Re^3Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
Paper • 2608.21305 • Published
Re³Cap
Model weights for "Re³Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning" (EMNLP 2026 Main)
-
-
kkk5/Re3Cap-CLIP-LLaVA1.5-7B
Image-Text-to-Text • 7B • Updated • 51 -
kkk5/Re3Cap-SC-LLaVA1.5-7B
Image-Text-to-Text • 7B • Updated • 51 -
kkk5/Re3Cap-CIM-LLaVA1.5-7B
Image-Text-to-Text • 7B • Updated • 44 -
kkk5/Re3Cap-CLIP-Qwen2-VL-7B
Image-Text-to-Text • 8B • Updated • 52 -
kkk5/Re3Cap-SC-Qwen2-VL-7B
Image-Text-to-Text • 8B • Updated • 44 -
kkk5/Re3Cap-CIM-Qwen2-VL-7B
Image-Text-to-Text • 8B • Updated • 37 -
kkk5/Re3Cap-CLIP-Qwen2.5-VL-7B
Image-Text-to-Text • 8B • Updated • 34 -
kkk5/Re3Cap-SC-Qwen2.5-VL-7B
Image-Text-to-Text • 8B • Updated • 36 -
kkk5/Re3Cap-CIM-Qwen2.5-VL-7B
Image-Text-to-Text • 8B • Updated • 33 -
kkk5/Re3Cap-CLIP-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 47 -
kkk5/Re3Cap-SC-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 44 -
kkk5/Re3Cap-CIM-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 48