语言大模型 / LLM

2509.17136 2025-09-23 cs.CV cs.AI 74%

SAEC: Scene-Aware Enhanced Edge-Cloud Collaborative Industrial Vision Inspection with Multimodal LLM

Yuhao Tian, Zheming Yang

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； Institute of AI for Industries（工业人工智能研究所）

专题命中效率与部署：LLM(title)；分类 cs.AI

Comments 5 pages, 5 figures

2509.17788 2025-09-23 cs.CL cs.AI 73%

One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts

Xingyu Fan, Feifei Li, Wenhui Que, Hailong Li

专题命中效率与部署：preference optimization(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 7 pages

2507.22424 2025-09-23 cs.LG cs.AI 73%

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance

Songsheng Wang, Rucheng Yu, Zhihang Yuan, Chao Yu, Feng Gao, Yu Wang, Derek F. Wong

机构 * NICS-EFC Lab, Department of Electronic Engineering, Tsinghua University（清华大学电子工程系NICS-EFC实验室）； Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）； Infinigence AI ； Tsinghua University（清华大学）； Zhongguancun Academy（中关村学院）

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

Comments 13 pages, 5 figures, Accepted by EMNLP 2025 (main conference)

2509.17791 2025-09-23 cs.LG 70%

Elucidating the Design Space of FP4 training

Robert Hu, Carlo Luschi, Paul Balanca

机构 * Graphcore London, UK（Graphcore伦敦）

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

2509.17493 2025-09-23 cs.CL 70%

Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages

Wenhao Zhuang, Yuan Sun, Xiaobing Zhao

机构 * Minzu University of China（中国民族大学）； National Language Resource Monitoring & Research Center Minority Languages Branch（国家语言资源监测与研究中心少数民族语言分部）； Institute of National Security, Minzu University of China（中国民族大学国家安全学院）

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

2509.15250 2025-09-23 cs.CV cs.AI 70%

Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning

Wenda Qin, Andrea Burns, Bryan A. Plummer, Margrit Betke

机构 * Boston University（波士顿大学）

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

Comments Accepted to EMNLP 2025. Data and code to be released at https://github.com/wdqin/VLN-NAP

2508.17343 2025-09-23 cs.SE cs.AI 70%

Agentic AI for Software: thoughts from Software Engineering community

Abhik Roychoudhury

机构 * NUS（国立新加坡大学）； SonarSource SA

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

Comments 4 pages

2502.01960 2025-09-23 cs.LG 70%

MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving

Shiju Zhao, Junhao Hu, Rongxiao Huang, Jiaqi Zheng, Guihai Chen

机构 * State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）； Nanjing University（南京大学）； School of Computer Science（计算机学院）

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

Comments 17 pages, 13 figures, the second version

2509.15059 2025-09-23 cs.HC cs.CV 67%

QuizRank: Picking Images by Quizzing VLMs

Tenghao Ji, Eytan Adar

机构 * University of Michigan（密歇根大学）

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

2509.16633 2025-09-23 cs.CV cs.AI cs.CL 62%

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

Abhirama Subramanyam Penamakuri, Navlika Singh, Piyush Arora, Anand Mishra

机构 * Indian Institute of Technology Jodhpur（印度理工学院朱诺尔）

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

Comments Accepted to EMNLP (Main) 2025

2506.00073 2025-09-23 cs.AI cs.CL cs.CY cs.HC cs.MA 62%

The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets

Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South, Alex Pentland, Jiaxin Pei

机构 * Stanford University（斯坦福大学）； University of Toronto（多伦多大学）； Google DeepMind（谷歌DeepMind）； University of Southern California（南加州大学）； Massachusetts Institute of Technology（麻省理工学院）

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

2509.17406 2025-09-23 cs.CV cs.AI 57%

Real-Time Fish Detection in Indonesian Marine Ecosystems Using Lightweight YOLOv10-nano Architecture

Jonathan Wuntu, Muhamad Dwisnanto Putro, Rendy Syahputra

机构 * Dept. of Electrical Engineering Sam Ratulangi University（电气工程系萨姆·拉图兰吉大学）

专题命中效率与部署：prompting(abstract)；分类 cs.AI

2509.18005 2025-09-23 cs.RO 50%

M3ET: Efficient Vision-Language Learning for Robotics based on Multimodal Mamba-Enhanced Transformer

