anker LLM Lab, Peking University（信息处理国家重点实验室，计算机学院，PKU-Anker LLM实验室，北京大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； University of Washington（华盛顿大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Nanyang Technological University（南洋理工大学） ； HKUST（香港科技大学） ； University of International Business and Economics（国际商务经济大学） 纠错

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

Comments ACL 2025

1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models

Zeliang Zong, Kai Zhang, Zheyang Li, Wenming Tan, Ye Ren, Yiyan Zhai, Jilin Hu

机构 * Hikvision Research Institute（海康威视研究院） ； School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院） 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

Comments 15 pages, 6 figures, EMNLP 2025 findings

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models

Weifei Jin, Yuxin Cao, Junjie Su, Minhui Xue, Jie Hao, Ke Xu, Jin Song Dong, Derui Wang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； National University of Singapore（新加坡国立大学） ； CSIRO’s Data61（CSIRO数据61） ； Responsible AI Research (RAIR) Centre, The University of Adelaide（负责任人工智能研究（RAIR）中心，阿德莱德大学） ； Tsinghua University（清华大学） 纠错

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

Comments Accepted to NeurIPS 2025

HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location

Ting Sun, Penghan Wang, Fan Lai

机构 * Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机与数据科学学院） ； Department of Computer Science, Purdue University（普渡大学计算机科学系） 纠错

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

Comments NeurIPS 2025. 21 pages, 17 figures

RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation

Min Hou, Chenxi Bai, Le Wu, Hao Liu, Kai Zhang, Weiwen Liu, Richang Hong, Ruiming Tang, Meng Wang

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

The Era of Agentic Organization: Learning to Organize with Language Models

Zewen Chi, Li Dong, Qingxiu Dong, Yaru Hao, Xun Wu, Shaohan Huang, Furu Wei

机构 * Microsoft Research（微软研究院） 纠错

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

Wisdom and Delusion of LLM Ensembles for Code Generation and Repair

Fernando Vallecillos-Ruiz, Max Hort, Leon Moonen

机构 * Simula Research Laboratory（Simula研究实验室） 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.LG

Comments Added Acknowledgments section and hyphenated last names

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

Jaewon Chu, Seunghun Lee, Hyunwoo J. Kim

机构 * Korea University（韩国大学） ； KAIST（韩国科学技术院） 纠错

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

Comments Accepted to NeurIPS 2025

LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding

Yuchen Ma, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel

机构 * Munich Center for Machine Learning（慕尼黑机器学习中心） ； LMU Munich（慕尼黑大学） 纠错

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

Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation

Woojin Kim, Jaeyoung Do

机构 * AIDAS Laboratory（AIDAS实验室） ； ECE（电子工程系） ； APAI（人工智能院） 纠错

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

Comments Accepted in NeurIPS 2025

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning

Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar, Amin Saied

机构 * Microsoft Responsible AI Research（微软负责任人工智能研究） ； University of California（加州大学） 纠错

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

Application and Validation of Geospatial Foundation Model Data for the Prediction of Health Facility Programmatic Outputs -- A Case Study in Malawi

Lynn Metz, Rachel Haggard, Michael Moszczynski, Samer Asbah, Chris Mwase, Patricia Khomani, Tyler Smith, Hannah Cooper, Annie Mwale, Arbaaz Muslim, Gautam Prasad, Mimi Sun, Tomer Shekel, Joydeep Paul, Anna Carter, Shravya Shetty, Dylan Green

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

Comments 13 pages, 3010 words, 2 tables, 2 figures

Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM

Jiachen Li, Xiwen Li, Justin Steinberg, Akshat Choube, Bingsheng Yao, Xuhai Xu, Dakuo Wang, Elizabeth Mynatt, Varun Mishra

机构 * Northeastern University（东北大学） ； Columbia University（哥伦比亚大学） 纠错

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

Comments Jiachen Li, Xiwen Li, Justin Steinberg, Akshat Choube, Bingsheng Yao, Xuhai Xu, Dakuo Wang, Elizabeth Mynatt, and Varun Mishra. 2025. Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-in-the-Loop LLM. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9, 3, Article 101 (September 2025), 37 pages

Journal ref Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9 (2025) 101:1-37

Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual

Sukrit Sriratanawilai, Jhayahgrit Thongwat, Romrawin Chumpu, Patomporn Payoungkhamdee, Sarana Nutanong, Peerat Limkonchotiwat

