语言大模型 / LLM

Experience Scaling: Post-Deployment Evolution For Large Language Models

Xingkun Yin, Kaibin Huang, Dong In Kim, Hongyang Du

机构 * Department of Electrical and Electronic Engineering, University of Hong Kong（香港大学电子与电气工程系） ； Department of Electrical and Computer Engineering, Sungkyunkwan University（成均馆大学电子与计算机工程系） 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.AI

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis

Run Luo, Ting-En Lin, Haonan Zhang, Yuchuan Wu, Xiong Liu, Min Yang, Yongbin Li, Longze Chen, Jiaming Li, Lei Zhang, Xiaobo Xia, Hamid Alinejad-Rokny, Fei Huang

机构 * Shenzhen Key Laboratory for High Performance Data Mining（深圳高性能数据挖掘重点实验室） ； Shenzhen Institute of Advanced Technology（深圳先进技术研究院） ； Chinese Academy of Sciences（中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Tongyi Laboratory（通义实验室） ； University of New South Wales（新南威尔士大学） ； National University of Singapore（新加坡国立大学） ； University of Science and Technology of China（中国科学技术大学） ； MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition（脑启发智能感知与认知重点实验室） 纠错

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

Automating Steering for Safe Multimodal Large Language Models

Lyucheng Wu, Mengru Wang, Ziwen Xu, Tri Cao, Nay Oo, Bryan Hooi, Shumin Deng

机构 * Zhejiang University（浙江大学） ； Zhejiang University - Ant Group Joint Lab of Knowledge Graph（浙江大学-蚂蚁集团知识图谱联合实验室） ； National University of Singapore, NUS-NCS Joint Lab（新加坡国立大学NUS-NCS联合实验室） 纠错

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

Comments EMNLP 2025 Main Conference. 23 pages (8+ for main); 25 figures; 1 table

SBVR: Summation of BitVector Representation for Efficient LLM Quantization

Wonjun Bang, Jongseok Park, Hongseung Yu, Kyungmin Bin, Kyunghan Lee

机构 * Seoul National University（首尔国立大学） 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 9 pages, 4 figures

FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction

Yuxuan Cai, Xiaozhuan Liang, Xinghua Wang, Jin Ma, Haijin Liang, Jinwen Luo, Xinyu Zuo, Lisheng Duan, Yuyang Yin, Xi Chen

机构 * Tencent（腾讯） 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

Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models

Xijun Wang, Junyun Huang, Rayyan Abdalla, Chengyuan Zhang, Ruiqi Xian, Dinesh Manocha

机构 * University of Maryland, College Park（马里兰大学） 纠错

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

Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs

Marcin Chrapek, Marcin Copik, Etienne Mettaz, Torsten Hoefler

机构 * ETH Zurich（苏黎世联邦理工学院） 纠错

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

Reflect before Act: Proactive Error Correction in Language Models

Qiuhai Zeng, Sarvesh Rajkumar, Di Wang, Narendra Gyanchandani, Wenbo Yan

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Amazon（亚马逊） 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

MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM Acceleration

Tatsuya Kubo, Daichi Tokuda, Tomoya Nagatani, Masayuki Usui, Lei Qu, Ting Cao, Shinya Takamaeda-Yamazaki

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

Language Models Resist Alignment: Evidence From Data Compression

Jiaming Ji, Kaile Wang, Tianyi Qiu, Boyuan Chen, Jiayi Zhou, Changye Li, Hantao Lou, Juntao Dai, Yunhuai Liu, Yaodong Yang

机构 * Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； School of Computer Science, Peking University（北京大学计算机科学学院） 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

Comments Accepted by ACL2025 Main

A Study of Skews, Imbalances, and Pathological Conditions in LLM Inference Deployment on GPU Clusters detectable from DPU

Javed I. Khan an Henry Uwabor Moye

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

Comments 12 pages, Technical Report 2025-07-01, Internetworking and Media Communications Research Laboratories, Department of Computer Science, Kent State University

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner

Bolian Li, Yanran Wu, Xinyu Luo, Ruqi Zhang

机构 * Department of Computer Science, Purdue University（计算机科学系，普渡大学） 纠错

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

Comments EMNLP 2025 Main Conference

MobiGPT: A Foundation Model for Mobile Wireless Networks

Xiaoqian Qi, Haoye Chai, Yong Li

机构 * Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, China（电子工程系，信息科学与技术国家研究中心（BNRist），清华大学，北京） 纠错

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

ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts

Amelia F. Hardy, Houjun Liu, Allie Griffith, Bernard Lange, Duncan Eddy, Mykel J. Kochenderfer

机构 * Stanford University（斯坦福大学） 纠错

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

Comments 8 pages, 7 pages of appendix, 3 tables, 4 figures

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation

Lianwei Yang, Haokun Lin, Tianchen Zhao, Yichen Wu, Hongyu Zhu, Ruiqi Xie, Zhenan Sun, Yu Wang, Qingyi Gu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） ； School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院） ； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） 纠错

