EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Paper
•
2507.21848
•
Published
•
7
Zhang Xingjian
Zhang199
AI & ML interests
Large Multimodal Models
Recent Activity
new activity
3 days ago
Zhang199/TinyLLaVA-Video-R1:Extend length of video which can be processed?
updated
a model
14 days ago
Zhang199/TinyLLaVA-Qwen2-0.5B-SigLIP
updated
a model
25 days ago
Zhang199/EDGE-GRPO-Qwen-1.5B
Organizations
None yet
upvoted
a
paper
25 days ago