EDGE-GRPO - a Zhang199 Collection

Zhang199 's Collections

TinyLLaVA-Video-R1

TinyLLaVA-Video

EDGE-GRPO

updated 6 days ago

Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Zhang199/EDGE-GRPO-Qwen-7B

Text Generation • 8B • Updated 6 days ago • 10
Zhang199/EDGE-GRPO-Qwen-1.5B

Text Generation • 2B • Updated 6 days ago • 28
EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Paper • 2507.21848 • Published 7 days ago • 6