Heng Su
Papers
2
Total Citations
11
H-Index
2
About
Heng Su is a rising researcher at the forefront of embodied intelligence and artificial general intelligence, with key contributions spanning reinforcement learning for robotics and the theoretical foundations of world models. In their highly cited 2024 work, Su proposed a novel obstacle avoidance method for robotic arms based on reinforcement learning, directly addressing the critical challenge of dynamic obstacle adaptation in industrial automation—a problem that traditional control algorithms have long struggled to solve. This paper has already garnered 9 citations, reflecting its immediate relevance to practical robotics. Complementing this applied work, Su co-authored a comprehensive survey on world models, examining the intersection of multimodal large language models and video generation systems like Sora. This survey, which has earned 2 citations, provides a vital roadmap for researchers pursuing artificial general intelligence by clarifying the distinction between understanding the world and merely predicting future states. Su’s dual focus on real-world robotic control and high-level AI theory positions them as a versatile thinker whose work bridges immediate industrial needs with long-term AGI aspirations.
Research Focus
Key Achievements
Top Papers
- 1
- 2