Mor Geva

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context

Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics

Towards Interpreting Visual Information Processing in Vision-Language Models

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty

When Can Transformers Count to n?

Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces

AdaptVis: Spatial Understanding in Vision-Language Models Requires Adaptive Attention