PrototypeCommon
THU-BPM/RLCSD
Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"
- Owner
- THU-BPM (organization)
- Stars
- Stars: 115
- Forks
- Forks: 5
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- large-language-modelsllmon-policy-distillationopsdreinforcement-learningself-distillationopd
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by THU-BPM
All 5 repos by THU-BPM- THU-BPM/MarkLLMStars: 1,088PythonBeta
- THU-BPM/MarkDiffusionStars: 334Jupyter NotebookAlpha
- THU-BPM/Omni-SafetyBenchStars: 116PythonPrototype
- THU-BPM/chatgpt-sqlStars: 106PythonPrototype
Nearby in Python
All Python repos- sucikhairida/CenterNagaStars: 115PythonPrototype
- null0526/dario-genesisStars: 115PythonPrototype
- Aevonix/FlashAlignStars: 115PythonPrototype
- mnaberez/supervisor_twiddlerStars: 115PythonPrototype
- brosner/django-taggingStars: 115PythonPrototype
- jwagner/playitslowlyStars: 115PythonPrototype