Previously led self-evolving large model research, Tencent AI Seattle former senior researcher Yu Wenhao joins OpenAI

robot
Abstract generation in progress

According to Beating Monitoring, former Tencent AI Seattle Laboratory senior researcher Yu Wenhao officially joined OpenAI last month, serving as an AGI Researcher. He confirmed on LinkedIn that he will participate in shaping the next-generation AI models and contribute to building AGI.

Yu Wenhao earned his Ph.D. in Computer Science from the University of Notre Dame in 2023. Over the past two years, his core research areas have been reinforcement learning post-training for large models, as well as reasoning and agents. In academia, he has published more than 30 papers at top conferences, with over 5,700 citations, and he received the EMNLP 2023 Outstanding Paper Award. During his time at Tencent, he led the proposal of the R-Zero training paradigm, exploring how to enable a model to self-evolve its capabilities by generating challenging problems and engaging in game-like head-to-head battles between models, without human-labeled data. In addition, the agent project WebVoyager led by him was adopted by organizations including OpenAI and Google.

With his deep accumulation in large model self-play (Self-play) and the agent field, Yu Wenhao is highly aligned with OpenAI’s current strategic focus on using reinforcement learning to improve model reasoning capabilities.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin