Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity
Gautam Ranka, Shubham Santosh Pandere, Aiden Dsouza
Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle many concepts in each neuro…
cs.CV2026
Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures
Gautam Ranka, Paras Chopra
Deep neural networks trained on natural images are shown to produce outputs consistent with human observers for brightness illusions. While this phenomenon has been documented acro…