Kevin Zhang

Kevin-thu's activity

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

upvoted a paper 1 day ago

DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency

Paper • 2609.39096 • Published 7 days ago • 7

authored a paper 5 days ago

DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency

Paper • 2609.39096 • Published 7 days ago • 7

upvoted a paper 9 days ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published 13 days ago • 33

upvoted a paper 12 days ago

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Paper • 2609.34981 • Published 13 days ago • 138

upvoted a paper about 1 month ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published Aug 26 • 333

liked a model about 2 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.84M • • 17.5k

upvoted a paper about 2 months ago

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Paper • 2608.13552 • Published Aug 13 • 48

upvoted a paper 2 months ago

Wonder: Video World Model Done Better

Paper • 2607.26037 • Published Jul 28 • 20

liked a model 2 months ago

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 3.61M • • 6.04k

upvoted a paper 2 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 528

updated a model 3 months ago

Kevin-thu/StoryMem

Text-to-Video • Updated Jul 22 • 44 • 96

upvoted 6 papers 3 months ago

Infinite Worlds with Versatile Interactions

Paper • 2607.07534 • Published Jul 8 • 47

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published Jul 7 • 49

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published Jul 8 • 64

Vision Pretraining for Dense Spatial Perception

Paper • 2607.05247 • Published Jul 6 • 44

Qwen-Image-2.0-RL Technical Report

Paper • 2606.27608 • Published Jun 25 • 55

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Paper • 2606.28128 • Published Jun 26 • 55

upvoted 3 papers 4 months ago

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published Jun 25 • 84

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

Paper • 2606.16449 • Published Jun 15 • 7

Memento: Reconstruct to Remember for Consistent Long Video Generation

Paper • 2606.14667 • Published Jun 12 • 19