Self-supervised learning of video representations from a child's perspective
Paper • 2402.00300 • Published
Emin Orhan
eminorhan
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
eminorhan/neural-pile-tokenizers updated a dataset 4 days ago
eminorhan/neural-pile-rodent-1x15 updated a dataset 5 days ago
eminorhan/neural-pile-primate-1x15Organizations
None yet
authored 4
papers over 1 year ago
Scaling may be all you need for achieving human-level object recognition capacity with human-like visual experience
Paper • 2308.03712 • Published
Recognition, recall, and retention of few-shot memories in large language models
Paper • 2303.17557 • Published
HVM-1: Large-scale video models pretrained with nearly 5000 hours of human-like video data
Paper • 2407.18067 • Published