BetaRare
yongliang-wu/DFT
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
- Owner
- yongliang-wu (personal account)
- Stars
- Stars: 928
- Forks
- Forks: 27
- Language
- Python
- License
- None
- Created
- 2025
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by yongliang-wu
All 2 repos by yongliang-wu- yongliang-wu/NumProStars: 150PythonPrototype
Nearby in Python
All Python repos- jwk1rose/RL_LearningStars: 928PythonBeta
- mustafaaljadery/gemma-2B-10MStars: 928PythonBeta
- wileewang/TransPixelerStars: 928PythonBeta
- seanliang/ConvertToUTF8Stars: 928PythonBeta
- bspaans/python-mingusStars: 928PythonBeta
- platomav/MCExtractorStars: 928PythonBeta