activity
20242026
collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Power-Softmax: Towards Secure LLM Inference over Encrypted Data

Itamar Zimerman, Allon Adir, Ehud Aharoni +7

Modern cryptographic methods for implementing privacy-preserving LLMs such as \gls{HE} require the LLMs to have a polynomial form. Forming such a representation is challenging beca…

cs.LG2026

TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors

Ido Andrew Atad, Itamar Zimerman, Shahar Katz +1

Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet,…

cs.LG2025

Efficient Decoding Methods for Language Models on Encrypted Data

Matan Avitan, Moran Baruch, Nir Drucker +2

Large language models (LLMs) power modern AI applications, but processing sensitive data on untrusted servers raises privacy concerns. Homomorphic encryption (HE) enables computati…

cs.LG2025

Differential Mamba

Nadav Schneider, Itamar Zimerman, Eliya Nachmani

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by prom…

cs.LG2025

Overflow Prevention Enhances Long-Context Recurrent LLMs

Assaf Ben-Kish, Itamar Zimerman, M. Jehanzeb Mirza +4

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on h…

cs.LG2025

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

Roy Eisenstadt, Itamar Zimerman, Lior Wolf

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" pro…