大模型对齐与安全

Diffusion Instruction Tuning

Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Teare

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments Project page at https://astrazeneca.github.io/vlm/

Next Token Perception Score: Analytical Assessment of your LLM Perception Skills

Yu-Ang Cheng, Leyang Hu, Hai Huang, Randall Balestriero

机构 * Atlassian（Atlassian公司） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data

Abderrahman Skiredj, Ferdaous Azhari, Houdaifa Atou, Nouamane Tazi, Ismail Berrada

机构 * College of Computing, Mohammed VI Polytechnic University（计算学院，穆莱·伊斯梅尔polytechnic大学） ； Hugging Face ； National Institute of Posts and Telecoms（国家电信研究所） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Can AI Read Between The Lines? Benchmarking LLMs On Financial Nuance

Dominick Kubica, Dylan T. Gordon, Nanami Emura, Derleen Saini, Charlie Goldenberg

机构 * Department of Business Analytics, Santa Clara University - Leavey School of Business（商学院分析部门，圣克拉拉大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments 6 pages, 4 figures. Research conducted as part of a Microsoft-sponsored Capstone Project at Santa Clara University

Knowledge Integration Strategies in Autonomous Vehicle Prediction and Planning: A Comprehensive Survey

Kumar Manas, Adrian Paschke

机构 * Freie Universität Berlin（柏林自由大学） ； Continental Automotive Technologies GmbH（大陆汽车技术有限公司） ； Fraunhofer FOKUS Berlin（弗劳恩霍夫研究所柏林） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted for publication in Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Cluj-Napoca - Romania, 22-25 June 2025

More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding

Yuan Tang, Xu Han, Xianzhi Li, Qiao Yu, Jinfeng Xu, Yixue Hao, Long Hu, Min Chen

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation

Yuhao Zhang, Xiangnan Ma, Kaiqi Kou, Peizhuo Liu, Weiqiao Shan, Benyou Wang, Tong Xiao, Yuxin Huang, Zhengtao Yu, Jingbo Zhu

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ACL 2025 Findings

Learning Novel Skills from Language-Generated Demonstrations

Ao-Qun Jin, Tian-Yu Xiang, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Yue Cao, Sheng-Bin Duan, Fu-Chao Xie, Zeng-Guang Hou

机构 * Institute of Automation Chinese Academy of Sciences（自动化研究所，中国科学院） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 10 pages, International Conference on Learning Representations (ICLR) 2025 Workshop on Generative Models for Robot Learning (GenBot)

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models

Yuqiao Tan, Shizhu He, Kang Liu, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ACL'25 Main. Code link: https://github.com/Trae1ounG/Neural_Incompatibility

Interpretable Neural System Dynamics: Combining Deep Learning with System Dynamics Modeling to Support Critical Applications

Riccardo D'Elia

机构 * University of Applied Sciences and Arts of Southern Switzerland（瑞士南瑞士应用科学与艺术大学） ； Dalle Molle Institute for Artificial Intelligence（达勒莫勒人工智能研究所） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments To be submitted to CEUR-WS.org for publication in the Doctoral Consortium Proceedings of XAI 2025, The World Conference on Explainable Artificial Intelligence

Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts

Youcheng Huang, Chen Huang, Duanyu Feng, Wenqiang Lei, Jiancheng Lv

机构 * Sichuan University, China（四川大学） ； Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China（教育部机器学习与工业智能工程研究中心） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments ACL 2025 Main Camera Ready

EpiLLM: Unlocking the Potential of Large Language Models in Epidemic Forecasting

Chenghua Gong, Rui Sun, Yuhao Zheng, Juyuan Zhang, Tianjun Gu, Liming Pan, Linyuan Lv

机构 * University of Science and Technology of China（中国科学技术大学） ； East China Normal University（华东师范大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments 18 pages

Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering

Xukai Liu, Ye Liu, Shiwen Wu, Yanghai Zhang, Yihao Yuan, Kai Zhang, Qi Liu

机构 * School of Computer Science and Technology, University of Science and Technology of China（计算机科学与技术学院，中国科学技术大学） ； State Key Laboratory of Cognitive Intelligence, Hefei, Anhui, China（认知智能国家重点实验室，安徽合肥，中国） ； The Hong Kong University of Science and Technology（香港科学与技术大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study

Baixuan Xu, Chunyang Li, Weiqi Wang, Wei Fan, Tianshi Zheng, Haochen Shi, Tao Fan, Yangqiu Song, Qiang Yang

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； WeBank ； The Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments 19 pages

Call for Rigor in Reporting Quality of Instruction Tuning Data

Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim

机构 * Department of Computer Science and Engineering, Korea University（韩国大学计算机科学与工程系） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted to the ACL2025-main

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning

Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li

机构 * Multimedia Laboratory (MMLab)（多媒体实验室） ； The Chinese University of Hong Kong（香港中文大学） ； CPII under InnoHK（创新香港科技署CPII） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ACL 2025 Findings

