I work on post-training for general-purpose agents at Tencent. I focus on how agents organize tasks, use tools, and carry out multi-step workflows.
Previously, I worked on embodied intelligence at Alibaba DAMO Academy. I led the development of ZeroSearch, a training framework for search agents. I was also one of the project leads for RynnBrain, where I was responsible for model pre-training and post-training. My research covers search agents, multimodal learning, and embodied intelligence.
Experience & Education
CURRENTTencent General-purpose agents · Model post-training
An open-source embodied foundation model for egocentric perception, spatiotemporal grounding, physical reasoning, and planning. Contributions include pre-training, Chain-of-Point reasoning, VLA, and training infrastructure.
An autoregressive framework that jointly models robot actions and future visual states. WorldVLA precedes RynnVLA-002; its original repository now redirects to the successor project.