GRPO-MA: Multi-Answer Generation in GRPO for Stable and Efficient Chain-of-Thought Training
Paper • 2509.24494 • Published • 11 •
2
Guanghui Ren
sundrops
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
Rollback: Experience Backtracking in World Models for Policy Improvement authored a paper 3 days ago
RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models upvoted a paper 11 days ago
Rollback: Experience Backtracking in World Models for Policy ImprovementOrganizations
None yet
commented 2
papers about 1 year ago