UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper
•
2510.13515
•
Published
•
11
UniME-V2
-
-
TianchengGu/UniME-V2-LLaVA-OneVision-8B
Image-Text-to-Text • 8B • Updated • 14 • 2 -
TianchengGu/UniME-V2-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 23 • 2 -
TianchengGu/UniME-V2-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 58 • 2 -
TianchengGu/UniME-V2-reranker-Qwen25VL-7B
Image-Text-to-Text • 8B • Updated • 30 • 2 -
TianchengGu/UniME-V2-Training-Datasets
Viewer • Updated • 1.99M • 47 • 3