Papers
1
Total Citations
2
H-Index
1
About
Ruochong Li is a rising force in robotics and embodied AI, whose work centers on dexterous manipulation, vision-language-action models, and generalizable robotic grasping. Li’s most notable contribution, *DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping* (2026), introduces a pioneering framework that integrates visual, linguistic, and motor reasoning to enable robots to grasp diverse objects in unstructured, real-world environments—moving beyond the single-object, constrained settings that have long limited the field. This work, already garnering early citations, addresses a critical bottleneck in robotic dexterity by leveraging large-scale pretrained models for task-agnostic, adaptive grasping. Li’s research pushes the boundaries of what robots can achieve in dynamic, arbitrary scenarios, with implications for manufacturing, assistive robotics, and home automation. As a young scholar, Li’s innovative approach to combining multimodal learning with physical action has quickly attracted attention, positioning them as a key voice in the next generation of general-purpose robotic systems. Their work exemplifies the shift toward holistic, real-world capable AI—a direction that promises to reshape how robots interact with the human world.
Research Focus
Key Achievements
Top Papers
- 1