Jay Wu

zhangjiewu's activity

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

upvoted a paper 5 months ago

Test-Time Training with KV Binding Is Secretly Linear Attention

Paper • 2602.21204 • Published Feb 24 • 32

upvoted a paper 7 months ago

Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?

Paper • 2512.13281 • Published Dec 15, 2025 • 65

liked a model 8 months ago

nvidia/ChronoEdit-14B-Diffusers-Paint-Brush-Lora

Image-to-Image • Updated Nov 21, 2025 • 32 • 23

liked 3 models 9 months ago

nvidia/ChronoEdit-14B-Diffusers-Upscaler-Lora

Image-to-Image • Updated Nov 21, 2025 • 60 • 94

nvidia/difix_ref

0.9B • Updated 7 days ago • 12.8k • 7

nvidia/ChronoEdit-14B-Diffusers

Other • 16B • Updated Nov 21, 2025 • 78 • 170

updated a collection 9 months ago

ChronoEdit

Collection

ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation • 8 items • Updated 12 days ago • 15

liked a model 10 months ago

nvidia/difix

0.9B • Updated 7 days ago • 5.95k • 30

liked a Space about 1 year ago

Paused

Agents

37

Difix3D

🚀

37

Interface to interact with NVIDIA's Difix3D+ model

updated a model about 1 year ago

nvidia/difix

0.9B • Updated 7 days ago • 5.95k • 30

published a model about 1 year ago

nvidia/difix_ref

0.9B • Updated 7 days ago • 12.8k • 7

updated a model about 1 year ago

nvidia/difix_ref

0.9B • Updated 7 days ago • 12.8k • 7

published a Space about 1 year ago

Paused

Agents

37

Difix3D

🚀

37

Interface to interact with NVIDIA's Difix3D+ model

published a model about 1 year ago

nvidia/difix

0.9B • Updated 7 days ago • 5.95k • 30

upvoted 2 papers over 1 year ago

Long-Context Autoregressive Video Modeling with Next-Frame Prediction

Paper • 2503.19325 • Published Mar 25, 2025 • 73

Impossible Videos

Paper • 2503.14378 • Published Mar 18, 2025 • 61