Hongbo Ma - 马洪博

I'm a final year undergraudate student from Xinya College and Department of Computer Science and Technology, Tsinghua University. In addition, I am also minoring in Economics and Finance at School of Economics and Management, Tsinghua University.

My research interests primarily focus on computer vision, generative models, and intelligent agent systems. Building upon these three areas, I aim to develop embodied agents that can perceive, reason, and act in real-world environments, and further explore scientific agents to advance the application of artificial intelligence in solving complex real-world problems.

In terms of research methodology, centered around these two core objectives, I plan to conduct broad and in-depth exploration across related upstream and downstream tasks, including:

  • Visual representation learning and generative modeling
  • World modeling and environment modeling
  • Efficient reasoning and decision-making mechanisms for intelligent agents
  • Training and generalization of agents in real-world environments

Email  /  Google Scholar  /  CV  /  Github  /  Rednote  /  Zhihu  /  Blog

profile photo
News

2025/11/07- Styletailor is accepted by AAAI-26 and selected as Oral 🎉!

Publications
StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback
Hongbo Ma, Fei Shen, Hongbin Xu, Xiaoce Wang, Gang Xu, Jinkai Zheng, Liangqiong Qu, Ming Li
The Fortieth Annual AAAI Conference on Artificial Intelligence (AAAI'26)
Oral Presentation (1,058/23,680 Top 4.5%)
Paper / Project / Code
Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks
Keyue Qiu*, Yuxuan Song*, Jie Yu, Hongbo Ma, Ziyao Cao, Zhilong Zhang, Yushuai Wu, Mingyue Zheng, Hao Zhou, Wei-Ying Ma

Forty-Second International Conference on Machine Learning (ICML'25)
Poster
Paper
Redefining the task of Bioactivity Prediction
Yanwen Huang*, Bowen Gao*, Yinjun Jia, Hongbo Ma, Wei-Ying Ma, Ya-Qin Zhang, Yanyan Lan

The Thirteenth International Conference on Learning Representations (ICLR'25)
Poster
Paper