DeepGlint

DeepGlint-AI's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

Kaichengalex 

updated a dataset 21 days ago

DeepGlint-AI/DanQing100M

Viewer • Updated 21 days ago • 99.9M • 2.36k • 49

yiyexy 

submitted a paper to Daily Papers about 2 months ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published Feb 9 • 52

tanhuajie2001 

authored a paper 3 months ago

RoboBrain 2.5: Depth in Sight, Time in Mind

Paper • 2601.14352 • Published Jan 20 • 12

Kaichengalex 

in DeepGlint-AI/DanQing100M 3 months ago

Add task categories, language and Arxiv ID to metadata

#2 opened 3 months ago by

nielsr

Kaichengalex 

authored a paper 3 months ago

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset

Paper • 2601.10305 • Published Jan 15 • 36

Kaichengalex 

submitted a paper to Daily Papers 3 months ago

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset

Paper • 2601.10305 • Published Jan 15 • 36

Kaichengalex 

published a dataset 3 months ago

DeepGlint-AI/DanQing100M

Viewer • Updated 21 days ago • 99.9M • 2.36k • 49

tanhuajie2001 

authored 3 papers 3 months ago

Towards Cross-View Point Correspondence in Vision-Language Models

Paper • 2512.04686 • Published Dec 4, 2025

RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration

Paper • 2510.26536 • Published Oct 30, 2025

Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

Paper • 2512.23703 • Published Dec 29, 2025 • 7

tanhuajie2001 

submitted a paper to Daily Papers 4 months ago

Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

Paper • 2512.23703 • Published Dec 29, 2025 • 7

Kaichengalex 

authored 3 papers 6 months ago

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

Paper • 2510.18795 • Published Oct 21, 2025 • 11

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28, 2025 • 49

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

Paper • 2510.13515 • Published Oct 15, 2025 • 12

tanhuajie2001 

authored a paper 6 months ago

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Paper • 2509.23661 • Published Sep 28, 2025 • 49

Kaichengalex 

authored a paper 7 months ago

Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

Paper • 2509.09118 • Published Sep 11, 2025 • 8

yiyexy 

published a model 8 months ago

DeepGlint-AI/ViCToR-LLaVA-SigLIP2-Qwen2.5-7b

Image-Text-to-Text • 8B • Updated Aug 15, 2025 • 4 • 2

yiyexy 

updated a model 8 months ago

DeepGlint-AI/ViCToR-LLaVA-SigLIP2-Qwen2.5-7b

Image-Text-to-Text • 8B • Updated Aug 15, 2025 • 4 • 2

xiangan 

in DeepGlint-AI/rice-vit-large-patch14-560 9 months ago

Add `library_name` to metadata and update Github link

1

#1 opened 9 months ago by

nielsr

yiyexy 

in DeepGlint-AI/mlcd-vit-large-patch14-336 9 months ago

Improve model card: Update to RICE paper details, add usage, and refine metadata

1

#1 opened 9 months ago by

nielsr