大模型对齐与安全

Blockchain-Based Federated Learning: Incentivizing Data Sharing and Penalizing Dishonest Behavior

Amir Jaberzadeh, Ajay Kumar Shrestha, Faijan Ahamad Khan, Mohammed Afaan Shaikh, Bhargav Dave, Jason Geng

专题命中 AI治理与伦理 ：trustworthy(abstract)；分类 cs.LG

Comments To appear in the 5th International Congress on Blockchain and Applications (BLOCKCHAIN'23). Publish by the Lecture Notes in Networks and Systems series of Springer Verlag

Journal ref Blockchain and Applications, 5th International Congress. BLOCKCHAIN 2023. Lecture Notes in Networks and Systems, vol 778. Springer, Cham

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment

Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks

专题命中 其他安全 ：alignment(title)；分类 cs.LG

Comments v2 Updates references. v3 Updates references; Adds IFEval results; Improves appendix readability; Adds author contributions

TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models

Jiahao Wang, Mingyue Cheng, Qingyang Mao, Yitong Zhou, Daoyu Wang, Qi Liu, Feiyang Xu, Xin Li

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学） ； Artificial Intelligence Research Institute, iFLYTEK Co., Ltd（人工智能研究院，iFLYTEK公司） 纠错

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

NUM2EVENT: Interpretable Event Reasoning from Numerical time-series

Ninghui Feng, Yiyan Qi

机构 * International Digital Economy Academy (IDEA)（国际数字经济学院（IDEA）） ； University of Nottingham Ningbo（诺丁汉大学宁波校区） 纠错

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

Modeling Electric Vehicle Car-Following Behavior: Classical vs Machine Learning Approach

Md. Shihab Uddin, Md Nazmus Shakib, Rahul Bhadani

机构 * Electrical and Computer Engineering, The University of Alabama in Huntsville, Huntsville, AL, USA（电气与计算机工程系，阿拉巴马大学亨茨维尔分校） 纠错

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

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Hanrong Ye, Chao-Han Huck Yang, Arushi Goel, Wei Huang, Ligeng Zhu, Yuanhang Su, Sean Lin, An-Chieh Cheng, Zhen Wan, Jinchuan Tian, Yuming Lou, Dong Yang, Zhijian Liu, Yukang Chen, Ambrish Dantrey, Ehsan Jahangiri, Sreyan Ghosh, Daguang Xu, Ehsan Hosseini-Asl, Danial Mohseni Taheri, Vidya Murali, Sifei Liu, Yao Lu, Oluwatobi Olabiyi, Yu-Chiang Frank Wang, Rafael Valle, Bryan Catanzaro, Andrew Tao, Song Han, Jan Kautz, Hongxu Yin, Pavlo Molchanov

机构 * NVIDIA 纠错

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

Comments Technical Report. Code: https://github.com/NVlabs/OmniVinci

What do vision-language models see in the context? Investigating multimodal in-context learning

Gabriel O. dos Santos, Esther Colombini, Sandra Avila

机构 * Instituto de Computação, Universidade Estadual de Campinas (UNICAMP)（计算机学院，Campinas州立大学（UNICAMP）） 纠错

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

SynAD: Enhancing Real-World End-to-End Autonomous Driving Models through Synthetic Data Integration

Jongsuk Kim, Jaeyoung Lee, Gyojin Han, Dongjae Lee, Minki Jeong, Junmo Kim

机构 * KAIST（韩国科学技术院） ； AI Center, Samsung Electronics（三星电子人工智能中心） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Journal ref International Conference on Computer Vision, ICCV 2025

GRS: Generating Robotic Simulation Tasks from Real-World Images

Alex Zook, Fan-Yun Sun, Josef Spjut, Valts Blukis, Stan Birchfield, Jonathan Tremblay

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

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

LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision

Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim

机构 * University of Pennsylvania（宾夕法尼亚大学） ； University of Central Florida（中央佛罗里达大学） 纠错

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

Comments Accepted at International Conference on Learning Representations (ICLR) 2025

MORA: AI-Mediated Story-Based practice for Speech Sound Disorder from Clinic to Home

Sumin Hong, Xavier Briggs, Qingxiao Zheng, Yao Du, Jinjun Xiong, Toby Jia-jun Li

专题命中 其他安全 ：alignment(abstract)

Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy

Yunhang Shen, Chaoyou Fu, Shaoqi Dong, Xiong Wang, Yi-Fan Zhang, Peixian Chen, Mengdan Zhang, Haoyu Cao, Ke Li, Shaohui Lin, Xiawu Zheng, Yan Zhang, Yiyi Zhou, Ran He, Caifeng Shan, Rongrong Ji, Xing Sun

机构 * Tencent Youtu Lab（腾讯云图实验室） ； Nanjing University（南京大学） ； East China Normal University（华东师范大学） ； Xiamen University（厦门大学） ； CASIA（中国科学院自动化研究所） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments https://github.com/VITA-MLLM/Long-VITA

RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning

Yunchuan Ma, Laiyun Qing, Guorong Li, Yuankai Qi, Amin Beheshti, Quan Z. Sheng, Qingming Huang

机构 * University of Chinese Academy of Science, Beijing,100190, China（中国科学院大学） ； Macquarie University（麦考瑞大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments Published in Pattern Recognition

Does CLIP perceive art the same way we do?

Andrea Asperti, Leonardo Dessì, Maria Chiara Tonetti, Nico Wu

机构 * Dept. of Informatics (DISI) University of Bologna（信息学院（DISI）博洛尼亚大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Journal ref Proceedings of IEEE International Conference on Content-Based Multimedia Indexing (IEEE CBMI 2025), Dublin, Ireland, 22-24 October 2025