Chan Hee Song
Papers
1
Total Citations
15
H-Index
1
About
Chan Hee Song is a rising researcher at the intersection of robotics, computer vision, and natural language processing, whose work focuses on endowing machines with spatial intelligence. His most impactful contribution, "RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics" (2025), directly tackles a critical bottleneck in embodied AI: the inability of vision-language models to accurately perceive and reason about spatial relationships in both 2D images and 3D environments. By developing novel training methodologies and benchmarks, Song’s work enables robots to move beyond simple object recognition toward a genuine understanding of concepts like "to the left of," "behind," or "inside," which are fundamental for safe and effective physical interaction. Already garnering 15 citations in its first year, this research is rapidly shaping how the robotics community approaches spatial reasoning. Song’s achievements are particularly notable for bridging the gap between large-scale pretrained models and the grounded, spatial demands of real-world robotics, making him a key voice in the push toward more capable and context-aware autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1