Itamar Zimerman
- Papers
- 9
Cite
Notes
Only stored in your browser.
9papers
Authored papers
9TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors
arXiv 2026
Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
arXiv 2025
Differential Mamba
arXiv 2025
Overflow Prevention Enhances Long-Context Recurrent LLMs
arXiv 2025
Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
arXiv 2025
Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
arXiv 2024
DeciMamba: Exploring the Length Extrapolation Potential of Mamba
arXiv 2024
The Hidden Attention of Mamba Models
arXiv 2024
2-D SSM: A General Spatial Layer for Visual Transformers
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 9 papers