2 papers
cs.CV2026
More Accurate, Less Human: Gestalt Grouping in Vision Models
Sudhanva Manjunath Athreya, Sai Phani Kumar Malladi
Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects. These a…
cs.LG2026
HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
Sudhanva Manjunath Athreya, Paul Rosen
Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to inte…