About Me
I am an undergraduate student majoring in
Intelligent Science and Technology
at Nankai University.
My research interests lie in
reinforcement learning, robot learning, and embodied intelligence.
I am interested in how intelligent systems perceive, learn, and
interact with the physical world.
I also maintain a personal blog for study notes, paper readings, and
learning records at
dpthink.vercel.app.
Research Interests
- Reinforcement learning and decision making
- Robot learning, policy learning, and embodied intelligence
- Vision-language-action models and action generation
- Generative models for robot policies, including diffusion and flow-based methods
Publications
-
2026
Yufu Dong
Manuscript, 2026.
A controlled audit of few-step generative robot policies,
comparing task success and executed-motion smoothness across
diffusion, flow-matching, and MeanFlow-style policy families.
Selected Writing & Notes
-
Paper reading note on diffusion-based robot policy learning.
Blog note.
-
A structured learning note for vision-language-action models.
Learning note.
-
A first-principles note on flow matching and generative models.
Generative modeling note.
Feel free to contact me by
email if you would
like to discuss reinforcement learning, embodied intelligence, robot
learning papers, or related study projects.
Design based on
Minimal Light
theme.
Copyright © 2026 Yufu Dong.