I am Idan, a researcher at Sony Israel. My position is academically inclined, aiming at producing research papers in machine learning. I am always looking for collaborations, so if you want to work together please don’t hesitate to reach out.
I hold a Ph.D. from Bar-Ilan University where I was supervised by Prof. Gal Chechik (CS department and NVIDIA), and Dr. Ethan Fetaya (EE department).
I am interested in both theoretical and practical aspects of machine and deep learning across various domains, e.g., images, texts, speech, and exact sciences. In general, I find the probabilistic modeling approach most compelling. Most recently I have been working on probabilistic generative models and Bayesian deep learning.
I hold a MSc degree in Computer Science and a BSc degree in Engineering, both with honors. Before my MSc degree, I worked for several years as a Data Scientist at RSA.
My CV can be found here

Publications

Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
Idan Achituve, Hai Victor Habi, Amir Rosenfeld, Arnon Netzer, Idit Diamant, Ethan Fetaya
International Conference on Machine Learning (ICML), 2025.
paper | code

Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
Neta Glazer, David Chernin, Idan Achituve, Sharon Gannot, Ethan Fetaya
Interspeech, 2025.

Efficient Image Restoration via Latent Consistency Flow Matching
Elad Cohen, Idan Achituve, Idit Diamant, Arnon Netzer, Hai Victor Habi
Arxiv, 2025.
paper

Electromyographic typing gesture classification dataset for neurotechnological human-machine interfaces
Jonathan Eby, Moshe Beutel, David Koivisto, Idan Achituve, Ethan Fetaya, José Zariffa
Scientific Data, 2025.
paper

De-Confusing Pseudo-Labels in Source-Free Domain Adaptation
Idit Diamant, Amir Rosenfeld, Idan Achituve, Jacob Goldberger, Arnon Netzer
European Conference on Computer Vision (ECCV), 2024.
paper | code

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
Idan Achituve, Idit Diamant, Arnon Netzer, Gal Chechik, Ethan Fetaya
International Conference on Machine Learning (ICML), 2024.
paper | code

Lay-A-Scene: Personalized 3D object arrangement using text-to-image priors
Ohad Rahamim, Hilit Segev, Idan Achituve, Yuval Atzmon, Yoni Kasten, Gal Chechik
Arxiv, 2024.
paper | code

Data Augmentations in Deep Weight Spaces
Aviv Shamsian, David W Zhang, Aviv Navon, Yan Zhang, Miltiadis Kofinas, Idan Achituve, Riccardo Valperga, Gertjan J Burghouts, Efstratios Gavves, Cees GM Snoek, Ethan Fetaya, Gal Chechik, Haggai Maron
NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations, 2023
paper

GD-VDM: Generated Depth for Better Diffusion-Based Video Generation
Ariel Lapid, Idan Achituve, Lior Bracha, Ethan Fetaya Arxiv, 2023.
paper

Guided Deep Kernel Learning
Idan Achituve, Gal Chechik, Ethan Fetaya Uncertainty in Artificial Intelligence (UAI), 2023.
paper | code

Equivariant Architectures for Learning in Deep Weight Spaces (Oral)
Aviv Navon, Aviv Shamsian, Idan Achituve, Ethan Fetaya, Gal Chechik, Haggai Maron
International Conference on Machine Learning (ICML), 2023.
paper | code

Communication Efficient Distributed Learning over Wireless Channels
Idan Achituve, Wenbo Wang, Ethan Fetaya, Amir Leshem
IEEE Signal Processing Letters, 2023.
paper

Functional Ensemble Distillation
Coby Penso, Idan Achituve, Ethan Fetaya
Neural Information Processing Systems (NeurIPS), 2022.
paper | code

Multi-Task Learning as a Bargaining Game
Aviv Navon, Aviv Shamsian, Idan Achituve, Haggai Maron, Kenji Kawaguchi, Gal Chechik, Ethan Fetaya
International Conference on Machine Learning (ICML), 2022.
paper | code

Personalized Federated Learning with Gaussian Processes
Idan Achituve, Aviv Shamsian, Aviv Navon, Gal Chechik, Ethan Fetaya
Neural Information Processing Systems (NeurIPS), 2021.
paper | code | Project Page

GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Idan Achituve, Aviv Navon, Yochai Yemini, Gal Chechik, Ethan Fetaya
International Conference on Machine Learning (ICML), 2021.
paper | code

Auxiliary Learning by Implicit Differentiation
Aviv Navon^, Idan Achituve^ , Haggai Maron, Gal Chechik, Ethan Fetaya
International Conference on Learning Representations (ICLR), 2021.
paper | code | Project Page

Self-Supervised Learning for Domain Adaptation on Point-Clouds
Idan Achituve, Haggai Maron, Gal Chechik
IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.
paper | code

Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism
Idan Achituve, Sarit Kraus and Jacob Goldberger
IEEE Machine Learning for Signal Processing Workshop (MLSP), 2019.
paper