Tao Liu

utaotao

·

Utaotao

AI & ML interests

None yet

Recent Activity

upvoted a paper about 11 hours ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

authored a paper 12 days ago

Simple-OPD: Demystifying Warm-up for On-policy Distillation

upvoted a paper 12 days ago

Simple-OPD: Demystifying Warm-up for On-policy Distillation

View all activity

Organizations

None yet

Papers 4

arxiv:2608.06802

arxiv:2601.09195

arxiv:2510.10977

arxiv:2509.23595

models 1

utaotao/Qwen3-4B-Non-Thinking-GRPO-Math-300step

4B • Updated May 21 • 5 • 1

datasets 0

None public yet