10 6 4

Haobo Yuan

HarborYuan

https://yuanhaobo.me

AI & ML interests

computer vision

Recent Activity

new activity about 2 months ago

ByteDance/Sa2VA-1B:ValueError due to Mismatch in Tensor Shapes when Loading Model

updated a dataset about 2 months ago

Dense-World/Sa2VA-Training

liked a dataset about 2 months ago

Dense-World/Sa2VA-Training

View all activity

Organizations

HarborYuan's activity

New activity in ByteDance/Sa2VA-1B about 2 months ago

ValueError due to Mismatch in Tensor Shapes when Loading Model

#3 opened about 2 months ago by

Nikuson

updated a dataset about 2 months ago

Dense-World/Sa2VA-Training

Updated Jan 20 • 904 • 3

liked a dataset about 2 months ago

Dense-World/Sa2VA-Training

Updated Jan 20 • 904 • 3

updated 2 models about 2 months ago

Dense-World/Sa2VA-26B

Updated Jan 17 • 13

Dense-World/Sa2VA-1B

Updated Jan 17 • 18

published 2 models about 2 months ago

Dense-World/Sa2VA-1B

Updated Jan 17 • 18

Dense-World/Sa2VA-26B

Updated Jan 17 • 13

updated a dataset about 2 months ago

HarborYuan/omgseg_data

Updated Jan 17 • 19 • 1

New activity in ByteDance/Sa2VA-4B about 2 months ago

Issue when running inference with the 4B model

#3 opened 2 months ago by

armandal

updated a dataset 2 months ago

HarborYuan/vid_ref_seg_benchmark

Preview • Updated Jan 12 • 12

authored 2 papers 2 months 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 Jan 7 • 43

upvoted a collection 2 months ago

Sa2VA Model Zoo

Collection

Huggingace Model Zoo For Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos By Bytedance Seed CV Research • 4 items • Updated Feb 9 • 32

upvoted a paper 2 months ago

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

Paper • 2501.04001 • Published Jan 7 • 43

liked a model 2 months ago

ByteDance/Sa2VA-4B

Image-Text-to-Text • Updated Jan 14 • 2.46k • 69

upvoted a paper 3 months ago

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

Paper • 2412.07589 • Published Dec 10, 2024 • 47

updated a model 3 months ago

Dense-World/Sa2VA-4B

Image-Text-to-Text • Updated Jan 7 • 17

updated a dataset 5 months ago

Dense-World/video-res

Viewer • Updated Nov 4, 2024 • 2.47k • 29

updated a model 5 months ago

HarborYuan/ovsam_models

Mask Generation • Updated Sep 30, 2024 • 3

New activity in HarborYuan/ovsam_models 5 months ago

Add model card

#1 opened 5 months ago by

nielsr