ziyun zeng PRO

zengziyun's activity

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

updated a dataset 6 days ago

zengziyun/VideoArgusBench

Viewer • Updated 6 days ago • 1.03k • 167 • 1

authored 2 papers 13 days ago

Aurora: Unified Video Editing with a Tool-Using Agent

Paper • 2605.18748 • Published May 18 • 30

MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

Paper • 2605.18652 • Published May 18 • 8

published a dataset 13 days ago

zengziyun/VideoArgusBench

Viewer • Updated 6 days ago • 1.03k • 167 • 1

updated a dataset 17 days ago

zengziyun/asdifagelifadgufladuf

Updated 17 days ago • 2.61k

published a dataset 17 days ago

zengziyun/asdifagelifadgufladuf

Updated 17 days ago • 2.61k

updated a dataset 18 days ago

zengziyun/temp_video_results

Viewer • Updated 18 days ago • 1.93k • 85

updated a dataset about 1 month ago

MMComposition/MMComposition

Viewer • Updated Jul 2 • 4.12k • 69 • 1

published 2 datasets about 1 month ago

MMComposition/MMComposition

Viewer • Updated Jul 2 • 4.12k • 69 • 1

zengziyun/temp_video_results

Viewer • Updated 18 days ago • 1.93k • 85

updated a dataset about 2 months ago

zengziyun/tempweb

Viewer • Updated Jun 27 • 6.21k • 18

upvoted a paper 2 months ago

Agent Skills Should Go Beyond Text: The Case for Visual Skills

Paper • 2606.01414 • Published May 31 • 10

upvoted 2 papers 3 months ago

Aurora: Unified Video Editing with a Tool-Using Agent

Paper • 2605.18748 • Published May 18 • 30

MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents

Paper • 2605.18652 • Published May 18 • 8

published a dataset 3 months ago

zengziyun/tempweb

Viewer • Updated Jun 27 • 6.21k • 18

updated a dataset 3 months ago

zengziyun/tempp

Updated May 3 • 30

published a dataset 4 months ago

zengziyun/tempp

Updated May 3 • 30

updated a dataset 5 months ago

zengziyun/temp_edit

Viewer • Updated Mar 20 • 7.95M • 13

upvoted a paper 5 months ago

Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion

Paper • 2603.15614 • Published Mar 16 • 6

updated a dataset 5 months ago

zengziyun/temp_edit

Viewer • Updated Mar 20 • 7.95M • 13