Dense World

Dense-World's activity

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

shilinxu 

authored a paper about 19 hours ago

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Paper • 2501.04001 • Published 1 day ago • 21

LXT 

authored a paper about 19 hours ago

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Paper • 2501.04001 • Published 1 day ago • 21

HarborYuan 

authored 2 papers about 23 hours ago

LLAVADI: What Matters For Multimodal Large Language Models Distillation

Paper • 2407.19409 • Published Jul 28, 2024

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Paper • 2501.04001 • Published 1 day ago • 21

zhangtao-whu 

updated 4 models 2 days ago

Dense-World/Sa2VA_InternVL2.5_26b

Image-Text-to-Text • Updated 2 days ago

Dense-World/Sa2VA_InternVL2.5_8b

Image-Text-to-Text • Updated 2 days ago

Dense-World/Sa2VA_InternVL2.5_4b

Image-Text-to-Text • Updated 2 days ago

Dense-World/Sa2VA-4B

Image-Text-to-Text • Updated 2 days ago • 2

LXT 

authored 2 papers 29 days ago

DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

Paper • 2412.07589 • Published 30 days ago • 45

EMOv2: Pushing 5M Vision Model Frontier

Paper • 2412.06674 • Published about 1 month ago • 13

LXT 

authored a paper about 1 month ago

HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing

Paper • 2412.04280 • Published Dec 5, 2024 • 13

HarborYuan 

updated a model about 1 month ago

Dense-World/Sa2VA-4B

Image-Text-to-Text • Updated 2 days ago • 2

zhangtao-whu 

updated a dataset 2 months ago

Dense-World/video-res

Viewer • Updated Nov 4, 2024 • 2.47k • 2

HarborYuan 

updated a dataset 3 months ago

Dense-World/video-res

Viewer • Updated Nov 4, 2024 • 2.47k • 2

LXT 

authored 6 papers 3 months ago

Generalizable Entity Grounding via Assistance of Large Language Model

Paper • 2402.02555 • Published Feb 4, 2024

DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries

Paper • 2404.00086 • Published Mar 29, 2024

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow

Paper • 2405.20282 • Published May 30, 2024

GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning

Paper • 2403.12003 • Published Mar 18, 2024 • 2

LLAVADI: What Matters For Multimodal Large Language Models Distillation

Paper • 2407.19409 • Published Jul 28, 2024

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Paper • 2410.08261 • Published Oct 10, 2024 • 50