PrototypeCommon
AMAP-ML/MathForge
[ICLR 2026] Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
- Owner
- AMAP-ML (organization)
- Stars
- Stars: 129
- Forks
- Forks: 1
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- data-augmentationgrpomathematical-reasoning
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by AMAP-ML
All 30 repos by AMAP-ML- AMAP-ML/SkillClawStars: 2,735PythonRC
- AMAP-ML/LongHorizon-HarnessStars: 1,794PythonBeta
- AMAP-ML/FluxTextStars: 920PythonBeta
- AMAP-ML/DreamX-WorldStars: 787PythonBeta
- AMAP-ML/Tree-GRPOStars: 409PythonAlpha
- AMAP-ML/DreamX-CreatorStars: 318PythonAlpha
Nearby in Python
All Python repos- ReckyStar/mcd-party-plannerStars: 129PythonPrototype
- wusuaya/overtime-meal-buddyStars: 129PythonPrototype
- Lanqiao-Luca/ai-video-markerStars: 129PythonPrototype
- ralsina/pyqt-by-exampleStars: 129PythonPrototype
- brosner/everyblock_codeStars: 129PythonPrototype
- marook/tagfsStars: 129PythonPrototype