PrototypeCommon
RLHFlow/Reinforce-Ada
[COLM 2026] An adaptive sampling framework for Reinforce-style LLM post training.
- Owner
- RLHFlow (organization)
- Stars
- Stars: 100
- Forks
- Forks: 17
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by RLHFlow
All 6 repos by RLHFlow- RLHFlow/RLHF-Reward-ModelingStars: 1,546PythonBeta
- RLHFlow/Online-RLHFStars: 543PythonAlpha
- RLHFlow/Online-DPO-R1Stars: 275PythonAlpha
- RLHFlow/Minimal-RLStars: 274PythonAlpha
- RLHFlow/Self-rewarding-reasoning-LLMStars: 229PythonPrototype
Nearby in Python
All Python repos- jobbie-bot/Summer-2027-Tech-InternshipsStars: 100PythonPrototype
- yangsir2077/pixel-loomStars: 100PythonPrototype
- CumulusAlpha/Dex-SupermimicStars: 100PythonPrototype
- ghewgill/pyqverStars: 100PythonPrototype
- vpulim/mangoStars: 100PythonPrototype
- wesabe/fixofxStars: 100PythonPrototype