Volgen
Itamar Zimerman
Itamar Zimerman
PhD Student, The School of Computer Science at Tel Aviv University
Geverifieerd e-mailadres voor tau.ac.il - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
The Hidden Attention of Mamba Models
A Ali, I Zimerman, L Wolf
arXiv preprint arXiv:2403.01590, 2024
462024
Decision s4: Efficient sequence-based rl via state spaces layers
SB David, I Zimerman, E Nachmani, L Wolf
The Eleventh International Conference on Learning Representations, 2022
292022
A 2-dimensional state space layer for spatial inductive bias
E Baron, I Zimerman, L Wolf
The Twelfth International Conference on Learning Representations, 2023
22*2023
Converting transformers to polynomial form for secure inference over homomorphic encryption
I Zimerman, M Baruch, N Drucker, G Ezov, O Soceanu, L Wolf
Forty-first International Conference on Machine Learning, 2023
192023
Sensitive tuning of large scale CNNs for E2E secure prediction using homomorphic encryption
M Baruch, N Drucker, G Ezov, E Kushnir, J Lerner, O Soceanu, ...
International Symposium on Cyber Security, Cryptology, and Machine Learning, 2023
9*2023
Focus your attention (with adaptive iir filters)
S Lutati, I Zimerman, L Wolf
The 2023 Conference on Empirical Methods in Natural Language Processing, 2023
72023
DeciMamba: Exploring the Length Extrapolation Potential of Mamba
A Ben-Kish, I Zimerman, S Abu-Hussein, N Cohen, A Globerson, L Wolf, ...
The Thirteenth International Conference on Learning Representations, 2024
52024
A Unified Implicit Attention Formulation for Gated-Linear Recurrent Sequence Models
I Zimerman, A Ali, L Wolf
The Thirteenth International Conference on Learning Representations, 2024
52024
Viewing Transformers Through the Lens of Long Convolutions Layers
I Zimerman, L Wolf
Forty-first International Conference on Machine Learning, 2024
5*2024
Power-Softmax: Towards Secure LLM Inference over Encrypted Data
I Zimerman, A Adir, E Aharoni, M Avitan, M Baruch, N Drucker, J Lerner, ...
arXiv preprint arXiv:2410.09457, 2024
42024
Multi-dimensional hyena for spatial inductive bias
I Zimerman, L Wolf
International Conference on Artificial Intelligence and Statistics, 973-981, 2024
42024
Decision s4: Efficient sequence-based rl via state spaces layers
S Bar-David, I Zimerman, E Nachmani, L Wolf
The Eleventh International Conference on Learning Representations, 2023
42023
Algorithms for reconstructing DDoS attack graphs using probabilistic packet marking
D Barak-Pelleg, D Berend, TJ Robinson, I Zimmerman
arXiv preprint arXiv:2304.05123, 2023
42023
Recovering AES keys with a deep cold boot attack
I Zimerman, E Nachmani, L Wolf
International Conference on Machine Learning, 12955-12966, 2021
32021
Efficient skip connections realization for secure inference on encrypted data
N Drucker, I Zimerman
International Symposium on Cyber Security, Cryptology, and Machine Learning …, 2023
12023
On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach
E Cohen-Karlik, I Zimerman, L Galanti, I Atad, A Globerson, L Wolf
arXiv preprint arXiv:2502.02209, 2025
2025
Polynomial Approximation of Deep Learning Models
I Zimerman, J Lerner, M Baruch, N Drucker
US Patent App. 18/137,175, 2024
2024
Accelerating privacy-preserving neural networks and an efficient skip-connection realization thereof
I Zimerman, N Drucker, M Baruch, O Soceanu
US Patent App. 18/127,700, 2024
2024
Training neural networks with non-polynomial elements for homomorphic encryption computations using sub-networks and multi-loss
I Zimerman, N Drucker
US Patent App. 18/182,746, 2024
2024
Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
I Zimerman, A Ali, L Wolf
arXiv preprint arXiv:2405.16504, 2024
2024
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20