Jun-Bo Wang
Papers
1
Total Citations
3
H-Index
1
About
Jun-Bo Wang is a rising researcher at the forefront of robotic manipulation and embodied AI, whose work bridges the gap between high-level task understanding and low-level physical interaction. His research centers on affordance learning, 3D object-centric manipulation, and the integration of vision-language models for robotics. Wang’s most notable contribution is the development of **UniAff**, a unified representation framework that models affordances for both tool usage and articulated object manipulation. By combining 3D motion constraints with semantic reasoning, UniAff enables robots to understand not just *what* an object can do, but *how* to interact with it—a critical step toward general-purpose manipulation. While his career is still in its early stages, his work has already garnered attention (3 citations for his 2025 paper), signaling strong potential for future impact. Wang’s approach challenges the fragmented nature of prior affordance research, offering a cohesive paradigm that could redefine how robots learn to handle everyday objects. For students and researchers, his work represents a compelling synthesis of perception, reasoning, and control—a blueprint for the next generation of intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1