Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
Paper
•
2601.20614
•
Published
•
118
•
19
Shubham Parashar
shubhamprshr
AI & ML interests
Computer Vision, Multi-Modal Learning
Recent Activity
commented on
a paper
14 days ago
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
commented on
a paper
15 days ago
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
updated
a model
3 months ago
shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Organizations
commented
a
paper
14 days ago