UniME
Collection
UniME is a series of multimodal large language models trained for learning universal multimodal embedding.
•
4 items
•
Updated
•
4
MLLM4Embedding
-
-
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Paper • 2412.16855 • Published • 5 -
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
Paper • 2410.05160 • Published • 4 -
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Paper • 2507.04590 • Published • 16 -
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 11 -
SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
Paper • 2510.12709 • Published • 10