机构 * VISTEC ； AI Singapore 纠错

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

Comments Work in progress

BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models

Patrick Haller, Jonas Golde, Alan Akbik

机构 * Humboldt-Universität zu Berlin（柏林洪堡大学） 纠错

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

Comments 7 pages, 7 figures and tables, Published in Proceedings of the BabyLM Challenge 2025

Journal ref In Proceedings of the 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning, CoNLL 2024, pages 82 to 94, Miami, FL, USA. Association for Computational Linguistics

Oneiros: KV Cache Optimization through Parameter Remapping for Multi-tenant LLM Serving

Ruihao Li, Shagnik Pal, Vineeth Narayan Pullu, Prasoon Sinha, Jeeho Ryoo, Lizy K. John, Neeraja J. Yadwadkar

专题命中 效率与部署 ：LLM(title,abstract)

ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems

Qiaoling Chen, Zijun Liu, Peng Sun, Shenggui Li, Guoteng Wang, Ziming Liu, Yonggang Wen, Siyuan Feng, Tianwei Zhang

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

MossNet: Mixture of State-Space Experts is a Multi-Head Attention

Shikhar Tuli, James Seale Smith, Haris Jeelani, Chi-Heng Lin, Abhishek Patel, Vasili Ramanishka, Yen-Chang Hsu, Hongxia Jin

机构 * Samsung Research America（三星美国研究院） 纠错

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

Beyond Benchmarks: The Economics of AI Inference

Boqin Zhuang, Jiacheng Qiao, Mingqian Liu, Mingxing Yu, Ping Hong, Rui Li, Xiaoxia Song, Xiangjun Xu, Xu Chen, Yaoyao Ma, Yujie Gao

机构 * WiNGPT Team（WiNGPT团队） 纠错

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

DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving

Mingyu Yang, Jae-Young Choi, Kihyo Moon, Minsung Jang, Eunjoo Jeon

机构 * Cloud Research Team, Samsung SDS（三星SDS云研究团队） 纠错

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

Comments Accepted for presentation at the IEEE BigData 2025 Workshop (Special Session on Intelligent Data Mining). This v2 updates formatting and adds IEEE copyright notice

Defeating the Training-Inference Mismatch via FP16

Penghui Qi, Zichen Liu, Xiangxin Zhou, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin

机构 * Sea AI Lab ； National University of Singapore（新加坡国立大学） 纠错

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

CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

Hao Li, Shuai Yang, Yilun Chen, Xinyi Chen, Xiaoda Yang, Yang Tian, Hanqing Wang, Tai Wang, Dahua Lin, Feng Zhao, Jiangmiao Pang

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

Comments 39 pages, 24 figures

zFLoRA: Zero-Latency Fused Low-Rank Adapters

Dhananjaya Gowda, Seoha Song, Harshith Goka, Junhyun Lee

机构 * Samsung Research（三星研究院） 纠错

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

RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching

Farnoush Rezaei Jafari, Oliver Eberle, Ashkan Khakzar, Neel Nanda

机构 * Machine Learning Group, Technische Universität Berlin（柏林技术大学机器学习组） ； BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究院） 纠错

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

Angular Steering: Behavior Control via Rotation in Activation Space

Hieu M. Vu, Tan M. Nguyen

机构 * Torilab ； Department of Mathematics National University of Singapore（数学系，新加坡国立大学） 纠错

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

Comments NeurIPS 2025 (Spotlight)

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

Hao Mark Chen, Guanxi Lu, Yasuyuki Okoshi, Zhiwen Mo, Masato Motomura, Hongxiang Fan

机构 * Imperial College London, UK（伦敦帝国学院） ； Institute of Science Tokyo, Japan（东京科学研究所） 纠错

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

Comments Accepted at NeurIPS 2025

ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference

Zixu Shen, Kexin Chu, Yifan Zhang, Dawei Xiang, Runxin Wu, Wei Zhang

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

Comments 12 pages, 11 figures

Polybasic Speculative Decoding Through a Theoretical Perspective

Ruilin Wang, Huixia Li, Yuexiao Ma, Xiawu Zheng, Fei Chao, Xuefeng Xiao, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception（多媒体可信感知关键实验室） ； Efficient Computing, Ministry of Education of China, Xiamen University（高效计算、教育部中国 ministry of education、厦门大学） ； Institute of Artificial Intelligence, Xiamen University（人工智能研究院、厦门大学） ； Peng Cheng Laboratory, Shenzhen, China（鹏城实验室、深圳中国） 纠错

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

Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search

Guochang Li, Yuchen Liu, Zhen Qin, Yunkun Wang, Jianping Zhong, Chen Zhi, Binhua Li, Fei Huang, Yongbin Li, Shuiguang Deng

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