语言大模型 / LLM

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels

语义锚点在上下文学习中的作用：为何小规模大语言模型无法翻转其标签

Anantha Padmanaban Krishna Kumar

机构 * Department of Computer Science, Boston University（计算机科学系，波士顿大学） 纠错

专题命中 其他LLM ：prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 研究探讨了上下文学习中语义锚点的作用，发现小规模LLM在翻转标签时无法有效覆盖语义，主要调整输入投射到预训练语义方向的方式。

Comments 13 pages total (7 pages main text, 3 pages references, 3 pages appendix), 2 figures, 14 tables. Code available at https://github.com/AnanthaPadmanaban-KrishnaKumar/semantic-anchors-icl

OVAL-Grasp: Open-Vocabulary Affordance Localization for Task Oriented Grasping

OVAL-Grasp：面向任务的开放词汇表征定位抓取

Edmond Tong, Advaith Balaji, Anthony Opipari, Stanley Lewis, Zhen Zeng, Odest Chadwicke Jenkins

机构 * University of Michigan, Ann Arbor, MI, USA（密歇根大学） ； J.P. Morgan AI Research（摩根大通AI研究） 纠错

专题命中 其他LLM ：LLM(abstract)；language model(abstract)

AI总结 OVAL-Grasp通过结合大语言模型和视觉-语言模型，实现面向任务的开放词汇表征抓取，有效识别物体部分并提高抓取成功率。

Comments 10 pages, 7 figures, 3 tables. Presented at the 2025 International Symposium on Experimental Robotics (ISER)

Proposal of an AI-Based Support Assistant for the ALICE-FIT Detector Setup at CERN

面向CERN ALICE-FIT探测器设置的基于AI的支持助手提案

Ignacy Mermer, Jakub Muszyński, Jakub Możaryn, Krystian Rosłon

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

AI总结 本文提出基于AI的助手，用于支持CERN ALICE-FIT探测器操作，通过结合LLMs和RAG管道，提供上下文感知的诊断与解决方案建议。

IndiTag: An Online Media Bias Analysis System Using Fine-Grained Bias Indicators

Luyang Lin, Lingzhi Wang, Jinsong Guo, Jing Li, Kam-Fai Wong

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Journal ref ICPADS 2025

Multi-Agent Collaborative Fuzzing with Continuous Reflection for Smart Contracts Vulnerability Detection

Jie Chen, Liangmin Wang

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Semantic-Aware Parsing for Security Logs

Julien Piet, Vivian Fang, Rishi Khare, Scott Coull, Vern Paxson, Raluca Ada Popa, David Wagner

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments 20 pages, 2 figures, 15 tables

OWLAPY: A Pythonic Framework for OWL Ontology Engineering

Alkid Baci, Luke Friedrichs, Caglar Demir, Axel-Cyrille Ngonga Ngomo

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction

Valiyeh A. Nezhad, Gokberk Elmas, Bilal Kabas, Fuat Arslan, Emine U. Saritas, Tolga Çukur

机构 * Department of Electrical and Electronics Engineering（电子工程系） ； National Magnetic Resonance Research Center（国家磁共振研究中心） ； Bilkent University（比尔肯特大学） 纠错

专题命中 其他LLM ：foundation model(abstract)；prompting(abstract)

Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge

Yi Yang, Yiming Xu, Timo Kaiser, Hao Cheng, Bodo Rosenhahn, Michael Ying Yang

机构 * Leibniz University Hannover（莱布尼茨汉诺威大学） ； University of Twente（特文特大学） ； University of Bath（巴斯大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Dense SAE Latents Are Features, Not Bugs

Xiaoqing Sun, Alessandro Stolfo, Joshua Engels, Ben Wu, Senthooran Rajamanoharan, Mrinmaya Sachan, Max Tegmark

机构 * MIT（麻省理工学院） ； ETH Zürich（苏黎世联邦理工学院） ； University of Sheffield（谢菲尔德大学） 纠错

专题命中 其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2025 poster

Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models

Hao Cheng, Erjia Xiao, Yichi Wang, Chengyuan Yu, Mengshu Sun, Qiang Zhang, Jiahang Cao, Yijie Guo, Ning Liu, Kaidi Xu, Jize Zhang, Chao Shen, Philip Torr, Jindong Gu, Renjing Xu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； University of Oxford（牛津大学） ； Xi’an Jiaotong University（西安交通大学） ； The Hong Kong University of Science and Technology（香港科学与技术大学） ； City University of Hong Kong（香港城市大学） ； Beijing University of Technology（北京理工大学） ； Duke University（杜克大学） ； X-Humanoid Project（X-Humanoid 项目） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception

Jiajing Lin, Zhenzhong Wang, Dejun Xu, Shu Jiang, YunPeng Gong, Min Jiang

机构 * School of Informatics, Xiamen University（厦门大学信息学院） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Accepted by ACM MM 2025. Project Page: https://jiajinglin.github.io/Phys4DGen

S3C2 Summit 2025-03: Industry Secure Supply Chain Summit

Elizabeth Lin, Jonah Ghebremichael, William Enck, Yasemin Acar, Michel Cukier, Alexandros Kapravelos, Christian Kastner, Laurie Williams

