Jang Hyun (Vincent) Cho

janghyuncho7's activity

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

liked a model about 17 hours ago

facebook/PE-Spatial-G14-448

Updated about 7 hours ago • 67 • 7

authored 2 papers 1 day ago

Perception Encoder: The best visual embeddings are not at the output of the network

Paper • 2504.13181 • Published 4 days ago • 21

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Paper • 2504.13180 • Published 4 days ago • 14

updated 5 models 2 days ago

facebook/Perception-LM-8B

Updated 2 days ago • 52 • 13

facebook/Perception-LM-1B

Updated 2 days ago • 137 • 13

facebook/Perception-LM-3B

Updated 2 days ago • 19 • 10

facebook/PE-Lang-G14-448

Updated about 7 hours ago • 32 • 11

facebook/PE-Lang-L14-448

Updated about 7 hours ago • 59 • 4

updated 3 models 3 days ago

facebook/PE-Spatial-G14-448

Updated about 7 hours ago • 67 • 7

facebook/PE-Core-B16-224

Updated about 7 hours ago • 1.72k • 7

facebook/PE-Detection

Updated 3 days ago • 1 • 6

updated a dataset 3 days ago

facebook/PE-Video

Viewer • Updated 3 days ago • 118k • 3.7k • 11

updated 2 models 3 days ago

facebook/PE-Core-G14-448

Updated about 7 hours ago • 2.18k • 10

facebook/PE-Core-L14-336

Updated about 7 hours ago • 3.58k • 14

upvoted 2 papers 3 days ago

Perception Encoder: The best visual embeddings are not at the output of the network

Paper • 2504.13181 • Published 4 days ago • 21

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Paper • 2504.13180 • Published 4 days ago • 14

updated 4 datasets 3 days ago

facebook/PLM-Image-Auto

Updated 3 days ago • 120 • 8

facebook/PLM-Video-Auto

Viewer • Updated 3 days ago • 6.41M • 122 • 7

facebook/PLM-Video-Human

Viewer • Updated 3 days ago • 2.8M • 663 • 10

facebook/PLM-VideoBench

Viewer • Updated 3 days ago • 44k • 634 • 7