LanTu: Dynamics-Enhanced Deep Learning for Eddy-Resolving Ocean Forecasting

Qingyu Zheng, Qi Shao, Guijun Han, Wei Li, Hong Li, Xuan Wang

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 22 pages, 6 figures

KBAlign: Efficient Self Adaptation on Specific Knowledge Bases

Zheni Zeng, Yuxuan Chen, Shi Yu, Ruobing Wang, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun

机构 * Tsinghua University（清华大学） ； Northeastern University（东北大学） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining

Wenqi Zhang, Hang Zhang, Xin Li, Jiashuo Sun, Yongliang Shen, Weiming Lu, Deli Zhao, Yueting Zhuang, Lidong Bing

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； DAMO Academy, Alibaba Group（阿里巴巴集团达摩院） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments Under review

Self-Data Distillation for Recovering Quality in Pruned Large Language Models

Vithursan Thangarasa, Ganesh Venkatesh, Mike Lasby, Nish Sinnadurai, Sean Lie

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments Accepted to MLSys 2025. Main paper: 14 pp., 4 figs., 6 tabs.; Supplementary: 5 pp

ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget

Riccardo Orlando, Pere-Lluis Huguet Cabot, Edoardo Barba, Roberto Navigli

机构 * Sapienza NLP Group, Sapienza University of Rome（罗马萨皮恩扎大学萨皮恩扎自然语言处理小组） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments Findings of the Association for Computational Linguistics ACL 2024

The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete

Gerrit Großmann, Larisa Ivanova, Sai Leela Poduru, Mohaddeseh Tabrizian, Islam Mesabah, David A. Selby, Sebastian J. Vollmer

机构 * Department of Data Science and its Applications, German Research Center for Artificial Intelligence (DFKI)（数据科学及其应用系，德国人工智能研究中心（DFKI）） ； Department of Computer Science, University of Kaiserslautern–Landau (RPTU)（计算机科学系，凯撒斯劳滕-兰道大学（RPTU）） ； Department of Language Science and Technology, Saarland University（语言科学与技术系，萨尔兰大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments 16 pages, 8 figures. Code available at https://github.com/storyagents25/story-agents

Vision-Language Models Create Cross-Modal Task Representations

Grace Luo, Trevor Darrell, Amir Bar

机构 * University of California, Berkeley, USA（加州大学伯克利分校） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments ICML 2025

JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models

Peike Li, Boyu Chen, Yao Yao, Yikai Wang, Allen Wang, Alex Wang

机构 * Futureverse AI Research（未来视AI研究） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments Github Demo Page: https://gogoduck912.github.io/Jen1-Demo-Page/

Journal ref https://ieeecai.org/2024/wp-content/pdfs/540900a773/540900a773.pdf

MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language

Yoel Shoshan, Moshiko Raboh, Michal Ozery-Flato, Vadim Ratner, Alex Golts, Jeffrey K. Weber, Ella Barkan, Simona Rabinovici-Cohen, Sagi Polaczek, Ido Amos, Ben Shapira, Liam Hazan, Matan Ninio, Sivan Ravid, Michael M. Danziger, Yosi Shamay, Sharon Kurant, Joseph A. Morrone, Parthasarathy Suryanarayanan, Michal Rosen-Zvi, Efrat Hexter

机构 * IBM Research-Israel（IBM研究以色列分公司） ； IBM TJ Watson Research Center（IBM TJ Watson研究中心） ； Faculty of Biomedical Engineering（生物医学工程学院） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans

Huangyue Yu, Baoxiong Jia, Yixin Chen, Yandan Yang, Puhao Li, Rongpeng Su, Jiaxin Li, Qing Li, Wei Liang, Song-Chun Zhu, Tengyu Liu, Siyuan Huang

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Beijing Institute of Technology（北京理工大学） ； Tsinghua University（清华大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments CVPR 2025

UoR-NCL at SemEval-2025 Task 1: Using Generative LLMs and CLIP Models for Multilingual Multimodal Idiomaticity Representation

Thanet Markchom, Tong Wu, Liting Huang, Huizhi Liang

机构 * Department of Computer Science, University of Reading（阅读大学计算机科学系） ； School of Computing, Newcastle University（新castle大学计算机学院） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

RDF-Based Structured Quality Assessment Representation of Multilingual LLM Evaluations

Jonas Gwozdz, Andreas Both

机构 * Leipzig University of Applied Sciences（莱比锡应用科学大学） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.AI

Model Connectomes: A Generational Approach to Data-Efficient Language Models

Klemen Kotar, Greta Tuckute

机构 * Department of Computer Science（计算机科学系） ； Cranberry-Lemon University（Cranberry-Lemon 大学） ； Department of Computational Neuroscience（计算神经科学系） ； University of the Witwatersrand（瓦特瓦特斯兰大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

Diverse Prompts: Illuminating the Prompt Space of Large Language Models with MAP-Elites

Gabriel Machado Santos, Rita Maria da Silva Julia, Marcelo Zanchetta do Nascimento

机构 * Federal University of Uberlândia Computer Science Faculty（伯南布哥联邦大学计算机科学学院） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments 8 pages Accepted for publication in IEEE CEC 2025