YuXin Song

Researcher, VIS, Baidu

Joined

January 2022

Names

YuXin Song (Preferred)

Emails

****@outlook.com (Confirmed)

****@baidu.com (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Researcher

VIS, Baidu (baidu.com)

2022 – Present

MS student

PRIS, Beijing University of Posts and Telecommunications (bupt.edu.cn)

2019 – 2022

Advisors, Relations & Conflicts

Coauthor

zhangchuang

2019 – 2022

Expertise

image / video generation and editing

2024 – 2026

multimodal understanding

2022 – 2026

video action recogniition

2021 – 2022

graph representation

image retrieval

2021 – 2022

Publications

Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
Bo Fang, YuXin Song, Haoyuan Sun, Qiangqiang Wu, Wenhao Wu, Antoni B. Chan
- ICLR 2026 Poster
- Readers: Everyone
Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
YuXin Song, Wenkai Dong, Shizun Wang, Qi Zhang, Song Xue, Tao Yuan, Hu Yang, Haocheng Feng, Hang Zhou, Xinyan Xiao, Jingdong Wang
- Submitted to ICLR 2026
- Readers: Everyone
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Huanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang, Yibo Wang, Shunyu Liu, Yingjie Wang, YuXin Song, Haocheng Feng, Li Shen, Dacheng Tao
- NeurIPS 2025 spotlight
- Readers: Everyone
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
Yang Shen, Xiu-Shen Wei, Yifan Sun, YuXin Song, Tao Yuan, Jian Jin, He-Yang Xu, Yazhou Yao, Errui Ding
- ICML 2025 poster
- Readers: Everyone
Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
Chuyang Zhao, YuXin Song, Junru Chen, KANG RONG, Haocheng Feng, Gang Zhang, Shufan Ji, Jingdong Wang, Errui Ding, Yifan Sun
- NeurIPS 2024 poster
- Readers: Everyone
Dense Connector for MLLMs
Huanjin Yao, Wenhao Wu, Taojiannan Yang, YuXin Song, Mengxi Zhang, Haocheng Feng, Yifan Sun, Zhiheng Li, Wanli Ouyang, Jingdong Wang
- NeurIPS 2024 poster
- Readers: Everyone
Automated Multi-level Preference for MLLMs
Mengxi Zhang, Wenhao Wu, Yu Lu, YuXin Song, KANG RONG, Huanjin Yao, Jianbo Zhao, Fanglong Liu, Haocheng Feng, Jingdong Wang, Yifan Sun
- NeurIPS 2024 poster
- Readers: Everyone
It Takes Two: Masked Appearance-Motion Modeling for Self-Supervised Video Transformer Pre-Training
YuXin Song, Min Yang, Wenhao Wu, Dongliang He, Fu Li, Jingdong Wang
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone

Co-Authors

View all 45 co-authors