Hongbo Ma

Hongbo Ma

Tsinghua University

My name is Hongbo Ma (马洪博). I am a final-year student at Xinya College and Department of Computer Science and Technology, Tsinghua University. I am also minoring in Economics and Management at School of Economics and Management, Tsinghua University.

My research interests primarily focus on computer vision, generative models, and intelligent agent systems. I aim to develop embodied agents that can perceive, reason, and act in real-world environments, and explore scientific agents for solving complex real-world problems.

If you want to learn more about me, feel free to check my CV.

Current methodology focus

  1. Visual representation learning and generative modeling
  2. World and environment modeling
  3. Efficient reasoning and decision-making for intelligent agents
  4. Training and generalization in real-world environments

Vision and Generation

  • Visual representation learning and generative modeling
  • On-device video synthesis with compact Diffusion Transformers
  • 3D-aware modeling and molecular structure understanding

Agent Systems

  • Reasoning and decision-making mechanisms for AI agents
  • Negative-feedback mechanisms for multi-agent systems
  • End-to-end evaluation protocols for agentic tasks

AI for Science

  • AI for drug discovery and molecule optimization
  • Bayesian Flow Networks and generative learning methods
  • Bridging theory, implementation, and application

News

  • 2025.11: StyleTailor is accepted by AAAI 2026 and selected as Oral (Top 4.5%)! 🎉🎉🎉
  • 2025.5: One paper is accepted by ICML 2025! 🎉
  • 2025.1: One paper is accepted by ICLR 2025! 🎉

Publications

Under Review
Batched Contextual Reinforcement

Batched Contextual Reinforcement

Bangji Yang*, Hongbo Ma*, Jiajun Fan*, Ge Liu
Under Review
Under Review
Towards High-Fidelity Mobile Video Synthesis with Slimmed Diffusion-Transformer

Towards High-Fidelity Mobile Video Synthesis with Slimmed Diffusion Transformer

Juncheng Yan, Qi Qin, Yinan Liang, Hongbo Ma, Le Zhuo, Yuandong Pu, Yi Xin, Wenzhao Zheng, Yu Qiao, Yihao Liu, Jiwen Lu
Under Review
AAAI 2026
StyleTailor

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 2026)
Oral
Top 4.5% (1,058/23,680)
Paper Project Code
ICML 2025
Empower Structure-based Molecule Optimization with Gradient Guidance

Empower Structure-based Molecule Optimization with Gradient Guidance

Keyue Qiu*, Yuxuan Song*, Jie Yu, Hongbo Ma, Ziyao Cao, Mingyue Zheng, Hao Zhou, Wei-Ying Ma
Forty-Second International Conference on Machine Learning (ICML 2025)
Poster
Paper
ICLR 2025
Redefining the Task of Bioactivity Prediction

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 2025)
Poster
Paper

Educations

  • 2023.09 - Present: B.S. in Economics and Management (Minor), Tsinghua University
  • 2022.09 - Present: B.S. in Computer Science and Technology (Major), Tsinghua University

Internships

  • 2025.12 - Present: Research Intern, Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign.
  • 2025.09 - 2025.10: Research Intern, i-Vision Group, Tsinghua University.
  • 2025.05 - 2025.08: Research Intern, Guangming Lab (Shenzhen), Shenzhen.
  • 2024.07 - 2025.02: Research Intern, GenSi Lab, Tsinghua University.
  • 2024.02 - 2024.06: Research Intern, ATOM Lab, Tsinghua University.

Blogs