Yanxin Zhang, Liang He, Zeyi Kang, 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西安）； Laboratoire L2Tl University Sorbonne Paris Nord Paris, France（L2Tl实验室索邦巴黎北大学巴黎）

专题命中效率与部署：pretraining(abstract)

Comments 8 pages

2509.17323 2025-09-23 cs.CV cs.RO eess.IV 50%

DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking

Buyin Deng, Lingxin Huang, Kai Luo, Fei Teng, Kailun Yang

机构 * School of Artificial Intelligence and Robotics, Hunan University（人工智能与机器人学院，湖南大学）

专题命中效率与部署：foundation model(abstract)

Comments The source code will be made publicly available at https://github.com/warriordby/DepTR-MOT

2509.17021 2025-09-23 cs.SD eess.AS 50%

Bridging the gap between training and inference in LM-based TTS models

Ruonan Zhang, Lingzhou Mu, Xixin Wu, Kai Zhang

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

专题命中效率与部署：language model(abstract)

Comments 5 pages, 4 figures

2509.16571 2025-09-23 q-bio.QM 50%

Enhancing Antimicrobial Molecule Prediction via Dynamic Routing Capsule Networks and Multi-Source Molecular Embeddings

R. He

专题命中效率与部署：language model(abstract)

2509.16476 2025-09-23 cs.CV 50%

Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs

Qinyu Chen, Jiawen Qi

机构 * Leiden Institute of Advanced Computer Science (LIACS)（莱顿先进计算机科学研究所）

专题命中效率与部署：language model(abstract)

Comments 11 pages

2509.16618 2025-09-23 cs.CV cs.AI 89%

Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic Surgery

Pengfei Hao, Hongqiu Wang, Shuaibo Li, Zhaohu Xing, Guang Yang, Kaishun Wu, Lei Zhu

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； Imperial College London（帝国理工学院伦敦分校）； The Hong Kong University of Science and Technology（香港科学与技术大学）

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments Early accepted by MICCAI2025

2405.04760 2025-09-23 cs.CR cs.AI 89%

Large Language Models for Cyber Security: A Systematic Literature Review

Hanxiang Xu, Shenao Wang, Ningke Li, Kailong Wang, Yanjie Zhao, Kai Chen, Ting Yu, Yang Liu, Haoyu Wang

机构 * Huazhong University of Science and Technology（华中科技大学）； Hamad Bin Khalifa University（哈马德·本·卡伊夫大学）； Nanyang Technological University（南洋理工大学）

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments Accepted by ACM Transactions on Software Engineering and Methodology (TOSEM)

2508.00742 2025-09-23 cs.CL cs.LG 88%

Applying Psychometrics to Large Language Model Simulated Populations: Recreating the HEXACO Personality Inventory Experiment with Generative Agents

Sarah Mercer, Daniel P. Martin, Phil Swatton

机构 * The Alan Turing Institute（艾伦·图灵研究所）

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.LG

2509.16413 2025-09-23 cs.CL cs.AI 87%

Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research

Richard Diehl Martinez, David Demitri Africa, Yuval Weiss, Suchir Salhan, Ryan Daniels, Paula Buttery

机构 * University of Cambridge（剑桥大学）

专题命中领域大模型：language model(title,abstract)；small language model(title)；分类 cs.CL、cs.AI

2509.17280 2025-09-23 q-bio.NC cs.AI 85%

From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?

Thomas Serre, Ellie Pavlick

专题命中领域大模型：foundation model(title,abstract)；language model(abstract)；pretraining(abstract)；分类 cs.AI

2509.16682 2025-09-23 cs.CR cs.AI 85%

Design and Development of an Intelligent LLM-based LDAP Honeypot

Javier Jiménez-Román, Florina Almenares-Mendoza, Alfonso Sánchez-Macián

专题命中领域大模型：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2509.16446 2025-09-23 cs.IR cs.CL 83%

Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval

Ruohan Zhang, Jiacheng Li, Julian McAuley, Yupeng Hou

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

2509.07755 2025-09-23 cs.CL cs.CR 83%

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts

Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng, Qian Lou

机构 * University of Central Florida（中央佛罗里达大学）

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted at EMNLP 2025 Findings. Camera Ready

