Yixiang Chen
Yixiang Chen is a PhD student at the Institute of Automation, Chinese Academy of Sciences, where he researches vision-language-action models, world models, and robotic manipulation. He is known for co-authoring BridgeVLA, a framework for efficient 3D manipulation learning with vision-language models, along with related work such as EC-Flow and BridgeV2W. His publications appear at venues including NeurIPS 2025 and ICCV 2025.
“We introduce XEWorld, a controlled cross-embodiment testbed for world models that isolates embodiments by evaluating held-out robots within physically identical scenes”
Source→“They have developed a highly practical, plug-and-play enhancement for VLA models that requires no architectural changes.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.