Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning
Doohyuk Jang
jadohu
AI & ML interests
None yet
Recent Activity
upvoted a paper 7 days ago
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL authored a paper 18 days ago
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache QuantizationOrganizations
models 14
jadohu/Qwen2.5-32B-GRPO
Reinforcement Learning • 33B • Updated • 7
jadohu/Qwen3-8B-GRPO
Reinforcement Learning • 8B • Updated • 17 • 1
jadohu/Qwen3-8B-MASA-efficient
Reinforcement Learning • 8B • Updated • 12 • 1
jadohu/Qwen3-8B-MASA
Reinforcement Learning • 8B • Updated • 12 • 2
jadohu/Qwen3-14B-GRPO
Reinforcement Learning • 15B • Updated • 11 • 1
jadohu/Qwen3-14B-MASA
Reinforcement Learning • 15B • Updated • 15 • 1
jadohu/Qwen2.5-32B-MASA-efficient
Reinforcement Learning • 33B • Updated • 9
jadohu/MongMong
Text Generation • 8B • Updated • 6
jadohu/anole_drafter
Text-to-Image • 0.5B • Updated
jadohu/llamagen_drafter
Text-to-Image • Updated • 52 • 1
datasets 0
None public yet