Daniel Bolya

dbolya's activity

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

upvoted a collection 7 months ago

Perception Encoder

Collection

OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code. • 19 items • Updated Sep 19, 2025 • 7

upvoted a collection 8 months ago

Perception LM

Collection

7 items • Updated Apr 17, 2025 • 63

upvoted a collection 11 months ago

Perception Encoder

Collection

16 items • Updated 8 days ago • 78

upvoted 2 papers 11 months ago

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

Paper • 2504.13181 • Published Apr 17, 2025 • 35

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

Paper • 2504.13180 • Published Apr 17, 2025 • 20