Wenwen Qiang
Wenwen Qiang is an Associate Professor at the National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences in Beijing. He received his Ph.D. from the University of Chinese Academy of Sciences in 2022 and has authored more than 50 papers in venues including IEEE TPAMI, ICML, NeurIPS, ICLR, and CVPR. His research focuses on causal inference, AI security, and embodied intelligence, with recent work on causal approaches to large language model post-training and policy optimization.
“Temporal GRPO keeps changes on the preceding stages close to zero and produces the largest positive improvement at md, indicating that it preserves acquired preceding behaviors and concentrates the update on the stage responsible for the rollout difference.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.