Ziqi Gao

UWGZQ

·

https://uwgzq.github.io

uwGZQ

AI & ML interests

Multi-modal, Computer Vision

Recent Activity

authored a paper 21 days ago

Vision-Language Grounding as Bidirectional Concept Correspondence

submitted a paper 22 days ago

Vision-Language Grounding as Bidirectional Concept Correspondence

upvoted a paper 22 days ago

Vision-Language Grounding as Bidirectional Concept Correspondence

View all activity

Organizations

Collections 1

Papers 2

arxiv:2608.07886

arxiv:2602.23543

spaces 1

ConCor-1 Concept Correspondence

All text-span ↔ image-mask correspondences in a pair

models 6

UWGZQ/ConCor-1

Image Segmentation • 0.9B • Updated 22 days ago • 452 • 2

UWGZQ/ft_mm_gdino

UWGZQ/TRASER

Video-Text-to-Text • 928k • Updated Mar 8 • 20 • 4

UWGZQ/GenVerse

Updated Aug 27, 2024

UWGZQ/Genverse_vid

Updated Aug 23, 2024

UWGZQ/Genverse_img

Updated Aug 23, 2024

datasets 7

UWGZQ/ConCor-1-Data

Viewer • Updated 22 days ago • 1.28M • 325 • 3

UWGZQ/Synthetic_Visual_Genome2

Viewer • Updated Jul 10 • 590k • 131 • 8

UWGZQ/pixmo_images_external

Updated Jun 25 • 6

UWGZQ/pixmo_images

Viewer • Updated Jun 25 • 1.07M • 4.21k • 1

UWGZQ/rf100_masks

Viewer • Updated Apr 7 • 3 • 9

UWGZQ/VideoOlmoDefections

Viewer • Updated Sep 19, 2025 • 10.2k • 31

UWGZQ/GenerateAnySceneDataset

Viewer • Updated May 16, 2025 • 61k • 45 • 1