Learning Vision from Models Rivals Learning Vision from Data
Paper • 2312.17742 • Published • 16
Saved trending papers
-
-
Unsupervised Universal Image Segmentation
Paper • 2312.17243 • Published • 20 -
Perspectives on the State and Future of Deep Learning - 2023
Paper • 2312.09323 • Published • 8 -
Vision-Language Models as a Source of Rewards
Paper • 2312.09187 • Published • 12 -
A Vision Check-up for Language Models
Paper • 2401.01862 • Published • 11 -
Denoising Vision Transformers
Paper • 2401.02957 • Published • 31 -
Learning and Leveraging World Models in Visual Representation Learning
Paper • 2403.00504 • Published • 33 -
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
Paper • 2403.10516 • Published • 16 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 107 -
The Road Less Scheduled
Paper • 2405.15682 • Published • 27