EPFL-VILAB/MODUS-Hunyuan
Image-to-Image • 83B • Updated
AI & ML interests
None defined yet.
Recent Activity
Papers
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
(1D) Ordered Tokens Enable Efficient Test-Time Search
EPFL-VILAB/Video-4M-tokenizers
Updated • 1
EPFL-VILAB/Video-4M-models
Image-to-Video • Updated • 1
EPFL-VILAB/FlexAR-3B-T2I
Text-to-Image • 3B • Updated • 30
EPFL-VILAB/GridAR-3B-T2I
Text-to-Image • 3B • Updated • 23
EPFL-VILAB/FlexAR-1B-T2I
Text-to-Image • 1B • Updated • 38
EPFL-VILAB/FlexAR-382M-T2I
Text-to-Image • 0.5B • Updated • 26
EPFL-VILAB/FlexAR-113M-T2I
Text-to-Image • 0.2B • Updated • 23 • 1
EPFL-VILAB/MODUS
Any-to-Any • 15B • Updated • 3
EPFL-VILAB/videoflextok_d18_d18_k600
Other • 1B • Updated • 18.2k
EPFL-VILAB/videoflextok_d18_d28
Other • 3B • Updated • 238 • 1
EPFL-VILAB/FlexAR-1B-C2I
2B • Updated • 13
EPFL-VILAB/TST-Replica-adapted
0.4B • Updated
EPFL-VILAB/TST-Replica-segmentation
95.3M • Updated
EPFL-VILAB/TST-Replica
0.4B • Updated
EPFL-VILAB/TST-ProcTHOR-segmentation
95.3M • Updated • 1
EPFL-VILAB/TST-ProcTHOR-adapted
0.4B • Updated
EPFL-VILAB/TST-ProcTHOR
0.4B • Updated
EPFL-VILAB/TST-Scannet-pp-segmentation
95.3M • Updated
EPFL-VILAB/TST-Scannet-pp-adapted
0.4B • Updated
EPFL-VILAB/TST-Scannet-pp
0.4B • Updated
EPFL-VILAB/flextok_d18_d28_dfn
3B • Updated • 444 • 1
EPFL-VILAB/flextok_d18_d28_in1k
3B • Updated • 266
EPFL-VILAB/flextok_d18_d18_in1k
0.9B • Updated • 199
EPFL-VILAB/flextok_d12_d12_in1k
0.3B • Updated • 276
EPFL-VILAB/flextok_vae_c16
83.8M • Updated • 91
EPFL-VILAB/flextok_vae_c8
83.7M • Updated • 18
EPFL-VILAB/flextok_vae_c4
83.7M • Updated • 14
EPFL-VILAB/VPE-ViPer
Image-Text-to-Text • Updated • 13 • 3
EPFL-VILAB/Metric-ViPer
Image-Text-to-Text • Updated • 20 • 2