Running
1
Meta Ability
ðŸ§
Enhance reasoning in large models by aligning meta-abilities
Zhiyuan Hu
zhiyuanhucs
AI & ML interests
None yet
Recent Activity
authored
a paper
21 days ago
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
authored
a paper
21 days ago
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
upvoted
a
paper
22 days ago
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Organizations
