8 3 2

Haobo Yuan

HarborYuan

https://yuanhaobo.me

AI & ML interests

computer vision

Recent Activity

updated a dataset about 1 month ago

OMG-Research/video-res

updated a model about 2 months ago

HarborYuan/ovsam_models

New activity about 2 months ago

HarborYuan/ovsam_models:Add model card

View all activity

Organizations

HarborYuan's activity

updated a dataset about 1 month ago

OMG-Research/video-res

Viewer • Updated 21 days ago • 2.47k • 27

updated a model about 2 months ago

HarborYuan/ovsam_models

Mask Generation • Updated Sep 30 • 3

New activity in HarborYuan/ovsam_models about 2 months ago

Add model card

#1 opened about 2 months ago by

nielsr

updated a Space about 2 months ago

Sleeping

📚

Open-Vocabulary SAM

New activity in HarborYuan/ovsam about 2 months ago

Link demo to paper

#4 opened about 2 months ago by

nielsr

updated a dataset 4 months ago

HarborYuan/omgseg_data

Updated Aug 2 • 10 • 1

New activity in HarborYuan/ovsam 4 months ago

the demo is error, could you restart it?

#3 opened 4 months ago by

HUG-NAN

updated a model 5 months ago

HarborYuan/omgseg_data

Updated Jul 10

authored a paper 5 months ago

Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model

Paper • 2406.19369 • Published Jun 27 • 2

updated a dataset 5 months ago

HarborYuan/imagenet

Preview • Updated Jun 28 • 3

authored a paper 5 months ago

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Paper • 2406.19389 • Published Jun 27 • 51

liked a dataset 5 months ago

ILSVRC/imagenet-1k

Updated Jul 16 • 23k • 416

upvoted 3 papers 5 months ago

Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model

Paper • 2406.19369 • Published Jun 27 • 2

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

Paper • 2406.19389 • Published Jun 27 • 51

MotionBooth: Motion-Aware Customized Text-to-Video Generation

Paper • 2406.17758 • Published Jun 25 • 18

updated 2 datasets 7 months ago

HarborYuan/HQSeg

Preview • Updated May 1 • 13 • 1

HarborYuan/MLLM-Finetune

Preview • Updated Apr 27 • 4

authored a paper 7 months ago

OMG-Seg: Is One Model Good Enough For All Segmentation?

Paper • 2401.10229 • Published Jan 18

New activity in LXT/OMG_Seg 10 months ago

Apply for community grant: Academic project (gpu)

#2 opened 10 months ago by

LXT

Update main.py

#4 opened 10 months ago by

HarborYuan