Ziyu Wan

Raywzy's activity

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

authored 5 papers about 5 hours ago

AvatarArtist: Open-Domain 4D Avatarization

Paper • 2503.19906 • Published Mar 25, 2025 • 8

$ε$-VAE: Denoising as Visual Decoding

Paper • 2410.04081 • Published Oct 5, 2024 • 7

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

Paper • 2508.02095 • Published Aug 4, 2025 • 10

AvatarPointillist: AutoRegressive 4D Gaussian Avatarization

Paper • 2604.04787 • Published Apr 6 • 12

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Paper • 2605.21573 • Published 7 days ago • 92

upvoted a paper about 20 hours ago

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Paper • 2605.21573 • Published 7 days ago • 92

liked 2 models 4 days ago

microsoft/Lens

Text-to-Image • Updated 4 days ago • 673 • 93

microsoft/Lens-Turbo

Text-to-Image • Updated 4 days ago • 908 • 98

liked a model about 1 year ago

microsoft/Phi-4-mini-reasoning

Text Generation • 4B • Updated Dec 10, 2025 • 40.5k • 228

liked a Space about 1 year ago

Running on Zero

Agents

17

AvatarArtist

🎨

17

Open-Domain 4D Avatarization

upvoted a paper almost 2 years ago

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

Paper • 2408.03178 • Published Aug 6, 2024 • 40

updated a model about 3 years ago

Raywzy/CVPR23_NDRF_Demo

Updated Apr 18, 2023