Quanzhu Niu

QuanzhuNiu's activity

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

upvoted a paper 26 days ago

Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

Paper • 2607.08765 • Published 28 days ago • 22

liked a dataset about 1 month ago

godx7/Pinpoint-Bench

Updated Jul 2 • 171 • 2

authored a paper about 1 month ago

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

Paper • 2607.00115 • Published Jun 30 • 13

upvoted a paper about 1 month ago

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

Paper • 2607.00115 • Published Jun 30 • 13

authored 2 papers about 1 month ago

SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track

Paper • 2603.27241 • Published Mar 28

Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding

Paper • 2604.26031 • Published Apr 28

liked a model about 1 month ago

godx7/PixelEyes-8B

Image-Text-to-Text • 9B • Updated Jul 3 • 21 • 3

upvoted a collection about 1 month ago

PixelEyes

Collection

A Visual Search Agent Guided by a Referring Segmentation Model • 4 items • Updated Jul 2 • 4

liked a model about 1 month ago

godx7/PixelEyes-4B

Image-Text-to-Text • 5B • Updated Jul 3 • 61 • 3

upvoted a paper about 2 months ago

UniSHARP: Universal Sharp Monocular View Synthesis

Paper • 2606.07514 • Published Jun 5 • 16

upvoted a paper 6 months ago

SAMTok: Representing Any Mask with Two Words

Paper • 2601.16093 • Published Jan 22 • 44

liked a dataset 8 months ago

QuanzhuNiu/OVIS_RGBD

Preview • Updated Dec 18, 2025 • 175 • 1

upvoted a paper 8 months ago

Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation

Paper • 2512.16913 • Published Dec 18, 2025 • 35

updated a dataset 8 months ago

QuanzhuNiu/OVIS_RGBD

Preview • Updated Dec 18, 2025 • 175 • 1

updated a collection 8 months ago

DVIS_Depth

Collection

Checkpoints and datasets for paper "Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation". • 4 items • Updated Dec 18, 2025 • 1

published a dataset 8 months ago

QuanzhuNiu/OVIS_RGBD

Preview • Updated Dec 18, 2025 • 175 • 1

updated a model 8 months ago

QuanzhuNiu/SaSaSa2VA-4B

4B • Updated Nov 24, 2025 • 14 • 1

updated a model 9 months ago

QuanzhuNiu/SaSaSa2VA-26B

26B • Updated Nov 20, 2025 • 20 • 1

New activity in QuanzhuNiu/SaSaSa2VA-26B 9 months ago

Update model card for Sa2VA-i

#1 opened 9 months ago by

nielsr

New activity in QuanzhuNiu/SaSaSa2VA-4B 9 months ago

Update model card for Sa2VA-i

1

#1 opened 9 months ago by

nielsr