zhongweixie/qwen3vl-8b-claw-vineppo-claweval-20260927 Image-Text-to-Text • 9B • Updated 1 day ago • 12
zhongweixie/qwen3vl-8b-claw-vineppo-claweval-20260927 Image-Text-to-Text • 9B • Updated 1 day ago • 12
zhongweixie/qwen3vl-8b-claw-drgrpo-claweval-20260927 Image-Text-to-Text • 9B • Updated 1 day ago • 14
zhongweixie/qwen3vl-8b-claw-drgrpo-claweval-20260927 Image-Text-to-Text • 9B • Updated 1 day ago • 14
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning Paper • 2609.36820 • Published 6 days ago • 27