Baiqiao Yin「尹柏乔」

Hi there! I'm Baiqiao Yin. Now I'm a research intern at Northwestern University, very fortunate to work with Manling Li. Previously, I got my B.Eng. in Intelligent Science and Technology from Sun Yat-sen University, where I worked closely with Xiaodan Liang.
In the near future, I'll go to New York University to serve as a research assistant in my gap year, working closely with Chen Feng.
⭐I am open for discussions and looking for PhD opportunities (26 Fall). If you think there is anything interesting we can discuss, feel free to email me!

Email / Scholar / Github

profile photo

Internships

  • 2024.07 - 2024.11, Shanghai AI Lab, Embodied AI Group. Mentor: Xudong Xu
  • 2023.05 - 2024.04, Peking University(SZ), HRI Lab. Mentor: Mengyuan Liu

📝Researches

💬My research interests lie in spatial intelligence. Currently, my focus is on designing spatial intelligence agents with the following capabilities:

  1. Spatial perception: MLLMs or Large spatial model?
  2. Active spatial interaction mechanisms, encompassing environment manipulation and viewpoint optimization
  3. Dynamic spatio-temporal understanding for predictive spatial modeling
Spatial Mental Modeling from Limited Views
Baiqiao Yin*, Qineng Wang*, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Manling Li, Jiajun Wu, Li Fei-Fei
arXiv, 2025
project page / arXiv

Key Takeaway: Guiding VLMs to first generate cognitive maps, then reason upon them, is an effective approach to approximate spatial mental modeling with limited views.

Skeleton2Point: Recognizing Skeleton-Based Actions as Point Clouds
Baiqiao Yin, Jiaying Lin, Jiajun Wen, Yue Li, Jinfu Liu, Yanfei Wang, Mengyuan Liu
IROS, 2025
project page / paper

Regard skeleton joints as point cloud via incorporating the position information of skeletons into point cloud methods, demonstrating the validity of modeling position relationships with 3D coordinates.

TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation
Junhao Cheng, Baiqiao Yin, Kaixin Cai, Minbin Huang, Hanhui Li, Yuxin He, Xi Lu, Yue Li, Yifei Li, Yiqiang Yan, Xiaodan Liang/a>
arrxiv, 2024
project page / arxiv

Theatergen can interact with users to consistently generate images over multiple Turns.

HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
Jinfu Liu*, Baiqiao Yin*, Jiaying Lin, Jiajun Wen, Yue Li, Mengyuan Liu
ICMEW, 2024
code / paper

Benefits from the graph convolutional network's proficiency in handling graph-structured data and the powerful modeling capabilities of Transformers for global information.

🏆Honors and Awards

  • 2024.04: Champion of ICME Grand Challenge Multi-Modal Video Reasoning and Analyzing Competition.
  • 2023.10: The Second Prize of Intelligent Robot Fighting and gaming competition.
  • 2023.10: Academic Competition Scholarship of Sun Yat-sen University.
  • 2023.10: The Third Prize Scholarship of Sun Yat-sen University.
  • 2022.10: Academic Competition Scholarship of Sun Yat-sen University.
  • 2022.10: The Third Prize Scholarship of Sun Yat-sen University.