语言大模型 / LLM

HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks

Zheng Xiong, Kang Li, Zilin Wang, Matthew Jackson, Jakob Foerster, Shimon Whiteson

机构 * University of Oxford（牛津大学） 纠错

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

Distributed Low-Communication Training with Decoupled Momentum Optimization

Sasho Nedelkoski, Alexander Acker, Odej Kao, Soeren Becker, Dominik Scheinert

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

Comments NeurIPS 2025 - DynaFront 2025: Dynamics at the Frontiers of Optimization, Sampling, and Games Workshop

Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility

Annan Yu, Danielle C. Maddix, Boran Han, Xiyuan Zhang, Abdul Fatir Ansari, Oleksandr Shchur, Christos Faloutsos, Andrew Gordon Wilson, Michael W. Mahoney, Yuyang Wang

机构 * Center for Applied Mathematics（应用数学中心） ； Cornell University（康奈尔大学） ； Amazon Web Services（亚马逊网络服务） ； Amazon Selling Partner Services（亚马逊销售合作伙伴服务） ； Amazon Supply Chain Optimization Technologies（亚马逊供应链优化技术） 纠错

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

Comments 42 pages

Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework

Hao Gu, Vibhas Nair, Amrithaa Ashok Kumar, Jayvart Sharma, Ryan Lagasse

机构 * Algoverse AI Research（Algoverse AI研究） 纠错

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

Comments Accepted to the NeurIPS 2025 Workshop on Mechanistic Interpretability (Mechinterp) and the NeurIPS 2025 Workshop on New Perspectives in Graph Machine Learning

Speculative Actions: A Lossless Framework for Faster Agentic Systems

Naimeng Ye, Arnav Ahuja, Georgios Liargkovas, Yunan Lu, Kostis Kaffes, Tianyi Peng

机构 * Columbia University（哥伦比亚大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.AI

ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context

Huiwon Jang, Sihyun Yu, Heeseung Kwon, Hojin Jeon, Younggyo Seo, Jinwoo Shin

机构 * KAIST（韩国科学技术院） ； RLWRLD ； UC Berkeley（伯克利大学） 纠错

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

Comments Project page: https://huiwon-jang.github.io/contextvla

Quantization Range Estimation for Convolutional Neural Networks

Bingtao Yang, Yujia Wang, Mengzhi Jiao, Hongwei Huo

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

Comments 11 pages, 5 tables, research report

ReTiDe: Real-Time Denoising for Energy-Efficient Motion Picture Processing with FPGAs

Changhong Li, Clément Bled, Rosa Fernandez, Shreejith Shanker

机构 * Trinity College Dublin（都柏林三一学院） 纠错

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

Comments This paper has been accepted by the 22nd ACM SIGGRAPH European Conference on Visual Media Production (CVMP 2025)

Lightweight and Data-Efficient MultivariateTime Series Forecasting using Residual-Stacked Gaussian (RS-GLinear) Architecture

Abukar Ali

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

Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations

Peichao Lai, Jiaxin Gan, Feiyang Ye, Yilei Wang, Bin Cui

机构 * School of Computer Science, Peking University（北京大学计算机科学学院） ； Institute of Computational Social Science, Peking University (Qingdao)（北京大学计算社会科学研究所） ； College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院） 纠错

专题命中 效率与部署 ：LLM(abstract)；分类 cs.CL

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling

Xiaoyu Liu, Di Liang, Chang Dai, Hongyu Shan, Peiyang Liu, Yonghao Liu, Muling Wu, Yuntao Li, Xianjie Wu, LI Miao, Jiangrong Shen, Minlong Peng

机构 * Northeastern University, Boston（东北大学，波士顿） ； Independent Developer（独立开发者） ； Peiking University（北京大学） ； Jilin University（吉林大学） ； Beihang University（北航） ； Xi’an Jiaotong University（西安交通大学） ； Baidu Inc（百度公司） 纠错

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

QuantDemoire: Quantization with Outlier Aware for Image Demoiréing

Zheng Chen, Kewei Zhang, Xiaoyang Liu, Weihang Zhang, Mengfan Wang, Yifan Fu, Yulun Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Central Media Technology Institute, Huawei（华为中央媒体技术研究所） 纠错

专题命中 效率与部署 ：post-training(abstract)

Comments Code is available at: https://github.com/zhengchen1999/QuantDemoire

AutoPrune: Each Complexity Deserves a Pruning Policy

Hanshi Wang, Yuhao Xu, Zekun Xu, Jin Gao, Yufan Liu, Weiming Hu, Ke Wang, Zhipeng Zhang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA（多模态人工智能系统国家重点实验室（MAIS），中国科学院自动化所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院AutoLab） ； Anyverse Intelligence ； Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information（北京多模态信息超智能安全重点实验室） ； School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院） 纠错

专题命中 效率与部署 ：language model(abstract)

Comments 13 pages, 2 figures

Journal ref NeurIPS 2025

Machine-learning inference of stellar properties using integrated photometric and spectroscopic data

