Fan-Yun Sun
Papers
1
Total Citations
3
H-Index
1
About
Fan-Yun Sun is a rising researcher at the intersection of computer vision, robotics, and embodied AI. Her work centers on bridging the gap between real-world perception and virtual simulation for robotic learning. In her highly cited paper, "GRS: Generating Robotic Simulation Tasks from Real-World Images" (2025), Sun introduces a novel system that creates digital twin simulations from a single RGB-D observation, enabling virtual agent training with solvable tasks. By leveraging vision-language models (VLMs), her three-stage pipeline—perception, generation, and verification—automates the creation of realistic, task-ready environments, addressing a critical bottleneck in sim-to-real transfer. Though early in her career, Sun’s contributions are already shaping how researchers approach scalable robot learning. Her work has been recognized for its practical impact, offering a pathway to reduce the manual effort in simulation design. With a focus on real-to-sim alignment and task generation, Fan-Yun Sun is poised to become a key figure in advancing autonomous systems that learn from and adapt to the physical world.
Research Focus
Key Achievements
Top Papers
- 1GRS: Generating Robotic Simulation Tasks from Real-World Images3 citations · 2025