3 papers
cs.LG2026
Self-Supervised Learning from Structural Invariance
Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee +3
Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related dat…
cs.CV2026
seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
Hafez Ghaemi, Eilif Muller, Shahab Bakhtiari
Joint-embedding self-supervised learning (SSL) commonly relies on transformations such as data augmentation and masking to learn visual representations, a task achieved by enforcin…
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…