Weiqi Wang

mightyweaver

7 4

·

https://mighty-weaver.github.io/

AI & ML interests

GUI Agent, Reinforcement Learning

Recent Activity

upvoted a paper about 2 hours ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

upvoted a paper about 23 hours ago

EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

upvoted a paper 5 days ago

Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations

View all activity

Organizations

None yet

mightyweaver 's models

None public yet