Ming-Yu Liu

mingyuliutw's activity

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

upvoted a collection 11 days ago

Cosmos Tokenizer

Collection

A suite of image and video tokenizers • 13 items • Updated 1 day ago • 37

liked a model 11 days ago

nvidia/Cosmos-1.0-Diffusion-7B-Text2World

Updated 8 days ago • 127k • 174

upvoted a collection 11 days ago

Cosmos

Collection

The collection of Cosmos models • 31 items • Updated 1 day ago • 233

liked 12 models 11 days ago

nvidia/Cosmos-1.0-Tokenizer-DV8x16x16

Updated 6 days ago • 924 • 14

nvidia/Cosmos-1.0-Tokenizer-CV8x8x8

Updated 6 days ago • 4.24k • 11

nvidia/Cosmos-1.0-Prompt-Upsampler-12B-Text2World

Updated 8 days ago • 4.21k • 10

nvidia/Cosmos-1.0-Diffusion-14B-Video2World

Updated 8 days ago • 2.22k • 43

nvidia/Cosmos-1.0-Diffusion-14B-Text2World

Updated 8 days ago • 56.4k • 39

nvidia/Cosmos-1.0-Diffusion-7B-Video2World

Updated 8 days ago • 3.15k • 25

nvidia/Cosmos-1.0-Diffusion-7B-Decoder-DV8x16x16ToCV8x8x8

Updated 8 days ago • 2.35k • 9

nvidia/Cosmos-1.0-Autoregressive-13B-Video2World

Updated 8 days ago • 862 • 28

nvidia/Cosmos-1.0-Autoregressive-12B

Updated 8 days ago • 779 • 24

nvidia/Cosmos-1.0-Autoregressive-5B-Video2World

Updated 8 days ago • 1.3k • 22

nvidia/Cosmos-1.0-Autoregressive-4B

Updated 8 days ago • 1.83k • 42

nvidia/Cosmos-1.0-Guardrail

Updated 8 days ago • 4.33k • 38

authored a paper 6 months ago

Wolf: Captioning Everything with a World Summarization Framework

Paper • 2407.18908 • Published Jul 26, 2024 • 32

authored a paper 9 months ago

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Paper • 2404.19752 • Published Apr 30, 2024 • 24

authored a paper 11 months ago

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

Paper • 2402.19481 • Published Feb 29, 2024 • 21

authored 2 papers over 1 year ago

ATT3D: Amortized Text-to-3D Object Synthesis

Paper • 2306.07349 • Published Jun 6, 2023 • 9

Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models

Paper • 2305.10474 • Published May 17, 2023 • 1