语言大模型 / LLM

EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models

Xiaoming Hou, Jiquan Zhang, Zibin Lin, DaCheng Tao, Shengli Zhang

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

Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes

Zhiyao Xu, Dan Zhao, Qingsong Zou, Qing Li, Yong Jiang, Yuhang Wang, Jingyu Xiao

机构 * Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院） ； Peng Cheng Laboratory（鹏城实验室） ； Southwest University（西南大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice

Yuanpeng Li, Qi Long, Zhiyuan Yao, Jian Xu, Lintao Xie, Xu He, Lu Geng, Xin Han, Yueyan Chen, Wenbo Duan

机构 * ByteDance（字节跳动） ； Carnegie Mellon University（卡内基梅隆大学） ； Zhejiang University（浙江大学） 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

Frontier: Simulating the Next Generation of LLM Inference Systems

Yicheng Feng, Xin Tan, Kin Hang Sew, Yimin Jiang, Yibo Zhu, Hong Xu

机构 * The Chinese University of Hong Kong（香港中文大学） ； StepFun 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

Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective

Garry A. Gabison, R. Patrick Xian

机构 * Queen Mary University of London（伦敦女王大学） ； UC Berkeley（伯克利大学） ； Certivize AI ； UC San Francisco（旧金山大学） 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 22 pages (incl. appendix), accepted at REALM workshop, ACL2025

Learning to Incentivize: LLM-Empowered Contract for AIGC Offloading in Teleoperation

Zijun Zhan, Yaxian Dong, Daniel Mawunyo Doe, Yuqing Hu, Shuai Li, Shaohua Cao, Zhu Han

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

Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis

Yifan Yang, Shujie Liu, Jinyu Li, Yuxuan Hu, Haibin Wu, Hui Wang, Jianwei Yu, Lingwei Meng, Haiyang Sun, Yanqing Liu, Yan Lu, Kai Yu, Xie Chen

机构 * Shanghai Jiao Tong University（上海交通大学） ； Microsoft Corporation（微软公司） ； Shanghai Jiao Tong University, Shanghai Innovation Institute（上海交通大学上海创新研究院） 纠错

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

Comments Accepted in ACMMM 2025

Efficient Agents: Building Effective Agents While Reducing Cost

Ningning Wang, Xavier Hu, Pai Liu, He Zhu, Yue Hou, Heyuan Huang, Shengyu Zhang, Jian Yang, Jiaheng Liu, Ge Zhang, Changwang Zhang, Jun Wang, Yuchen Eleanor Jiang, Wangchunshu Zhou

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 Work in progress. For GitHub repository, see https://github.com/OPPO-PersonalAI/OAgents

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models

Jiabing Yang, Chenhang Cui, Yiyang Zhou, Yixiang Chen, Peng Xia, Ying Wei, Tao Yu, Yan Huang, Liang Wang

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

AQUAH: Automatic Quantification and Unified Agent in Hydrology

Songkun Yan, Zhi Li, Siyu Zhu, Yixin Wen, Mofan Zhang, Mengye Chen, Jie Cao, Yang Hong

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

Comments 8 pages, 5 figures, 2025 ICCV SEA workshop paper

Agentic Privacy-Preserving Machine Learning

Mengyu Zhang, Zhuotao Liu, Jingwen Huang, Xuanqi Liu

机构 * 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

OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving Framework

Jiaxi Li, Lu Yin, Xilu Wang

机构 * Computer Science Research Centre University of Surrey Guildford, United Kingdom（计算机科学研究中心 英国萨里大学 吉尔福德） 纠错

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

Comments IJCNN2025

Real-time speech enhancement in noise for throat microphone using neural audio codec as foundation model

Julien Hauret, Thomas Joubaud, Éric Bavu

专题命中 效率与部署 ：foundation model(title)

