语言大模型 / LLM

Meta-Learning for Speeding Up Large Model Inference in Decentralized Environments

Yipeng Du, Zihao Wang, Ahmad Farhan, Claudio Angione, Harry Yang, Fielding Johnston, James P. Buban, Patrick Colangelo, Yue Zhao, Yuzhe Yang

机构 * Nesa Research（Nesa研究机构） 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 COLM2025

Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

Xu Wang, Chenkai Xu, Yijie Jin, Jiachun Jin, Hao Zhang, Zhijie Deng

机构 * Shanghai Jiao Tong University（上海交通大学） ； University of California San Diego（加州大学圣地亚哥分校） ； Shanghai University（上海大学） 纠错

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

Efficient Inference for Large Reasoning Models: A Survey

Yue Liu, Jiaying Wu, Yufei He, Ruihan Gong, Jun Xia, Liang Li, Hongcheng Gao, Hongyu Chen, Baolong Bi, Jiaheng Zhang, Zhiqi Huang, Bryan Hooi, Stan Z. Li, Keqin Li

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

CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge

Muqing Li, Ning Li, Xin Yuan, Wenchao Xu, Quan Chen, Song Guo, Haijun Zhang

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Hong Kong University of Science and Technology（香港科技大学） ； Guangdong University of Technology（广东工业大学） ； University of Science and Technology Beijing（北京科技大学） 纠错

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

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities

Lilit Grigoryan, Vladimir Bataev, Nikolay Karpov, Andrei Andrusenko, Vitaly Lavrukhin, Boris Ginsburg

机构 * NVIDIA 纠错

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

Comments Accepted to Automatic Speech Recognition and Understanding Workshop (ASRU) 2025

Efficient Speech Translation through Model Compression and Knowledge Distillation

Yasmin Moslem

机构 * ADAPT Centre School of Computer Science and Statistics（ADAPT中心计算机科学与统计学学院） 纠错

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

Comments IWSLT 2025

Journal ref Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)

Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges

Changyuan Zhao, Guangyuan Liu, Ruichen Zhang, Yinqiu Liu, Jiacheng Wang, Jiawen Kang, Dusit Niyato, Zan Li, Xuemin, Shen, Zhu Han, Sumei Sun, Chau Yuen, Dong In Kim

机构 * College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） ； School of Automation, Guangdong University of Technology（广东工业大学自动化学院） ； State Key Laboratory of Integrated Services Networks, Xidian University（西安电子科技大学集成服务网络国家重点实验室） ； Department of Electrical and Computer Engineering, University of Waterloo（滑铁卢大学电气与计算机工程系） ； Department of Computer Science and Engineering, Kyung Hee University（韩国庆熙大学计算机科学与工程系） ； Institute for Infocomm Research, Agency for Science, Technology and Research（科技研究局信息通信研究所） ； Department of Electrical and Computer Engineering, Sungkyunkwan University（庆熙大学电气与计算机工程系） 纠错

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

Comments 21 pages. 9 figures

MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI

Zijun Jiang, Yangdi Lyu

机构 * Microelectronics Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）微电子研究组） 纠错

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

Comments 9 pages, 6 figures, accepted by ICCAD'25

CWFBind: Geometry-Awareness for Fast and Accurate Protein-Ligand Docking

Liyan Jia, Chuan-Xian Ren, Hong Yan

机构 * School of Mathematics, Sun Yat-Sen University（中山大学数学学院） ； Department of Electrical Engineering, City University of Hong Kong（香港城市大学电子工程系） 纠错

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

Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference

Danil Sivtsov, Aleksandr Katrutsa, Ivan Oseledets

机构 * AIRI ； Skoltech（斯克里普钦斯基理工学院） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI

MX-AI: Agentic Observability and Control Platform for Open and AI-RAN

Ilias Chatzistefanidis, Andrea Leone, Ali Yaghoubian, Mikel Irazabal, Sehad Nassim, Lina Bariah, Merouane Debbah, Navid Nikaein

机构 * Communications Department（通讯部门） ； EURECOM ； AI Department（AI部门） ； BubbleRAN ； RIC Department（RIC部门） ； Aalto University（阿莱大学） ； EECS Department（EECS部门） ； Khalifa University（卡利法大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI

Comments This work has been submitted to the IEEE for possible publication

Plug it and Play on Logs: A Configuration-Free Statistic-Based Log Parser

Qiaolin Qin, Xingfang Wu, Heng Li, Ettore Merlo

专题命中 效率与部署 ：language model(abstract)

Evaluating the Role of Large Language Models in Legal Practice in India

Rahul Hemrajani

机构 * National Law School of India（印度国家法律学校） 纠错

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

Specialised or Generic? Tokenization Choices for Radiology Language Models

Hermione Warr, Wentian Xu, Harry Anthony, Yasin Ibrahim, Daniel McGowan, Konstantinos Kamnitsas

机构 * Department of Engineering Science, University of Oxford, Oxford, UK（牛津大学工程科学系） ； Department of Oncology, University of Oxford, UK（牛津大学肿瘤学系） ； Department of Medical Physics and Clinical Engineering, Oxford University Hospitals NHS FT, Oxford, UK（牛津大学医院医学物理与临床工程系） ； Department of Computing, Imperial College London, London, UK（伦敦帝国理工学院计算机系） ； School of Computer Science, University of Birmingham, Birmingham, UK（伯明翰大学计算机科学学院） 纠错

