语言大模型 / LLM

The Platonic Universe: Do Foundation Models See the Same Sky?

UniverseTBD, :, Kshitij Duraphe, Michael J. Smith, Shashwat Sourav, John F. Wu

机构 * Independent Researcher（独立研究者） ； AstroAI ； Harvard-Smithsonian CfA（哈佛-史密松天体物理中心） ； University of Hertfordshire（赫特福德郡大学） ； Washington University St. Louis（圣路易斯华盛顿大学） ； Space Telescope Science Institute（空间望远镜科学研究所） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

专题命中 评测与基准 ：foundation model(title,abstract)；分类 cs.LG

Comments 9 pages, 3 tables, 1 figure. Accepted as a workshop paper to Machine Learning and the Physical Sciences at NeurIPS 2025

Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation

Qingsong Wang, Tao Wu, Wang Lin, Yueying Feng, Gongsheng Yuan, Chang Yao, Jingyuan Chen

机构 * Zhejiang University（浙江大学） 纠错

专题命中 评测与基准 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to Findings of EMNLP 2026

Oversampling and Downsampling with Core-Boundary Awareness: A Data Quality-Driven Approach

Samir Brahim Belhaouari, Yunis Carreon Kahalan, Humaira Shaffique, Ismael Belhaouari, Ashhadul Islam

机构 * Hamad Bin Khalifa University（哈马德·本·卡尔法大学） ； Maastricht University（马斯特里赫特大学） ； KTH Royal Institute of Technology（皇家理工学院） 纠错

专题命中 评测与基准 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding

Phyo Thet Yee, Dimitrios Kollias, Sudeepta Mishra, Abhinav Dhall

机构 * IIT Ropar（印度IIT罗帕尔） ； Queen Mary University of London（伦敦女王玛丽大学） ； Monash University（墨尔本大学） 纠错

专题命中 评测与基准 ：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments Accepted at WACV 2026, project page : https://novicemm.github.io/synchrorama

Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems

Sergey Berezin, Reza Farahbakhsh, Noel Crespi

机构 * SAMOVAR ； Télécom SudParis Institut Polytechnique de Paris（巴黎高等理工学院） 纠错

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Journal ref https://aclanthology.org/2025.woah-1.13/

Multimodal Reference Visual Grounding

Yangxiao Lu, Ruosen Li, Liqiang Jing, Jikai Wang, Xinya Du, Yunhui Guo, Nicholas Ruozzi, Yu Xiang

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Project page with our code and dataset: https://irvlutd.github.io/MultiGrounding

LLMs Reproduce Stereotypes of Sexual and Gender Minorities

Ruby Ostrow, Adam Lopez

机构 * University of Edinburgh（爱丁堡大学） 纠错

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 13 pages, 5 figures, 9 tables (including bibliography and appendix). Accepted to Findings of EMNLP 2025

SINAI at eRisk@CLEF 2025: Transformer-Based and Conversational Strategies for Depression Detection

Alba Maria Marmol-Romero, Manuel Garcia-Vega, Miguel Angel Garcia-Cumbreras, Arturo Montejo-Raez

机构 * Computer Science Department, SINAI, CEATIC, University of Jaen, 23071, Spain（计算机科学系、SINAI、CEATIC、杰恩大学） 纠错

专题命中 评测与基准 ：LLM(abstract)；language model(abstract)；分类 cs.CL

Comments 16 pages, 10 figures, 8 tables. CLEF (Working Notes). 2025

Journal ref CEUR Workshop Proceedings 2025, vol. 4038, pp. 1620-1635

The Indispensable Role of User Simulation in the Pursuit of AGI

Krisztian Balog, ChengXiang Zhai

机构 * University of Stavanger（斯塔万格大学） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted for publication in Communications of the ACM

Culture is Everywhere: A Call for Intentionally Cultural Evaluation

Juhyun Oh, Inha Cha, Michael Saxon, Hyunseung Lim, Shaily Bhatt, Alice Oh

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.CL

DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors

Yize Cheng, Wenxiao Wang, Mazda Moayeri, Soheil Feizi

机构 * University of Maryland, College Park（马里兰大学学院 park） 纠错

专题命中 评测与基准 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments EMNLP2025 main, Camera-ready

Frontiers in Intelligent Colonoscopy

Ge-Peng Ji, Jingyi Liu, Peng Xu, Nick Barnes, Fahad Shahbaz Khan, Salman Khan, Deng-Ping Fan

机构 * Nankai Institute of Advanced Research (SHENZHEN FUTIAN)（南开先进研究院（深圳福田）） ； College of Computer Science & VCIP, Nankai University（计算机科学与VCIP学院，南开大学） ； School of Computing, Australian National University（计算学院，澳大利亚国立大学） ； Graduate School of Science and Technology, Keio University（科学与技术研究生院，庆应大学） ； Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

专题命中 评测与基准 ：language model(abstract,comments)；instruction tuning(abstract)

Comments [Work in progress] A comprehensive survey of intelligent colonoscopy in the multimodal era. [Updated Version V2] New training strategy for colonoscopy-specific multimodal language model

Journal ref Machine Intelligence Research 2025

Improved Therapeutic Antibody Reformatting through Multimodal Machine Learning

Jiayi Xin, Aniruddh Raghu, Nick Bhattacharya, Adam Carr, Melanie Montgomery, Hunter Elliott

机构 * University of Pennsylvania（宾夕法尼亚大学） ； BigHat Biosciences（BigHat生物技术公司） 纠错

专题命中 评测与基准 ：language model(abstract,comments)；分类 cs.LG；large language model(comments)；foundation model(comments)

Comments NeurIPS 2025 AI4Science Workshop and NeurIPS 2025 Multi-modal Foundation Models and Large Language Models for Life Sciences Workshop