Ilay Kamai, Alex M. Bronstein, Hagai B. Perets

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

Comments Accepted to ApJ

ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks

Yinghao Zhu, Junyi Gao, Zixiang Wang, Weibin Liao, Xiaochen Zheng, Lifang Liang, Miguel O. Bernabeu, Yasha Wang, Lequan Yu, Chengwei Pan, Ewen M. Harrison, Liantao Ma

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

Comments Code: https://github.com/yhzhu99/ehr-llm-benchmark

AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science

Chenyue Li, Wen Deng, Mengqian Lu, Binhang Yuan

机构 * HKUST（香港科技大学） 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.AI、cs.LG

Comments 37 pages, 4 figures, 13 tables

Evaluation of Clinical Trials Reporting Quality using Large Language Models

Mathieu Laï-king, Patrick Paroubek

机构 * Université Paris-Saclay, CNRS, LISN（巴黎-萨克雷大学、法国国家科学研究中心、LISN） 纠错

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

Journal ref Revue TAL 65.2, 2024

FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification

Chao Liu, Ling Luo, Tengxiao Lv, Huan Zhuang, Lejing Yu, Jian Wang, Hongfei Lin

机构 * 1 College of Computer Science ； Technology, Dalian University of Technology, Dalian, China ； 2 Cancer Hospital of Dalian University of Technology, Liaoning Cancer Hospital \& Institute, Shenyang, China 纠错

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

Comments Accepted as a regular paper at BIBM2025

Can Large Language Models generalize analogy solving like children can?

Claire E. Stevenson, Alexandra Pafford, Han L. J. van der Maas, Melanie Mitchell

机构 * Psychological Methods, University of Amsterdam, the Netherlands（心理学方法，阿姆斯特丹大学，荷兰） ； Sante Fe Institute, USA（圣菲研究所，美国） 纠错

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

Comments Accepted to Transactions of the Association for Computational Linguistics (TACL)

Red Lines and Grey Zones in the Fog of War: Benchmarking Legal Risk, Moral Harm, and Regional Bias in Large Language Model Military Decision-Making

Toby Drinkall

机构 * Oxford Internet Institute, University of Oxford（牛津互联网研究所、牛津大学） 纠错

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

Comments 54 pages; 11 figures

Foundation models for equation discovery in high energy physics

Manuel Morales-Alvarado

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

Comments 6 pages

Empowering Denoising Sequential Recommendation with Large Language Model Embeddings

Tongzhou Wu, Yuhao Wang, Maolin Wang, Chi Zhang, Xiangyu Zhao

机构 * City University of Hong Kong（香港城市大学） ； Harbin Engineering University（哈尔滨工程大学） 纠错

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

Comments Accepted by CIKM2025

A Trustworthy Industrial Fault Diagnosis Architecture Integrating Probabilistic Models and Large Language Models

Yue wu

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

Comments 1tables,6 figs,11pages

TeachLM: Post-Training LLMs for Education Using Authentic Learning Data

Janos Perczel, Jin Chow, Dorottya Demszky

机构 * Polygence ； Stanford University（斯坦福大学） 纠错

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

Comments 28 pages, 9 figures

Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking

Yunyi Zhang, Ruozhen Yang, Siqi Jiao, SeongKu Kang, Jiawei Han

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Korea University（韩国大学） 纠错

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

Comments Accepted to EMNLP 2025 Findings

Selecting Cybersecurity Requirements: Effects of LLM Use and Professional Software Development Experience

Damjan Fujs, Damjan Vavpotič, Tomaž Hovelja, Marko Poženel

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

Comments 5 pages, 1 figure, 2 tables, presented at IARIA CYBER 2025

Journal ref The Tenth International Conference on Cyber-Technologies and Cyber-Systems (CYBER 2025), September 28, 2025 to October 02, 2025 - Lisbon, Portugal

Enhancing Cybersecurity in Critical Infrastructure with LLM-Assisted Explainable IoT Systems

Ashutosh Ghimire, Ghazal Ghajari, Karma Gurung, Love K. Sah, Fathi Amsaad

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

LLM-Based Information Extraction to Support Scientific Literature Research and Publication Workflows

Samy Ateia, Udo Kruschwitz, Melanie Scholz, Agnes Koschmider, Moayad Almohaishi

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

Comments This PDF is the author-prepared camera-ready version corresponding to the accepted manuscript and supersedes the submitted version that was inadvertently published as the version of record

Journal ref New Trends in Theory and Practice of Digital Libraries. TPDL 2025. Communications in Computer and Information Science, vol 2694. pp 90-99

LLM Chemistry Estimation for Multi-LLM Recommendation

Huascar Sanchez, Briland Hitaj

机构 * Computer Science Laboratory（计算机科学实验室） ； SRI International（SRI国际） 纠错

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

Comments 20 pages, 5 figures, 5 tables

LogSage: An LLM-Based Framework for CI/CD Failure Detection and Remediation with Industrial Validation

Weiyuan Xu, Juntao Luo, Tao Huang, Kaixin Sui, Jie Geng, Qijun Ma, Isami Akasaka, Xiaoxue Shi, Jing Tang, Peng Cai

专题命中 领域大模型 ：LLM(title,abstract)；prompting(abstract)

Comments 12 pages, 8 figures