Liang Heng
Papers
1
Total Citations
3
H-Index
1
About
Liang Heng is a rising researcher in embodied AI and robotic manipulation, with a focus on bridging vision, language, and action for more intuitive human-robot interaction. His work centers on developing object-centric, prompt-driven models that allow robots to interpret and execute tasks specified through multiple modalities—including natural language, goal images, and goal videos. Heng’s key contribution is the introduction of CrayonRobo, a novel vision-language-action framework designed to overcome the ambiguity of language and the overspecification of visual inputs, enabling robots to grasp task intent with greater precision and flexibility. Though early in his career, his 2025 paper on this topic has already garnered attention, accumulating 3 citations and signaling growing interest in his approach. By tackling the fundamental challenge of multimodal task specification, Heng is helping to shape the next generation of robotic systems that can understand and act upon human goals more naturally. His work stands at the intersection of computer vision, natural language processing, and robotics, promising to make robotic assistants more adaptable and user-friendly in real-world environments.
Research Focus
Key Achievements
Top Papers
- 1