语言大模型 / LLM

GAIA: A General Agency Interaction Architecture for LLM-Human B2B Negotiation & Screening

Siming Zhao, Qi Li

机构 * Alibaba.com US E-Commerce（阿里巴巴美国电子商务） ； Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） 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

Production-Grade Local LLM Inference on Apple Silicon: A Comparative Study of MLX, MLC-LLM, Ollama, llama.cpp, and PyTorch MPS

Varun Rajesh, Om Jodhpurkar, Pooja Anbuselvan, Mantinder Singh, Ashok Jallepali, Shantanu Godbole, Pradeep Kumar Sharma, Hritvik Shrivastava

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

From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge

Hui Lu, Yi Yu, Song Xia, Yiming Yang, Deepu Rajan, Boon Poh Ng, Alex Kot, Xudong Jiang

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

Comments AAAI 2026 (Oral presentation)

GoCkpt: Gradient-Assisted Multi-Step overlapped Checkpointing for Efficient LLM Training

Keyao Zhang, Yiquan Chen, Zhuo Hu, Wenhai Lin, Jiexiong Xu, Wenzhi Chen

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

Comments 12 pages, 10 figures, 1 tables

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism

Jialin Sun, Yuchen Hu, Dean You, Yushu Du, Hui Wang, Xinwei Fang, Weiwei Shan, Nan Guan, Zhe Jiang

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

Comments require revision, update later

Data Trajectory Alignment for LLM Domain Adaptation: A Two-Phase Synthesis Framework for Telecommunications Mathematics

Zhicheng Zhou, Jing Li, Suming Qiu, Junjie Huang, Linyuan Qiu, Zhijie Sun

机构 * Global Technical Service (GTS) Huawei Technologies Co., Ltd（华为技术有限公司全球技术服务部） 纠错

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

From Prompts to Power: Measuring the Energy Footprint of LLM Inference

Francisco Caravaca, Ángel Cuevas, Rubén Cuevas

机构 * UC3M-Santander Big Data Institute（UC3M-桑坦德大数据研究所） 纠错

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

ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction

Wenxuan Wu, Shuai Wang, Xixin Wu, Helen Meng, Haizhou Li

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

Federated Learning for Video Violence Detection: Complementary Roles of Lightweight CNNs and Vision-Language Models for Energy-Efficient Use

Sébastien Thuau, Siba Haidar, Rachid Chelouah

机构 * esieaLab, ETIS Laboratory（esiea实验室，ETIS实验室） ； ESIEA, University of CY Cergy（ESIEA，CY塞克大学） ； ETIS Laboratory, CNR1S, UMR8051（ETIS实验室，CNR1S，UMR8051） 纠错

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

Comments 5 pages, 3 figures, ICTAI 2025

Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements

Patrick Haller, Jonas Golde, Alan Akbik

机构 * Humboldt-Universität zu Berlin（洪堡大学柏林分校） 纠错

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

Journal ref Proceedings of the First BabyLM Workshop 2025, pages 175 to 191, Suzhou, China. Association for Computational Linguistics

LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure

Jaehong Cho, Hyunmin Choi, Jongse Park

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

Comments 4 pages, 3 figures

Journal ref IEEE Computer Architecture Letters (CAL) 2025

How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices

Han Peng, Peiyu Liu, Zican Dong, Daixuan Cheng, Junyi Li, Yiru Tang, Shuo Wang, Wayne Xin Zhao

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； University of International Business and Economics（国际商务经济大学） ； Tsinghua University（清华大学） ； Department of Data Science, City University of Hong Kong（香港城市大学数据科学系） 纠错

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

CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference

Kaijie Xu, Fandi Meng, Clark Verbrugge, Simon Lucas

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

MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modeling

Etienne Le Naour, Tahar Nabil, Ghislain Agoua

机构 * EDF R&D（EDF研究与开发研究院） 纠错

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

Comments 10th Workshop on Advanced Analytics and Learning on Temporal Data (AALTD), ECML 2025

SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

Bohan Yu, Wei Huang, Kang Liu

机构 * Baidu（百度） 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

Comments Accepted by AAAI 2026

Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models

Mayank Saini, Arit Kumar Bishwas

机构 * PwC US（普华永道美国） 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 15 pages, 4 figures

Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

Zhen Xu, Zhen Tan, Song Wang, Kaidi Xu, Tianlong Chen

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

CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling

Zekai Qu, Yinxu Pan, Ao Sun, Chaojun Xiao, Xu Han

机构 * OpenBMB（开放智能实验室） ； Tsinghua University（清华大学） 纠错

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

Comments 13 pages, 4 figures

WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms

Goksenin Yuksel, Pierre Guetschel, Michael Tangermann, Marcel van Gerven, Kiki van der Heijden

机构 * Donders Institute, Radboud University Nijmegen（多纳尔斯研究所，拉德堡德大学尼美根分校） ； Mortimer B Zuckerman Institute, Columbia University（莫蒂默·B·茨克erman研究所，哥伦比亚大学） 纠错

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

Comments Still under review

ZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compression

Zirui Wang, Tingfeng Lan, Zhaoyuan Su, Juncheng Yang, Yue Cheng

专题命中 效率与部署 ：LLM(title,abstract)

TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generation

Qiao Xiao, Hong Ting Tsang, Jiaxin Bai

机构 * Cornell University（康奈尔大学） ； Hong Kong University of Science and Technology（香港理工大学） 纠错

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

Comments 16 pages, 3 figures, 4 tables. Code available at https://github.com/wocqcm2/TERAG

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins

Yigitcan Kaya, Anton Landerer, Stijn Pletinckx, Michelle Zimmermann, Christopher Kruegel, Giovanni Vigna

机构 * University of California, Santa Barbara（加州大学圣巴bara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.AI

Comments At IEEE S&P 2026

AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance

Yuyang Zhao, Wentao Shi, Fuli Feng, Xiangnan He

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

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

Comments Accepted at CIKM 2025. 10 pages, 5 figures. Our code is available at: https://github.com/LaoKuiZe/AppAgent-Pro. The demonstration video could be found at: https://www.dropbox.com/scl/fi/hvzqo5vnusg66srydzixo/AppAgent-Pro-demo-video.mp4?rlkey=o2nlfqgq6ihl125mcqg7bpgqu&st=d29vrzii&dl=0

Journal ref Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025), ACM, 2025

Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training

Elia Cunegatti, Leonardo Lucio Custode, Giovanni Iacca

机构 * University of Trento（特伦托大学） 纠错

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

Comments Published in Transactions on Machine Learning Research (TMLR)

VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving

Ruifei Zhang, Wei Zhang, Xiao Tan, Sibei Yang, Xiang Wan, Xiaonan Luo, Guanbin Li

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； Sun Yat-sen University（中山大学） ； Baidu Inc.（百度公司） ； Guilin University of Electronic Technology（桂林电子科技大学） ； Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室） 纠错

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

Comments Accepted by ICCV2025

Logic Distillation: Learning from Code Function by Function for Decision-making Tasks

Dong Chen, Shilin Zhang, Fei Gao, Yueting Zhuang, Siliang Tang, Qidong Liu, Mingliang Xu

机构 * The School of Computer and Artificial Intelligence of Zhengzhou University（郑州大学计算机与人工智能学院） ； Engineering Research Center of Intelligent Swarm Systems, Ministry of Education（教育部智能群体系统工程研究中心） ； National Supercomputing Center In Zhengzhou（郑州国家超级计算中心） ； Zhejiang University（浙江大学） 纠错

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

Comments 9 pages, 7 figures

UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8

Preston Firestone, Shubham Ugare, Gagandeep Singh, Sasa Misailovic

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

Comments COLM 2025

Optimal Inference Schedules for Masked Diffusion Models

Sitan Chen, Kevin Cong, Jerry Li

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

Comments 33 pages, 1 figure. [added discussion of additional related work]

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Aayush Aluru, Myra Malik, Samarth Patankar, Spencer Kim, Kevin Zhu, Sean O'Brien, Vasu Sharma

机构 * Algoverse AI Research（Algoverse AI研究） 纠错

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

Comments Multi-Turn Interactions in Large Language Models (MTI-LLM) Workshop at NeurIPS 2025

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression

Yilong Chen, Xiang Bai, Zhibin Wang, Chengyu Bai, Yuhan Dai, Ming Lu, Shanghang Zhang

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