Itamar Zimerman

Neural Brain Fields: A NeRF-Inspired Approach for Generating Nonexistent EEG Electrodes

On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

Overflow Prevention Enhances Long-Context Recurrent LLMs

Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability

DeciMamba: Exploring the Length Extrapolation Potential of Mamba

PowerSoftmax: Towards secure LLM Inference Over Encrypted Data