Zou

APolarishen's activity

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

authored 6 papers 1 day ago

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers

Paper • 2508.16211 • Published Aug 22, 2025 • 1

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching

Paper • 2509.10312 • Published Sep 12, 2025

Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers

Paper • 2510.04188 • Published Oct 5, 2025 • 1

HunyuanVideo 1.5 Technical Report

Paper • 2511.18870 • Published Nov 24, 2025 • 29

LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

Paper • 2602.20497 • Published Feb 24

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

Paper • 2602.05449 • Published Feb 5 • 1

liked a model 1 day ago

tencent/DisCa

Updated 3 days ago • 10

updated a model 3 days ago

tencent/DisCa

Updated 3 days ago • 10

upvoted a paper 17 days ago

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Paper • 2603.29620 • Published 18 days ago • 46

upvoted an article about 1 month ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

Mar 5

•

125

upvoted a paper 2 months ago

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Paper • 2602.03139 • Published Feb 3 • 44

upvoted a paper 3 months ago

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

Paper • 2601.19325 • Published Jan 27 • 81

New activity in Comfy-Org/HunyuanVideo_1.5_repackaged 4 months ago

Anyone tested this yet?

👍 2

29

#1 opened 5 months ago by

gpundt

liked a model 8 months ago

tencent/Hunyuan-GameCraft-1.0

Image-to-Video • Updated Aug 19, 2025 • 69 • 312

liked a model 9 months ago

tencent/HunyuanWorld-1

Image-to-3D • Updated Oct 20, 2025 • 6.5k • 419