RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Paper
•
2510.02240
•
Published
•
17
Kaiwen TUO
KaiwenTUO
AI & ML interests
None yet
Recent Activity
authored
a paper
8 days ago
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via
Multi-Stage Reinforcement Learning
liked
a dataset
10 days ago
FSCCS/ReasonMap-Train
Organizations
None yet
authored
a
paper
8 days ago