Dai

Pengwa's activity

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

upvoted a paper 24 days ago

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Paper • 2412.04467 • Published 25 days ago • 104

upvoted a paper 6 months ago

SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

Paper • 2407.00367 • Published Jun 29 • 9

upvoted a paper 11 months ago

V-IRL: Grounding Virtual Intelligence in Real Life

Paper • 2402.03310 • Published Feb 5 • 15

updated a model over 1 year ago

Pengwa/path-to-save-model

Text-to-Image • Updated Jul 14, 2023 • 5

liked a Space over 2 years ago

Running

33

⚡

Screen Image Demoireing