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

Comments Accepted to ELAMI@MICCAI2025

PDEformer-2: A Versatile Foundation Model for Two-Dimensional Partial Differential Equations

Zhanhong Ye, Zining Liu, Bingyang Wu, Hongjie Jiang, Leheng Chen, Minyan Zhang, Xiang Huang, Qinghe Meng. Jingyuan Zou, Hongsheng Liu, Bin Dong

专题命中 领域大模型 ：foundation model(title,abstract)；pretraining(abstract)

Chemist Eye: A Visual Language Model-Powered System for Safety Monitoring and Robot Decision-Making in Self-Driving Laboratories

Francisco Munguia-Galeano, Zhengxue Zhou, Satheeshkumar Veeramani, Hatem Fakhruldeen, Louis Longley, Rob Clowes, Andrew I. Cooper

机构 * Cooper Group, Department of Chemistry, University of Liverpool（Cooper集团，化学系，利物浦大学） 纠错

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

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations

Jordan Vice, Naveed Akhtar, Yansong Gao, Richard Hartley, Ajmal Mian

机构 * University of Western Australia（西澳大学） ； University of Melbourne（墨尔本大学） ； Australian National University（澳大利亚国立大学） 纠错

专题命中 领域大模型 ：language model(title,abstract)

Comments Keywords: Vision-Language Models, Frequency-Domain Perturbations, Adversarial Robustness, Image Authenticity, Reliability

From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training

Yuan Yuan, Tina Sriskandarajah, Anna-Luisa Brakman, Alec Helyar, Alex Beutel, Andrea Vallone, Saachi Jain

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

Capabilities of GPT-5 on Multimodal Medical Reasoning

Shansong Wang, Mingzhe Hu, Qiang Li, Mojtaba Safari, Xiaofeng Yang

机构 * Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine（放射肿瘤科、Winship癌症研究所、埃默里大学医学院） 纠错

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

Comments Corrected some typos

DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning

Linpu He, Yanan Li, Bingze Li, Elvis Han Cui, Donghui Wang

机构 * Department of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术系） ； Research Center for Frontier Fundamental Studies, Zhejiang Lab（浙江实验室前沿基础研究中心） ； Department of Neurology, University of California, Irvine（加州大学伊市医学院神经科） 纠错

专题命中 领域大模型 ：prompting(title)

Comments Accepted to ACMMM 2025

HyperKD: Distilling Cross-Spectral Knowledge in Masked Autoencoders via Inverse Domain Shift with Spatial-Aware Masking and Specialized Loss

Abdul Matin, Tanjim Bin Faruk, Shrideep Pallickara, Sangmi Lee Pallickara

机构 * Colorado State University（科罗拉多州立大学） 纠错

专题命中 领域大模型 ：foundation model(abstract)；分类 cs.LG

Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation

Xuanru Zhou, Cheng Li, Shuqiang Wang, Ye Li, Tao Tan, Hairong Zheng, Shanshan Wang

专题命中 领域大模型 ：foundation model(abstract)；分类 cs.AI

Privacy-Preserving Models for Legal Natural Language Processing

Ying Yin, Ivan Habernal

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

Comments Camera ready, to appear at the Natural Legal Language Processing Workshop 2022 co-located with EMNLP

Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions

Tina Raissi, Nick Rossenbach, Ralf Schlüter

机构 * Human Language Technology Group RWTH Aachen University Aachen, Germany（人类语言技术小组 拉夫·海因里希·魏德廷亚琛大学 德国亚琛） ； Human Language Technology Group RWTH Aachen University AppTek GmbH Aachen, Germany（人类语言技术小组 拉夫·海因里希·魏德廷亚琛大学 AppTek GmbH 德国亚琛） 纠错

专题命中 领域大模型 ：language model(abstract)

Comments Accepted for presentation at IEEE ASRU 2025

Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation

Xujie Yuan, Shimin Di, Jielong Tang, Libin Zheng, Jian Yin

专题命中 领域大模型 ：language model(abstract)

Multimodal LLM-based Query Paraphrasing for Video Search

Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan, Sheng-Hua Zhong, Xiong-Yong Wei, Qing Li

专题命中 知识编辑与模型理解 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Vision Language Models Know Law of Conservation without Understanding More-or-Less

Dezhi Luo, Haiyun Lyu, Qingying Gao, Haoran Sun, Yijiang Li, Hokin Deng

机构 * University of Michigan（密歇根大学） ； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Johns Hopkins University（约翰霍普金斯大学） ； University of California, San Diego（加州大学圣地亚哥分校） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 知识编辑与模型理解 ：language model(title,abstract)；分类 cs.AI

Comments Published at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign)

Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models

Anish Narain, Ritam Majumdar, Nikita Narayanan, Dominic Marshall, Sonali Parbhoo

机构 * Imperial College London（帝国理工学院伦敦校区） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 32 pages, 7 figures, accepted at Machine Learning for Healthcare Conference (MLHC) 2025

Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders

Charles O'Neill, Mudith Jayasekara, Max Kirkby

机构 * Parsed, London, UK（伦敦大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong

专题命中 知识编辑与模型理解 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted by the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)