Yehonathan Refael

20 papers A* 1Journal 19
YearRankTypeTitle / Venue / Authors
2026 J jnl
Lorenza: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM.
Trans. Mach. Learn. Res.
Yehonathan Refael, Iftach Arbel, Ofir Lindenbaum, Tom Tirer
2026 J jnl
Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity.
CoRR
Jonathan Svirsky, Yehonathan Refael, Ofir Lindenbaum
2025 J jnl
A Recipe for Improving Remote Sensing VLM Zero Shot Generalization.
CoRR
Aviad Barzilai, Yotam Gigi, Amr Helmy, Vered Silverman, Yehonathan Refael, Bolous Jaber, Tomer Shekel, George Leifman, Genady Beryozkin
2025 A* conf
AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning.
ICLR
Yehonathan Refael, Jonathan Svirsky, Boris Shustin, Wasim Huleihel, Ofir Lindenbaum
2025 J jnl
Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning.
CoRR
Aaron Bell, Amit Aides, Amr Helmy, Arbaaz Muslim, Aviad Barzilai, Aviv Slobodkin, Bolous Jaber, David Schottlander, George Leifman, Joydeep Paul, Mimi Sun, Nadav Sherman, Natalie Williams, Per Bjornsson, Roy Lee, Ruth Alcantara, Thomas Turnbull, Tomer Shekel, Vered Silverman, Yotam Gigi, Adam Boulanger, Alex Ottenwess, Ali Ahmadalipour, Anna Carter, Behzad Vahedi, Charles Elliott, David Andre, Elad Aharoni, Gia Jung, Hassler Thurston, Jacob Bien, Jamie McPike, Juliet Rothenberg, Kartik Hegde, Kel Markert, Kim Philipp Jablonski, Luc Houriez, Monica Bharel, Phing VanLee, Reuven Sayag, Sebastian Pilarski, Shelley Cazares, Shlomi Pasternak, Siduo Jiang, Thomas Colthurst, Yang Chen, Yehonathan Refael, Yochai Blau, Yuval Carny, Yael Maguire, Avinatan Hassidim, James Manyika, Tim Thelin, Genady Beryozkin, Gautam Prasad, Luke Barrington, Yossi Matias, Niv Efron, Shravya Shetty
2025 J jnl
LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM.
CoRR
Yehonathan Refael, Iftach Arbel, Ofir Lindenbaum, Tom Tirer
2025 J jnl
No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks.
CoRR
Yehonathan Refael, Guy Smorodinsky, Ofir Lindenbaum, Itay Safran
2025 J jnl
On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration.
CoRR
Yehonathan Refael, Amit Aides, Aviad Barzilai, George Leifman, Genady Beryozkin, Vered Silverman, Bolous Jaber, Tomer Shekel
2025 J jnl
SLIP-SEC: Formalizing Secure Protocols for Model IP Protection.
CoRR
Racchit Jain, Satya Lokam, Yehonathan Refael, Adam Hakim, Lev Greenberg, Jay Tenenbaum
2025 J jnl
SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training.
CoRR
Yehonathan Refael, Guy Smorodinsky, Tom Tirer, Ofir Lindenbaum
2025 J jnl
Unveiling Multiple Descents in Unsupervised Autoencoders.
Trans. Mach. Learn. Res.
Kobi Rahimi, Yehonathan Refael, Tom Tirer, Ofir Lindenbaum
2024 J jnl
AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning.
CoRR
Yehonathan Refael, Jonathan Svirsky, Boris Shustin, Wasim Huleihel, Ofir Lindenbaum
2024 J jnl
FineGates: LLMs Finetuning with Compression using Stochastic Gates.
CoRR
Jonathan Svirsky, Yehonathan Refael, Ofir Lindenbaum
2024 J jnl
Learning
Trans. Mach. Learn. Res.
Yehonathan Refael, Iftach Arbel, Wasim Huleihel
2024 J jnl
Mathematical Framework for Online Social Media Auditing.
J. Mach. Learn. Res.
Wasim Huleihel, Yehonathan Refael
2024 J jnl
SLIP: Securing LLMs IP Using Weights Decomposition.
CoRR
Yehonathan Refael, Adam Hakim, Lev Greenberg, Tal Aviv, Satya Lokam, Ben Fishman, Shachar Seidman
2024 J jnl
TransformLLM: Adapting Large Language Models via LLM-Transformed Reading Comprehension Text.
CoRR
Iftach Arbel, Yehonathan Refael, Ofir Lindenbaum
2022 J jnl
Learning k-Level Sparse Neural Networks Using a New Generalized Group Sparse Envelope Regularization.
CoRR
Yehonathan Refael, Iftach Arbel, Wasim Huleihel
2022 J jnl
Mathematical Framework for Online Social Media Regulation.
CoRR
Wasim Huleihel, Yehonathan Refael
2022 J jnl
Sparse regularization via bidualization.
J. Glob. Optim.
Amir Beck, Yehonathan Refael