Urania: Differentially Private Insights into AI Use

Daogao Liu, Edith Cohen, Badih Ghazi, Peter Kairouz, Pritish Kamath, Alexander Knop, Ravi Kumar, Pasin Manurangsi, Adam Sealfon, Da Yu, Chiyuan Zhang

机构 * Google Research（谷歌研究） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments To appear at COLM 2025

Quantifying Compositionality of Classic and State-of-the-Art Embeddings

Zhijin Guo, Chenhao Xue, Zhaozhen Xu, Hongbo Bo, Yuxuan Ye, Janet B. Pierrehumbert, Martha Lewis

机构 * University of Oxford（牛津大学） ； University of Bristol（布里斯托大学） ； University of Amsterdam（阿姆斯特丹大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Findings of the Association for Computational Linguistics: EMNLP 2025

CUPID: Curating Data your Robot Loves with Influence Functions

Christopher Agia, Rohan Sinha, Jingyun Yang, Rika Antonova, Marco Pavone, Haruki Nishimura, Masha Itkina, Jeannette Bohg

机构 * Stanford University（斯坦福大学） ； University of Cambridge（剑桥大学） ； NVIDIA Research（NVIDIA研究） ； Toyota Research Institute（丰田研究机构） 纠错

专题命中 评测与基准 ：post-training(abstract)；分类 cs.AI、cs.LG

Comments Project page: https://cupid-curation.github.io. 27 pages, 15 figures. Accepted to the Conference on Robot Learning (CoRL) 2025

Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets

Mahdi Zakizadeh, Mohammad Taher Pilehvar

机构 * Tehran Institute for Advanced Studies（泰赫兰高级研究所） ； Khatam University（卡塔姆大学） ； Cardiff NLP（卡迪夫自然语言处理） ； Cardiff University（卡迪夫大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2025

GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering

Saumya Saxena, Blake Buchanan, Chris Paxton, Peiqi Liu, Bingqing Chen, Narunas Vaskevicius, Luigi Palmieri, Jonathan Francis, Oliver Kroemer

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Neya Systems（Neya系统） ； Agility Robotics（敏捷机器人） ； Hello Robot ； Bosch Center for AI（博世人工智能中心） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.CL、cs.LG

Comments Project website: https://saumyasaxena.github.io/grapheqa

DiffNator: Generating Structured Explanations of Time-Series Differences

Kota Dohi, Tomoya Nishida, Harsh Purohit, Takashi Endo, Yohei Kawaguchi

机构 * Research and Development Group, Hitachi, Ltd.（日立株式会社研发部） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.CL

When Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset

Sarmistha Das, R E Zera Marveen Lyngkhoi, Kirtan Jain, Vinayak Goyal, Sriparna Saha, Manish Gupta

机构 * Indian Institute of Technology Patna（印度帕纳布理工大学） ； Microsoft, India（微软印度） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.AI

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation

Ramy ElMallah, Krish Chhajer, Chi-Guhn Lee

机构 * University of Toronto（多伦多大学） 纠错

专题命中 评测与基准 ：language model(abstract)；分类 cs.AI

Comments Accepted to the CoRL 2025 Eval&Deploy Workshop

Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation

Ashim Dahal, Ankit Ghimire, Saydul Akbar Murad, Nick Rahimi

机构 * University of Southern Mississippi（密苏里州南方大学） 纠错

专题命中 评测与基准 ：LLM(abstract)；分类 cs.CL

Generalist Robot Manipulation beyond Action Labeled Data

Alexander Spiridonov, Jan-Nico Zaech, Nikolay Nikolov, Luc Van Gool, Danda Pani Paudel

机构 * ETH Zurich, Switzerland（苏黎世联邦理工学院，瑞士） 纠错

专题命中 评测与基准 ：language model(abstract)

Comments Accepted at Conference on Robot Learning 2025

SCORE: Scaling audio generation using Standardized COmposite REwards

Jaemin Jung, Jaehun Kim, Inkyu Shin, Joon Son Chung

专题命中 评测与基准 ：language model(abstract)

Is Reuse All You Need? A Systematic Comparison of Regular Expression Composition Strategies

Berk Çakar, Charles M. Sale, Sophie Chen, Dongyoon Lee, James C. Davis

专题命中 评测与基准 ：LLM(abstract)

A systematic review of trial-matching pipelines using large language models

Braxton A. Morrison, Madhumita Sushil, Jacob S. Young

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

Comments 28 pages, 3 figures

Large Language Models for Pedestrian Safety: An Application to Predicting Driver Yielding Behavior at Unsignalized Intersections

Yicheng Yang, Zixian Li, Jean Paul Bizimana, Niaz Zafri, Yongfeng Dong, Tianyi Li

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

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing

Ruihan Jin, Pengpeng Shao, Zhengqi Wen, Jinyang Wu, Mingkuan Feng, Shuai Zhang, Jianhua Tao

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） ； Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心） 纠错

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

Comments EMNLP 2025 Findings

RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models

Aditya Gunturu, Shivesh Jadon, Nandi Zhang, Morteza Faraji, Jarin Thundathil, Wesley Willett, Ryo Suzuki

机构 * University of Calgary（卡尔加里大学） ； University of Colorado Boulder（科罗拉多大学博尔德分校） ； Apple（苹果公司） ； University of Rochester（罗切斯特大学） 纠错

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

Comments SUI 2025

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning

Benedikt Roth, Stephan Rappensperger, Tianming Qiu, Hamza Imamović, Julian Wörmann, Hao Shen

机构 * fortiss GmbH（fortiss公司） ； School of Computation and Information Technology（计算与信息科技学院） 纠错

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