Amil Dravid

amildravid4292's activity

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

upvoted a paper 5 days ago

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

Paper • 2609.38079 • Published 6 days ago • 53

upvoted a collection over 1 year ago

Test-Time-Registers

Collection

A collection of models augmented with test-time registers, a training-free way to add register tokens to pretrained models. • 3 items • Updated Jun 23, 2025 • 3

upvoted a paper over 1 year ago

Vision Transformers Don't Need Trained Registers

Paper • 2506.08010 • Published Jun 9, 2025 • 22

upvoted 2 papers about 2 years ago

Diffusion Models as Data Mining Tools

Paper • 2408.02752 • Published Jul 20, 2024 • 15

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Paper • 2407.14435 • Published Jul 19, 2024 • 7

upvoted a paper over 2 years ago

Interpreting the Weight Space of Customized Diffusion Models

Paper • 2406.09413 • Published Jun 13, 2024 • 20