Yossi Gandelsman

Teaching Humans Subtle Differences with DIFFusion

In-Context Representation Hijacking

AG-ViT: Atlas-Guided Vision Transformer for Predicting Cognitive Decline

Vision Transformers Don't Need Trained Registers

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs

Teaching Humans Subtle Differences with DIFFusion

Interpreting the Second-Order Effects of Neurons in CLIP

Interpreting the Repeated Token Phenomenon in Large Language Models

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

LLMs can see and hear without any training

Token to Token Learning From Videos

Video Representation Learning Without Natural Videos