Comments 2 pages, 2 figures

Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health

Xingbo Wang, Janessa Griffith, Daniel A. Adler, Joey Castillo, Tanzeem Choudhury, Fei Wang

机构 * Weill Cornell Medicine, \ University New York NY USA ； Weill Cornell Medicine, \ University 纠错

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

Comments Accepted to CHI Conference on Human Factors in Computing Systems (CHI 2025). Code is available at https://github.com/xingbow/sleephealthLLM

Key-Augmented Neural Triggers for Knowledge Sharing

Alex Wolf, Marco Edoardo Palma, Pooja Rani, Harald C. Gall

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

How Can Objects Help Video-Language Understanding?

Zitian Tang, Shijie Wang, Junho Cho, Jaewook Yoo, Chen Sun

机构 * Brown University（布朗大学） ； Samsung Electronics（三星电子） 纠错

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

SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec

Chunyu Qiang, Haoyu Wang, Cheng Gong, Tianrui Wang, Ruibo Fu, Tao Wang, Ruilong Chen, Jiangyan Yi, Zhengqi Wen, Chen Zhang, Longbiao Wang, Jianwu Dang, Jianhua Tao

机构 * School of New Media and Communication, Tianjin University（新媒体与传播学院，天津大学） ； Kuaishou Technology（快手科技） ； Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University（认知计算与应用重点实验室，智能计算学院，天津大学） ； Department of Automation, BNRist, Tsinghua University（自动化系，北研所，清华大学） ； Shenzhen Institute of Advanced Technology, Chinese Academy of Science（深圳先进技术研究院，中国科学院） 纠错

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

Efficient Morphology-Aware Policy Transfer to New Embodiments

Michael Przystupa, Hongyao Tang, Martin Jagersand, Santiago Miret, Mariano Phielipp, Matthew E. Taylor, Glen Berseth

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

Comments 19 pages, 10 Figures, Published at the 2025 Reinforcement Learning Conference

Adaptive AI Agent Placement and Migration in Edge Intelligence Systems

Xingdan Wang, Jiayi He, Zhiqing Tang, Jianxiong Guo, Jiong Lou, Liping Qian, Tian Wang, Weijia Jia

机构 * Institute of Artificial Intelligence and Future Networks, Beijing Normal University, China（人工智能与未来网络研究院，北京师范大学，中国） ； Faculty of Arts and Sciences, Beijing Normal University, China（文理学院，北京师范大学，中国） ； Department of Computer Science and Engineering, Shanghai Jiao Tong University, China（计算机科学与工程系，上海交通大学，中国） ； College of Information Engineering, Zhejiang University of Technology, China（信息工程学院，浙江工业大学，中国） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models

Jisoo Kim, Wooseok Seo, Junwan Kim, Seungho Park, Sooyeon Park, Youngjae Yu

机构 * Yonsei University（延世大学） 纠错

专题命中 效率与部署 ：SFT(abstract)；分类 cs.AI

Comments ICCV2025 accepted

CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base

Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu, Shuai Zhao, Thong Nguyen, Anh Tuan Luu

机构 * Nanyang Technological University, Singapore（南洋理工大学） ； National University of Singapore, Singapore（国立新加坡大学） 纠错

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

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging

Leon Götz, Marcel Kollovieh, Stephan Günnemann, Leo Schwinn

机构 * Technical University of Munich（慕尼黑技术大学） ； Munich Data Science Institute（慕尼黑数据科学研究所） ； Munich Center for Machine Learning（慕尼黑机器学习中心） 纠错

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

Comments 21 pages in total, 20 figures

Mamba-X: An End-to-End Vision Mamba Accelerator for Edge Computing Devices

Dongho Yoon, Gungyu Lee, Jaewon Chang, Yunjae Lee, Dongjae Lee, Minsoo Rhu

专题命中 效率与部署 ：language model(abstract)

Comments Accepted for publication at the 44th International Conference on Computer-Aided Design (ICCAD), 2025