2506.08283 2025-09-23 cs.IR 82%

Serendipitous Recommendation with Multimodal LLM

Haoting Wang, Jianling Wang, Hao Li, Fangjun Yi, Mengyu Fu, Youwei Zhang, Yifan Liu, Liang Liu, Minmin Chen, Ed H. Chi, Lichan Hong, Haokai Lu

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)

Comments Accepted by 2025 Recsys EARL Workshop

2509.03116 2025-09-23 cs.CL 81%

Measuring Scalar Constructs in Social Science with LLMs

Hauke Licht, Rupak Sarkar, Patrick Y. Wu, Pranav Goel, Niklas Stoehr, Elliott Ash, Alexander Miserlis Hoyle

机构 * University of Innsbruck（因斯布鲁克大学）； University of Maryland（马里兰大学）； American University（美国大学）； Northeastern University（东北大学）； ETH Zürich（苏黎世联邦理工学院）

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted to EMNLP 2025 (Main)

2509.16345 2025-09-23 cs.LG cs.AI 81%

Estimating Clinical Lab Test Result Trajectories from PPG using Physiological Foundation Model and Patient-Aware State Space Model -- a UNIPHY+ Approach

Minxiao Wang, Runze Yan, Carol Li, Saurabh Kataria, Xiao Hu, Matthew Clark, Timothy Ruchti, Timothy G. Buchman, Sivasubramanium V Bhavani, Randall J. Lee

机构 * School of Nursing, Emory University（埃默里大学护理学院）； NKDHS, Inc（NKDHS公司）； Emory Healthcare（埃默里医疗集团）； UCSF（加州大学旧金山分校）

专题命中领域大模型：foundation model(title,abstract)；分类 cs.AI、cs.LG

2509.17066 2025-09-23 cs.AI cs.IR 79%

RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking

Kunrong Li, Kwan Hui Lim

机构 * Singapore University of Technology and Design（新加坡科技设计大学）

专题命中领域大模型：LLM(title,abstract)；分类 cs.AI

Comments PRICAI 2025

2509.18091 2025-09-23 cs.IR cs.AI cs.CL 79%

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

Sunhao Dai, Jiakai Tang, Jiahua Wu, Kun Wang, Yuxuan Zhu, Bingjun Chen, Bangyang Hong, Yu Zhao, Cong Fu, Kangle Wu, Yabo Ni, Anxiang Zeng, Wenjie Wang, Xu Chen, Jun Xu, See-Kiong Ng

机构 * Renmin University of China（中国人民大学）； Shopee ； University of Science and Technology of China（中国科学技术大学）； National University of Singapore（新加坡国立大学）

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments OnePiece Technical Report; Applied in Shopee

1. 效率与部署 47 篇

SAEC: Scene-Aware Enhanced Edge-Cloud Collaborative Industrial Vision Inspection with Multimodal LLM

One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance

Elucidating the Design Space of FP4 training

Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages

Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning

Agentic AI for Software: thoughts from Software Engineering community

MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM Serving

QuizRank: Picking Images by Quizzing VLMs

When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets

Real-Time Fish Detection in Indonesian Marine Ecosystems Using Lightweight YOLOv10-nano Architecture

M3ET: Efficient Vision-Language Learning for Robotics based on Multimodal Mamba-Enhanced Transformer

DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking

Bridging the gap between training and inference in LM-based TTS models

Enhancing Antimicrobial Molecule Prediction via Dynamic Routing Capsule Networks and Multi-Source Molecular Embeddings

Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs

2. 领域大模型 26 篇

Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic Surgery

Large Language Models for Cyber Security: A Systematic Literature Review

Applying Psychometrics to Large Language Model Simulated Populations: Recreating the HEXACO Personality Inventory Experiment with Generative Agents

Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research

From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?

Design and Development of an Intelligent LLM-based LDAP Honeypot

Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts

Serendipitous Recommendation with Multimodal LLM

Measuring Scalar Constructs in Social Science with LLMs

Estimating Clinical Lab Test Result Trajectories from PPG using Physiological Foundation Model and Patient-Aware State Space Model -- a UNIPHY+ Approach

RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System