Mingzhe Li's picture

7 2

Mingzhe Li

Mubuky

·

https://www.mubuky.com

Mubuky

AI & ML interests

RL & Agent

Recent Activity

authored a paper 1 day ago

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation

upvoted a paper 3 days ago

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation

upvoted a paper 12 days ago

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

View all activity

Organizations

liked a dataset 3 months ago

OpenMOSS-Team/VideoThinkBench

Viewer • Updated Dec 20, 2025 • 4.9k • 790 • 13

liked a model 4 months ago

Qwen/WorldPM-72B

Text Classification • 73B • Updated May 17, 2025 • 64 • 80