Machine Intelligence Laboratory (The University of Tokyo)

MIL-UT's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

tossyy 

updated a dataset 25 days ago

MIL-UT/DEJIMA-dataset

Viewer • Updated 25 days ago • 27.2M • 105 • 1

tossyy 

published a dataset 26 days ago

MIL-UT/DEJIMA-dataset

Viewer • Updated 25 days ago • 27.2M • 105 • 1

k-uehara 

updated a dataset 5 months ago

MIL-UT/JA-OKVQA-Reasoning

Viewer • Updated Jul 30 • 15k • 16

k-uehara 

published a dataset 9 months ago

MIL-UT/JA-OKVQA-Reasoning

Viewer • Updated Jul 30 • 15k • 16

k-uehara 

published 2 models 10 months ago

MIL-UT/Asagi-4B

Image-Text-to-Text • 4B • Updated Feb 24 • 43 • 5

MIL-UT/Asagi-14B

Image-Text-to-Text • 14B • Updated Feb 24 • 124 • 11

k-uehara 

updated 4 models 10 months ago

MIL-UT/Asagi-14B

Image-Text-to-Text • 14B • Updated Feb 24 • 124 • 11

MIL-UT/Asagi-4B

Image-Text-to-Text • 4B • Updated Feb 24 • 43 • 5

MIL-UT/Asagi-8B

Image-Text-to-Text • 8B • Updated Feb 24 • 27 • 4

MIL-UT/Asagi-2B

Image-Text-to-Text • 2B • Updated Feb 24 • 426 • 6

k-uehara 

updated a collection 10 months ago

Asagi-VLM

Collection

Asagi is a Japanese Vision & Language model, trained on a large-scale synthetic dataset. • 4 items • Updated 29 days ago • 7

k-uehara 

published a model 10 months ago

MIL-UT/Asagi-8B

Image-Text-to-Text • 8B • Updated Feb 24 • 27 • 4

k-uehara 

published a model 11 months ago

MIL-UT/Asagi-2B

Image-Text-to-Text • 2B • Updated Feb 24 • 426 • 6

mukuta 

authored a paper over 1 year ago

Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images

Paper • 2406.13393 • Published Jun 19, 2024 • 5