3 papers
q-bio.NC2025
Why all roads don't lead to Rome: Representation geometry varies across the human visual cortical hierarchy
Arna Ghosh, Zahraa Chorghay, Shahab Bakhtiari +1
Biological and artificial intelligence systems navigate the fundamental efficiency-robustness tradeoff for optimal encoding, i.e., they must efficiently encode numerous attributes…
cs.LG2025
Harnessing small projectors and multiple views for efficient vision pretraining
Kumar Krishna Agrawal, Arna Ghosh, Shagun Sodhani +2
Recent progress in self-supervised (SSL) visual representation learning has led to the development of several different proposed frameworks that rely on augmentations of images but…
cs.LG2024
Learning Successor Features the Simple Way
Raymond Chua, Arna Ghosh, Christos Kaplanis +2
In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successo…