fun-research (fun-research)

yucornetto

authored a paper 2 months ago

Randomized Autoregressive Visual Generation

Paper • 2411.00776 • Published Nov 1, 2024 • 17

yucornetto

updated a model 5 months ago

fun-research/TiTok

Updated Aug 28, 2024 • 12

yucornetto

updated a Space 7 months ago

Running on Zero

12

🏆

TiTok

yucornetto

authored 2 papers 7 months ago

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models

Paper • 2406.09416 • Published Jun 13, 2024 • 27

An Image is Worth 32 Tokens for Reconstruction and Generation

Paper • 2406.07550 • Published Jun 11, 2024 • 57

Peng-Wang

authored a paper 9 months ago

COCONut: Modernizing COCO Segmentation

Paper • 2404.08639 • Published Apr 12, 2024 • 28

yucornetto

authored a paper 9 months ago

COCONut: Modernizing COCO Segmentation

Paper • 2404.08639 • Published Apr 12, 2024 • 28

yucornetto

updated a Space about 1 year ago

Runtime error

6

🌖

KMaXDeepLab

Peng-Wang

authored a paper over 1 year ago

MVDream: Multi-view Diffusion for 3D Generation

Paper • 2308.16512 • Published Aug 31, 2023 • 102

yucornetto

authored a paper over 1 year ago

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Paper • 2308.02487 • Published Aug 4, 2023 • 12

yucornetto

updated a Space over 1 year ago

Running

12

🏢

FC CLIP

Peng-Wang

authored a paper over 1 year ago

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

Paper • 2307.01097 • Published Jul 3, 2023 • 10

fun-research

AI & ML interests

fun-research's activity

Randomized Autoregressive Visual Generation

fun-research/TiTok

TiTok

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models

An Image is Worth 32 Tokens for Reconstruction and Generation

COCONut: Modernizing COCO Segmentation

COCONut: Modernizing COCO Segmentation

KMaXDeepLab

MVDream: Multi-view Diffusion for 3D Generation

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

FC CLIP

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

AI & ML interests

Team members 4

fun-research's activity

TiTok

KMaXDeepLab

FC CLIP