Mingqiao Ye PRO

mqye

·

ymq2017

AI & ML interests

None yet

Recent Activity

published a model about 1 month ago

EPFL-VILAB/MODUS-Hunyuan

updated a model about 1 month ago

EPFL-VILAB/MODUS-Hunyuan

upvoted a paper about 1 month ago

Native Action-Prior Learning from Videos for World Action Models

View all activity

Organizations

published a model about 1 month ago

EPFL-VILAB/MODUS-Hunyuan

Image-to-Image • 83B • Updated Oct 10 • 71

updated a model about 1 month ago

EPFL-VILAB/MODUS-Hunyuan

Image-to-Image • 83B • Updated Oct 10 • 71

upvoted a paper about 1 month ago

Native Action-Prior Learning from Videos for World Action Models

Paper • 2610.03391 • Published Oct 2 • 56

liked a Space 2 months ago

MODUS

MODUS any-to-any multimodal demo (16 aligned modalities)

liked a model 3 months ago

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated 4 days ago • 6.54M • • 6.88k

New activity in EPFL-VILAB/MODUS 4 months ago

Add pipeline tag, link to paper

#1 opened 4 months ago by

authored a paper 4 months ago

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Paper • 2607.25948 • Published Jul 28 • 13

upvoted a paper 4 months ago

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Paper • 2607.25948 • Published Jul 28 • 13

submitted a paper to Daily Papers 4 months ago

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Paper • 2607.25948 • Published Jul 28 • 13

updated a Space 4 months ago

MODUS

MODUS any-to-any multimodal demo (16 aligned modalities)

updated a model 4 months ago

EPFL-VILAB/MODUS

Any-to-Any • 15B • Updated Jul 30 • 3

published a model 4 months ago

EPFL-VILAB/MODUS

Any-to-Any • 15B • Updated Jul 30 • 3

updated a Space 4 months ago

MODUS

MODUS any-to-any multimodal demo (16 aligned modalities)

published a Space 4 months ago

MODUS

MODUS any-to-any multimodal demo (16 aligned modalities)

updated a model 4 months ago

mqye/modus-16mod-stage3

Any-to-Any • 15B • Updated Jul 5

published a model 4 months ago

mqye/modus-16mod-stage3

Any-to-Any • 15B • Updated Jul 5

New activity in EPFL-VILAB/MODUS 5 months ago

Apply for a GPU community grant: Academic project

#1 opened 5 months ago by

published a Space 5 months ago

MODUS

MODUS any-to-any multimodal demo (16 aligned modalities)

liked a Space 7 months ago

Search over Tokens

Test-time search over ordered visual tokens.

upvoted a collection 7 months ago

AR Models with FlexTok

Autoregressive models trained on FlexTok. • 6 items • Updated May 5 • 1