大模型对齐与安全

ToDi: Token-wise Distillation via Fine-Grained Divergence Control

Seongryong Jung, Suwan Yoon, DongGeon Kim, Hwanhee Lee

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

Comments EMNLP 2025 (Oral)

VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning

Zhaozhi Wang, Tong Zhang, Mingyue Guo, Yaowei Wang, Qixiang Ye

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Peng Cheng Lab（鹏城实验室） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments 16 pages, 6 figures

DAM: Dual Active Learning with Multimodal Foundation Model for Source-Free Domain Adaptation

Xi Chen, Hongxun Yao, Zhaopan Xu, Kui Jiang

机构 * Harbin Institute of Technology（哈尔滨工业大学） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments 5 pages

Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens

Zijian Dong, Ruilin Li, Joanna Su Xian Chong, Niousha Dehestani, Yinghui Teng, Yi Lin, Zhizhou Li, Yichi Zhang, Yapei Xie, Leon Qi Rong Ooi, B. T. Thomas Yeo, Juan Helen Zhou

专题命中 其他安全 ：alignment(abstract)

Comments NeurIPS 2025. The first two authors contributed equally

UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

Xuenan Xu, Jiahao Mei, Zihao Zheng, Ye Tao, Zeyu Xie, Yaoyun Zhang, Haohe Liu, Yuning Wu, Ming Yan, Wen Wu, Chao Zhang, Mengyue Wu

机构 * Shanghai Artificial Intelligence Lab（上海人工智能实验室） ； Shanghai Jiao Tong University（上海交通大学） ； Peking University（北京大学） ； Meta ； Alibaba Group（阿里巴巴集团） 纠错

专题命中 其他安全 ：alignment(abstract)

Comments Project page: https://wsntxxn.github.io/uniflow_audio

METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding

Mengyue Wang, Shuo Chen, Kristian Kersting, Volker Tresp, Yunpu Ma

专题命中 其他安全 ：alignment(abstract)

Comments EMNLP 2025; 15 pages, 10 figures

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Junsong Chen, Shuchen Xue, Yuyang Zhao, Jincheng Yu, Sayak Paul, Junyu Chen, Han Cai, Song Han, Enze Xie

专题命中 其他安全 ：alignment(abstract)

Comments 22 pages, 11 figures, 8 tables, In submission

MoReact: Generating Reactive Motion from Textual Descriptions

Xiyan Xu, Sirui Xu, Yu-Xiong Wang, Liang-Yan Gui

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

专题命中 其他安全 ：alignment(abstract)

Comments Published in Transactions on Machine Learning Research

INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception

Yunjiang Xu, Lingzhi Li, Jin Wang, Yupeng Ouyang, Benyuan Yang

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院） ； School of Future Science and Engineering, Soochow University（苏州大学未来科学与工程学院） 纠错

专题命中 其他安全 ：safety(abstract)

Comments 14 pages, 8 figures

LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation

Shaoxiong Zhan, Hai Lin, Hongming Tan, Xiaodong Cai, Hai-Tao Zheng, Xin Su, Zifei Shan, Ruitong Liu, Hong-Gee Kim

专题命中 其他安全 ：alignment(abstract)

Comments 8 pages, 4 figures. Accepted to ECAI

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Ge Wu, Shen Zhang, Ruijing Shi, Shanghua Gao, Zhenyuan Chen, Lei Wang, Zhaowei Chen, Hongcheng Gao, Yao Tang, Jian Yang, Ming-Ming Cheng, Xiang Li

机构 * NKIARI, Shenzhen Futian（NKIARI，深圳福田） ； VCIP, CS, Nankai University（VCIP，计算机科学，南开大学） ； JIIOV Technology（JIIOV技术） ； Harvard University（哈佛大学） ； 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)