Zekai Gu

EXCAI's activity

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

published 2 models 7 days ago

VAST-AI/EdenLive-5B-Causal-Diffusers

Image-to-Video • 5B • Updated 10 days ago • 24

VAST-AI/EdenLive-14B-Causal-Diffusers

Image-to-Video • 16B • Updated 10 days ago • 9

updated 4 models 10 days ago

VAST-AI/EdenLive-14B-Causal-Diffusers

Image-to-Video • 16B • Updated 10 days ago • 9

VAST-AI/EdenLive-14B-Diffusers

Image-to-Video • 16B • Updated 10 days ago • 26

VAST-AI/EdenLive-5B-Causal-Diffusers

Image-to-Video • 5B • Updated 10 days ago • 24

VAST-AI/EdenLive-5B-Diffusers

Image-to-Video • 5B • Updated 10 days ago • 32

upvoted a collection 11 days ago

SMD

Collection

Simplifying and Improving On-Policy Distillation for Few-Step Diffusion • 19 items • Updated 22 days ago • 5

updated a model 12 days ago

EXCAI/ForcingBooster

Text-to-Video • Updated 12 days ago

updated a model 15 days ago

VAST-AI/EdenLive

Image-to-Video • Updated 15 days ago • 533 • 24

upvoted a collection 16 days ago

ForcingBooster

Collection

We introduce ForcingBooster, a general framework that dynamically allocates denoising steps to individual patches. • 2 items • Updated 19 days ago • 1

upvoted a paper 16 days ago

ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Paper • 2610.12625 • Published 28 days ago • 32

published 2 models 16 days ago

VAST-AI/EdenLive-14B-Diffusers

Image-to-Video • 16B • Updated 10 days ago • 26

VAST-AI/EdenLive-5B-Diffusers

Image-to-Video • 5B • Updated 10 days ago • 32

authored 3 papers 18 days ago

ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Paper • 2610.12625 • Published 28 days ago • 32

PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training

Paper • 2610.14698 • Published 26 days ago • 2

UniRecGen: Unifying Multi-View 3D Reconstruction and Generation

Paper • 2604.01479 • Published Apr 1 • 4

New activity in EXCAI/ForcingBooster 18 days ago

Add model card

#1 opened 19 days ago by

nielsr

updated a collection 19 days ago

ForcingBooster

Collection

We introduce ForcingBooster, a general framework that dynamically allocates denoising steps to individual patches. • 2 items • Updated 19 days ago • 1

submitted a paper to Daily Papers 19 days ago

ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Paper • 2610.12625 • Published 28 days ago • 32