AI & ML interests
Artificial General Intelligence
Recent Activity
Papers
Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
Organization Card
DeepGlint Research
UniME is a series of multimodal large language models trained for learning universal multimodal embedding.
-
DeepGlint-AI/UniME-Phi3.5-V-4.2B
Image-Text-to-Text • Updated • 60 • 7 -
DeepGlint-AI/UniME-LLaVA-1.6-7B
Image-Text-to-Text • 8B • Updated • 43 • 5 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 41 -
DeepGlint-AI/UniME-LLaVA-OneVision-7B
Image-Text-to-Text • 8B • Updated • 22 • 3
UniME is a series of multimodal large language models trained for learning universal multimodal embedding.
-
DeepGlint-AI/UniME-Phi3.5-V-4.2B
Image-Text-to-Text • Updated • 60 • 7 -
DeepGlint-AI/UniME-LLaVA-1.6-7B
Image-Text-to-Text • 8B • Updated • 43 • 5 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 41 -
DeepGlint-AI/UniME-LLaVA-OneVision-7B
Image-Text-to-Text • 8B • Updated • 22 • 3
models 18
DeepGlint-AI/UniME-R1-4B
Image-Text-to-Text • Updated
DeepGlint-AI/UniME-R1-2B
Image-Text-to-Text • Updated • 1
DeepGlint-AI/UniDoc-RL-7B
8B • Updated • 5
DeepGlint-AI/UniDoc-RL-3B
4B • Updated • 9
DeepGlint-AI/ViCToR-LLaVA-SigLIP2-Qwen2.5-7b
Image-Text-to-Text • 8B • Updated • 18 • 2
DeepGlint-AI/rice-vit-large-patch14-560
Image Feature Extraction • 0.3B • Updated • 50 • 11
DeepGlint-AI/MLCD-Seg
9B • Updated • 7 • 9
DeepGlint-AI/mlcd-vit-bigG-patch14-448
Image Feature Extraction • 2B • Updated • 611 • 4
DeepGlint-AI/UniME-LLaVA-OneVision-7B
Image-Text-to-Text • 8B • Updated • 22 • 3
DeepGlint-AI/UniME-Phi3.5-V-4.2B
Image-Text-to-Text • Updated • 60 • 7