Jiangmiao Pang
Papers
1
Total Citations
3
H-Index
1
About
Jiangmiao Pang is a researcher at the forefront of computer vision, robotics, and embodied AI, with work spanning object detection, instance segmentation, 3D perception, and vision-language integration. Among his most recognized contributions is RoboGround (2025), which investigates the use of grounded vision-language priors — specifically grounding masks as intermediate representations — to improve policy generalization in robotic manipulation tasks. This work exemplifies Pang's broader research philosophy: bridging perceptual understanding and actionable intelligence in robotic systems. By leveraging spatial guidance alongside semantic richness, RoboGround addresses a fundamental challenge in making robots more adaptable to diverse real-world scenarios. Though early in its citation trajectory with 3 citations, the work reflects timely and increasingly critical directions in embodied AI research. Pang's scholarship sits at a productive intersection of foundational vision research and practical robotics applications, making his contributions relevant both to theoretical advances in perception and to the engineering of intelligent autonomous systems. His ongoing work continues to push boundaries in how machines see, understand, and interact with their environments.
Research Focus
Key Achievements
Top Papers
- 1RoboGround: Robotic Manipulation with Grounded Vision-Language Priors3 citations · 2025