MeiYi

natalie5's activity

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

upvoted a paper about 8 hours ago

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published 2 days ago • 18

updated a model 1 day ago

natalie5/Cosmos3-Super_Mirror

Updated 1 day ago

published a model 1 day ago

natalie5/Cosmos3-Super_Mirror

Updated 1 day ago

New activity in AkaneTendo25/Cosmos3-ConvRot 2 days ago

Update README.md

👀 1

#1 opened 2 days ago by

natalie5

upvoted a collection 7 days ago

Xiaomi-Robotics-U0

Collection

Unified embodied synthesis model that bridges foundation image generation and embodied world modeling • 2 items • Updated 12 days ago • 10

upvoted a paper 9 days ago

Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget

Paper • 2607.13125 • Published 7 days ago • 136

liked a model 9 days ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated 2 days ago • 31.6k • • 1.56k

New activity in nvidia/PiD 15 days ago

Undistilled checkpoints?

3

#1 opened 2 months ago by

natalie5

liked a model 16 days ago

peaes/GeoWorld

Updated 18 days ago • 124 • 4

New activity in robbyant/lingbot-video-moe-30b-a3b 16 days ago

Comfyui support and workflow. ?

👍 8

1

#1 opened 17 days ago by

mediainteresting

upvoted a paper 16 days ago

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 17 days ago • 64

liked a model 17 days ago

robbyant/lingbot-video-moe-30b-a3b

30B • Updated 17 days ago • 1.08k • 121

upvoted a collection 17 days ago

LingBot-Video

Collection

3 items • Updated 17 days ago • 21

upvoted a paper 19 days ago

EXAONE 4.5 Technical Report

Paper • 2604.08644 • Published Apr 9 • 75

liked a model 19 days ago

tencent/Hy3

Text Generation • 299B • Updated 5 days ago • 18.6k • • 871

liked a model 20 days ago

shauray/l2p-ckpts

Updated 19 days ago • 2

liked a model 22 days ago

mistralai/Leanstral-1.5-119B-A6B

Updated 10 days ago • 531 • 207

upvoted 2 collections 23 days ago

KVAE 2.0

Collection

KVAE 2.0 is a family of video tokenizers with a time compression ratio of 4 and spacial compression ratio of 8 and 16 • 2 items • Updated Apr 16 • 5

KVAE-Audio

Collection

KVAE-Audio is a continuous full-band audio waveform autoencoder • 1 item • Updated 26 days ago • 7

liked a model 26 days ago

kandinskylab/KVAE-Audio

Updated 24 days ago • 80 • 54