UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
Paper • 2604.14967 • Published • 15
SquaredCube PRO
squaredcuber
·
AI & ML interests
Post-training & RL
Recent Activity
updated a Space 7 days ago
squaredcuber/mlintern-v7premium published a Space 7 days ago
squaredcuber/mlintern-v7premium published a bucket 7 days ago
squaredcuber/mlintern-v7q36-bucket-2Organizations
upvoted a paper 15 days ago