专题命中 效率与部署 ：post-training(title,abstract)

LCMF: Lightweight Cross-Modality Mambaformer for Embodied Robotics VQA

Zeyi Kang, Liang He, Yanxin Zhang, Zuheng Ming, Kaixing Zhao

机构 * School of Software Northwestern Polytechnical University Xi'an, China（软件学院 西安理工大学中国） ； Laboratoire L2Tl University Sorbonne Paris Nord Paris, France（L2Tl实验室 索邦巴黎北大学巴黎法国） 纠错

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

Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash

Fucheng Jia, Zewen Wu, Shiqi Jiang, Huiqiang Jiang, Qianxi Zhang, Yuqing Yang, Yunxin Liu, Ju Ren, Deyu Zhang, Ting Cao

机构 * Central South University（中南大学） ； Tsinghua University University（清华大学） ； Microsoft Research（微软研究院） ； Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学） ； Tsinghua University（清华大学） 纠错

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

LightThinker: Thinking Step-by-Step Compression

Jintian Zhang, Yuqi Zhu, Mengshu Sun, Yujie Luo, Shuofei Qiao, Lun Du, Da Zheng, Huajun Chen, Ningyu Zhang

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

Comments EMNLP 2025 (oral)

StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs

Hanchen Ye, Deming Chen

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

Comments Accepted by MICRO'25

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs

Jindong Jiang, Xiuyu Li, Zhijian Liu, Muyang Li, Guo Chen, Zhiqi Li, De-An Huang, Guilin Liu, Zhiding Yu, Kurt Keutzer, Sungjin Ahn, Jan Kautz, Hongxu Yin, Yao Lu, Song Han, Wonmin Byeon

机构 * NVIDIA（英伟达） ； Rutgers University（罗格斯大学） ； UC Berkeley（加州大学伯克利分校） ； MIT（麻省理工学院） ； Nanjing University（南京大学） ； KAIST（韩国科学技术院） 纠错

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

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration

Chunhao Tian, Yutong Wang, Xuebo Liu, Zhexuan Wang, Liang Ding, Miao Zhang, Min Zhang

专题命中 效率与部署 ：LLM(title)；分类 cs.AI

Comments EMNLP 2025 Findings

Abduct, Act, Predict: Scaffolding Causal Inference for Automated Failure Attribution in Multi-Agent Systems

Alva West, Yixuan Weng, Minjun Zhu, Zhen Lin, Zhiyuan Ning, Yue Zhang

机构 * School of Engineering, Westlake University（西湖大学工程学院） 纠错

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

Detection of security smells in IaC scripts through semantics-aware code and language processing

Aicha War, Adnan A. Rawass, Abdoul K. Kabore, Jordan Samhi, Jacques Klein, Tegawende F. Bissyande

机构 * University of Luxembourg（卢森堡大学） 纠错

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

CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs

Jin Young Kim, Ji Won Yoon

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

Comments Published as a main conference paper at EMNLP 2025

Towards General Computer Control with Hierarchical Agents and Multi-Level Action Spaces

Zihan Dong, Xinyu Fan, Zixiang Tang, Yunqing Li

机构 * The University of Tokyo（东京大学） ； Lenovo US（联想美国） ； Advanced AI Technology Center（高级人工智能技术中心） 纠错

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

Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass

Nicholas Popovič, Michael Färber

机构 * TU Dresden（德累斯顿技术大学） 纠错

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

Comments EMNLP 2025

FlexSED: Towards Open-Vocabulary Sound Event Detection

Jiarui Hai, Helin Wang, Weizhe Guo, Mounya Elhilali

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； 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(abstract)；language model(abstract)；分类 cs.AI

Automatic coherence-driven inference on arguments

Steve Huntsman

机构 * Steve Huntsman（独立研究者） 纠错

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

Comments Workshop on Data Mining and AI for Law (https://dmail-workshop.github.io/DMAIL2025/)

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, Bokai Xu, Junbo Cui, Yingjing Xu, Liqing Ruan, Luoyuan Zhang, Hanyu Liu, Jingkun Tang, Hongyuan Liu, Qining Guo, Wenhao Hu, Bingxiang He, Jie Zhou, Jie Cai, Ji Qi, Zonghao Guo, Chi Chen, Guoyang Zeng, Yuxuan Li, Ganqu Cui, Ning Ding, Xu Han, Yuan Yao, Zhiyuan Liu, Maosong Sun

机构 * MiniCPM-V Team, OpenBMB（MiniCPM-V团队，OpenBMB） 纠错

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

Comments Project Website: https://github.com/OpenBMB/MiniCPM-V

Knowledge Transfer from Interaction Learning

Yilin Gao, Kangyi Chen, Zhongxing Peng, Hengjie Lu, Shugong Xu

机构 * Shanghai University（上海大学） ； Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学） 纠错

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

Comments Accepted by ICCV2025