Zhongxi Chen
Zhongxi Chen is a researcher affiliated with Shanghai Jiao Tong University (SJTU) who serves as co-first author of BORA, an offline-to-online reinforcement learning framework for real-world dexterous Vision-Language-Action models. He is listed as a researcher at Tencent YouTu Lab and was previously an MS student at Xiamen University, with expertise in diffusion-based models and camouflaged object detection. He is best known for his work on BORA and CamoDiffusion, having published at venues including AAAI, ECCV, and ACM Multimedia.
“BORA solves a critical bottleneck in deploying dexterous robot hands — the gap between a VLA model that 'understands' a task visually and one that can actually execute it reliably with 20+ fingers and joints in the real world. It achieves an 86% average success rate on five real-world dexterous tasks, up from ~53% with pure imitation learning.”
Source→“Designed the action-conditioned critic that 'fuses continuous action chunks with the VLM's cognition tokens... enables precise, action-conditioned value guidance evaluated on physical execution consequences rather than visual context alone.'”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.