activity
20212026
most citedImaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation

2 citations · 4 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

BRo-JEPA: Learning Modular Transformations in Latent Space

Divyansh Jha, Yuanfang Xie, Brennen Yu +1

Can neural networks learn algebraic rules from visual inputs, or do they merely fit observed patterns? We study this question using MNIST (or EMNIST letters) as states and modular…