DeepGlint

company

deepglint

Activity Feed Request to join this org

AI & ML interests

Artificial General Intelligence

Recent Activity

xiangan updated a model about 4 hours ago

DeepGlint-AI/MLCD-Embodied-7B

xiangan new activity about 6 hours ago

DeepGlint-AI/llava-mlcd-qwen2.5-7b:Improve language tag

xiangan new activity about 6 hours ago

DeepGlint-AI/MLCD-Embodied-7B:Improve language tag

View all activity

DeepGlint-AI's activity

xiangan

updated a model about 4 hours ago

DeepGlint-AI/MLCD-Embodied-7B

Updated about 4 hours ago • 16 • 6

xiangan

in DeepGlint-AI/llava-mlcd-qwen2.5-7b about 6 hours ago

Improve language tag

#1 opened about 6 hours ago by

lbourdois

xiangan

in DeepGlint-AI/MLCD-Embodied-7B about 6 hours ago

Improve language tag

#1 opened about 6 hours ago by

lbourdois

Kaichengalex

updated a model 1 day ago

DeepGlint-AI/UniME-LLaVA-1.6-7B

Image-Text-to-Text • Updated 1 day ago • 184 • 3

xiangan

updated a model 1 day ago

DeepGlint-AI/MLCD-Seg

Updated 1 day ago • 2 • 5

Kaichengalex

authored a paper 3 days ago

Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs

Paper • 2504.17432 • Published 4 days ago • 36

Kaichengalex

updated a collection 3 days ago

UniME

Collection

UniME is a series of multimodal large language models trained for learning universal multimodal embedding. • 3 items • Updated 3 days ago • 4

Kaichengalex

updated a model 3 days ago

DeepGlint-AI/UniME-Phi3.5-V-4.2B

Image-Text-to-Text • Updated 3 days ago • 54 • 4

Kaichengalex

authored a paper 4 days ago

Decoupled Global-Local Alignment for Improving Compositional Understanding

Paper • 2504.16801 • Published 5 days ago • 15

killTheHostage

updated a model 5 days ago

DeepGlint-AI/MLCD-Seg

Updated 1 day ago • 2 • 5

xiangan

published a model 5 days ago

DeepGlint-AI/MLCD-Seg

Updated 1 day ago • 2 • 5

xiangan

updated a collection 6 days ago

MLCD-VL

Collection

2 items • Updated 6 days ago • 1

Kaichengalex

updated a collection 6 days ago

UniME

Collection

UniME is a series of multimodal large language models trained for learning universal multimodal embedding. • 3 items • Updated 3 days ago • 4

Kaichengalex

published 2 models 6 days ago

DeepGlint-AI/UniME-LLaVA-1.6-7B

Image-Text-to-Text • Updated 1 day ago • 184 • 3

DeepGlint-AI/UniME-Phi3.5-V-4.2B

Image-Text-to-Text • Updated 3 days ago • 54 • 4

xiangan

in DeepGlint-AI/mlcd-vit-bigG-patch14-224 12 days ago

Update config.json

#1 opened 12 days ago by

xiangan

updated a model 13 days ago

DeepGlint-AI/mlcd-vit-bigG-patch14-448

Image Feature Extraction • Updated 13 days ago • 1.47k • 3

Yin-Xie

authored a paper about 2 months ago

RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm

Paper • 2502.12513 • Published Feb 18 • 16

xiangan

authored a paper 2 months ago

RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm

Paper • 2502.12513 • Published Feb 18 • 16

AI & ML interests

Recent Activity

Team members 8

DeepGlint-AI's activity

Improve language tag

Improve language tag

Update config.json