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
Fidelity-Aware Data Composition for Robust Robot Generalization authored a paper 3 days ago
Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training authored a paper 3 days ago
GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic ManipulationOrganizations
None yet
commented a
paper 8 months ago
commented a
paper 10 months ago