-
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 11 -
TianchengGu/UniME-V2-LLaVA-OneVision-8B
Image-Text-to-Text • 8B • Updated • 24 • 2 -
TianchengGu/UniME-V2-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 578 • 2 -
TianchengGu/UniME-V2-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 598 • 2
Kaicheng Yang
Kaichengalex
AI & ML interests
Multimodal Representation Learning/ Vision-Language Pretraining/DeepResearch
Recent Activity
upvoted
a
paper
about 12 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
liked
a model
1 day ago
Qwen/Qwen3-VL-Embedding-8B
liked
a model
1 day ago
Qwen/Qwen3-VL-Embedding-2B
Organizations
-
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 11 -
TianchengGu/UniME-V2-LLaVA-OneVision-8B
Image-Text-to-Text • 8B • Updated • 24 • 2 -
TianchengGu/UniME-V2-Qwen2VL-7B
Image-Text-to-Text • 8B • Updated • 578 • 2 -
TianchengGu/UniME-V2-Qwen2VL-2B
Image-Text-to-Text • 2B • Updated • 598 • 2
datasets
6
Kaichengalex/WebPerson-1M
Viewer
•
Updated
•
944k
•
88
•
1
Kaichengalex/WebPerson-5M
Viewer
•
Updated
•
5M
•
344
•
2
Kaichengalex/RealSyn15M
Viewer
•
Updated
•
13.5M
•
330
•
3
Kaichengalex/RealSyn30M
Viewer
•
Updated
•
27M
•
194
•
4
Kaichengalex/RealSyn100M
Viewer
•
Updated
•
89.6M
•
1.4k
•
16
Kaichengalex/YFCC15M
Viewer
•
Updated
•
13.4M
•
6.3k
•
7