Chengcai Yang

Beijing Institute of Technology

Papers

1

Total Citations

4

H-Index

1

About

Chengcai Yang is a rising researcher in robotics and artificial intelligence, with a primary focus on advancing policy learning through generative modeling and video-based demonstration. His most notable contribution, "GraphMimic: Graph-to-Graphs Generative Modeling from Videos for Policy Learning," introduces a novel framework that addresses a critical bottleneck in robotic skill acquisition: the high cost of collecting action-labeled robot data. By leveraging the rich, diverse behavioral and physical knowledge embedded in readily available video data, Yang’s work enables robots to learn complex tasks without expensive direct demonstrations. This approach, which has already garnered 4 citations since its 2025 publication, represents a significant step toward scalable and cost-effective robotic training. Yang’s research sits at the intersection of computer vision, graph neural networks, and reinforcement learning, offering a promising pathway for robots to acquire skills from passive observation. His innovative use of graph-to-graphs generative modeling not only reduces data dependency but also enhances the generalization capabilities of learned policies, marking him as a forward-thinking contributor to the future of autonomous systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
4
Total Citations
4
Avg Citations/Paper
🏆 Most Cited Paper
GraphMimic: Graph-to-Graphs Generative Modeling from Videos for Policy Learning
4 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: Beijing Institute of Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 10 days ago