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Politically Speaking: LLMs on Changing International Affairs

Xuenan Cao, Wai Kei Chung, Ye Zhao, Lidia Mengyuan Zhou

专题命中 其他LLM ：LLM(abstract)；prompting(abstract)

Learning the PTM Code through a Coarse-to-Fine, Mechanism-Aware Framework

Jingjie Zhang, Hanqun Cao, Zijun Gao, Yu Wang, Shaoning Li, Jun Xu, Cheng Tan, Jun Zhu, Chang-Yu Hsieh, Chunbin Gu, Pheng Ann Heng

专题命中 其他LLM ：language model(abstract)；prompting(abstract)

Comments 47 pages

Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs

Xinlu He, Swayambhu Nath Ray, Harish Mallidi, Jia-Hong Huang, Ashwin Bellur, Chander Chandak, M. Maruf, Venkatesh Ravichandran

机构 * Worcester Polytechnic Institute（沃斯特理工大学） ； Amazon AGI（亚马逊人工智能实验室） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

gem5 Co-Pilot: AI Assistant Agent for Architectural Design Space Exploration

Zuoming Fu, Alex Manley, Mohammad Alian

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Accepted by CAMS25, October, 2025, Seoul, Republic of Korea

C2T-ID: Converting Semantic Codebooks to Textual Document Identifiers for Generative Search

Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Wenjun Peng, Sen Li, Fuyu Lv, Xueqi Cheng

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Detecting AI-Assisted Cheating in Online Exams through Behavior Analytics

Gökhan Akçapınar

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Accepted in the Proceedings of the IADIS International Conference on Cognition and Exploratory Learning in the Digital Age (CELDA), 2025

Training-free Online Video Step Grounding

Luca Zanella, Massimiliano Mancini, Yiming Wang, Alessio Tonioni, Elisa Ricci

机构 * University of Trento（特伦托大学） ； Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会） ； Google（谷歌） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments NeurIPS 2025. Project website at https://lucazanella.github.io/baglm/

MapIO: Embodied Interaction for the Accessibility of Tactile Maps Through Augmented Touch Exploration and Conversation

Matteo Manzoni, Sergio Mascetti, Dragan Ahmetovic, Ryan Crabb, James M. Coughlan

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments 25 pages

EPIPTrack: Rethinking Prompt Modeling with Explicit and Implicit Prompts for Multi-Object Tracking

Yukuan Zhang, Jiarui Zhao, Shangqing Nie, Jin Kuang, Shengsheng Wang

机构 * College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院） ； Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University（吉林大学教育部长春符号计算与知识工程重点实验室） ； Yangtze University（扬子大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Simulating Persuasive Dialogues on Meat Reduction with Generative Agents

Georg Ahnert, Elena Wurth, Markus Strohmaier, Jutta Mata

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Code available at https://github.com/dess-mannheim/MeatlessAgents

Journal ref NLPSI 2025: First Workshop on Integrating NLP and Psychology to Study Social Interactions

What Generative Search Engines Like and How to Optimize Web Content Cooperatively

Yujiang Wu, Shanshan Zhong, Yubin Kim, Chenyan Xiong

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

It's 2025 -- Narrative Learning is the new baseline to beat for explainable machine learning

Gregory D. Baker

机构 * Australian National University（澳大利亚国立大学） 纠错

专题命中 其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 18 pages, 5 figures

Beyond Words: Infusing Conversational Agents with Human-like Typing Behaviors

Jijie Zhou, Yuhan Hu

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Author's version of a paper published at CUI '24 (ACM Conversational User Interfaces 2024)

Journal ref CUI '24: Proceedings of the ACM Conversational User Interfaces 2024, July 8-10, 2024, Luxembourg, Luxembourg. ACM, New York, NY, USA, 11 pages

Fine-grained text-driven dual-human motion generation via dynamic hierarchical interaction

Mu Li, Yin Wang, Zhiying Leng, Jiapeng Liu, Frederick W. B. Li, Xiaohui Liang

机构 * State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China（虚拟现实技术与系统国家重点实验室，北京航空航天大学，北京，中国） ； Department of Computer Science, University of Durham, UK（计算机科学系，达勒姆大学，英国） ； Zhongguancun Laboratory, Beijing, China（中关村实验室，北京，中国） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

An empirical study on declined proposals: why are these proposals declined?

Masanari Kondo, Mahmoud Alfadel, Shane McIntosh, Yasutaka Kamei, Naoyasu Ubayashi

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Unpacking Discourses on Childbirth and Parenthood in Popular Social Media Platforms Across China, Japan, and South Korea

Zheng Wei, Yunqi Li, Yucheng He, Yuelu Li, Xian Xu, Huamin Qu, Pan Hui, Muzhi Zhou

专题命中 其他LLM ：large language model(abstract)；language model(abstract)

Comments Accepted for publication at The International AAAI Conference on Web and Social Media (ICWSM 2026)

Evil twins are not that evil: Qualitative insights into machine-generated prompts

Nathanaël Carraz Rakotonirina, Corentin Kervadec, Francesca Franzon, Marco Baroni

机构 * Universitat Pompeu Fabra（庞培法布拉大学） ； ICREA 纠错

专题命中 其他LLM ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published as workshop paper at BlackBox NLP 2025