Talia Konkle

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

A biologically-inspired foveated interface for deep vision models

Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Rethinking Language-Alignment in Human Visual Cortex with Syntax Manipulation and Word Models