AI & ML interests
Artificial General Intelligence
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
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 • 618 • 7 -
DeepGlint-AI/UniME-LLaVA-1.6-7B
Image-Text-to-Text • 8B • Updated • 36 • 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 • 41 • 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 • 618 • 7 -
DeepGlint-AI/UniME-LLaVA-1.6-7B
Image-Text-to-Text • 8B • Updated • 36 • 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 • 41 • 3
Large-Scale Visual Representation Model