MASA - a jadohu Collection

jadohu 's Collections

MASA

MASA

updated 24 days ago

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

jadohu/Qwen3-14B-MASA

Reinforcement Learning • 15B • Updated 25 days ago • 23 • 1
jadohu/Qwen3-14B-GRPO

Reinforcement Learning • 15B • Updated 25 days ago • 9 • 1
jadohu/Qwen3-8B-MASA

Reinforcement Learning • 8B • Updated 25 days ago • 17 • 2
jadohu/Qwen3-8B-MASA-efficient

Reinforcement Learning • 8B • Updated 24 days ago • 11 • 1
jadohu/Qwen3-8B-GRPO

Reinforcement Learning • 8B • Updated 25 days ago • 11 • 1