I am a second-year Ph.D. student in Computer Science at Ben-Gurion University, advised by Dr. Omri Azencot. I completed both my B.Sc. (cum laude) and M.Sc. (summa cum laude) in Computer Science at Ben-Gurion University. During my master’s studies, I worked as a Machine Learning Algorithm Engineer at Proteantecs. I also had the opportunity to work at Bosch AI Center in Israel, under the supervision of Dr. Dotan Di Castro. Currently, I am interning as an Applied Researcher at Amazon Prime Video, working under the supervision of Dr. Igor Kviatkovsky, where I focus on developing and integrating multimodal large language models for video-related tasks and long context setups.

Today, my research focuses on exploring the intersection of large multimodal models with generative modeling and representation learning. I work across multiple modalities, including vision, audio, time series, and text, with the goal of developing general, mathematically grounded methods that are applicable across a wide range of domains through both theoretical insight and empirical analysis.

Email | LinkedIn | Google Scholar

Publications and Preprints

Website

Arxiv

github

Preprint 2025
Who Said Neural Networks Aren't Linear?
Nimrod Berman*, Assaf Hallak*, Assaf Shocher*

Website

Arxiv

github

NeurIPS - 2025
One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling
Nimrod Berman*, Ilan Naiman*, Moshe Eliasof, Hedi Zesling, Omri Azencot

Paper

NeurIPS - 2025
Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge
Nimrod Berman*, Omkar Joglekar*, Eitan Kosman, Dotan Di Castro, Omri Azencot

Arxiv

github

NeurIPS - 2025
Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
Tal Gonen*, Itay Pemper*, Ilan Naiman, Nimrod Berman, Omri Azencot

Paper

github

NeurIPS - 2025
Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
Tal Barami*, Nimrod Berman*, Ilan Naiman*, Amos Haviv Hason, Rotem Ezra Omri Azencot

Website

Arxiv

github

NeurIPS - 2025
A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
Gal Fadlon*, Idan Arbiv*, Nimrod Berman, Omri Azencot

Arxiv

github

NeurIPS - 2024
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Ilan Naiman*, Nimrod Berman*, Itai Pemper, Gal Fadlon, Idan Arbiv, Omri Azencot

Arxiv

github

ICML - 2024
Sequential Disentanglement by Extracting Static Information From A Single Sequence Element
Nimrod Berman*, Ilan Naiman*, Gal Fadlon*, Idan Arbiv* Omri Azencot

Arxiv

TMLR - 2024
Generative Modeling of Graphs via Joint Diffusion of Node and Edge Attributes
Nimrod Berman, Eitan Kosman, Dotan Di Castro, Omri Azencot

Arxiv

github

ICML - 2023
Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation
Ilan Naiman*, Nimrod Berman*, Omri Azencot

Arxiv

github

ICLR (Oral) - 2023
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
Nimrod Berman*, llan Naiman*, Omri Azencot

*equal contributors

Articles

towardsdatascience.com

Active Learning for Cell Imagaing

Nimrod Berman*, Noam Siegel*, Adi Nissim*, Assaf Zaritsky

link

Awards

2025 - Dean's honor list (Ben Gurion @ Exact Science faculty)

2025 - high distinction in MSc (Ben Gurion @ CS department)

2024 - Dean's prize - top 1% (Ben Gurion @ Exact Science faculty)

2024 - Dean's honor list (Ben Gurion @ Exact Science faculty)

2023 - Dinitzs Award for excellent papers (Ben Gurion @ CS department)

2023 - Dean's honor list (Ben Gurion @ Exact Science faculty)

2022 - distinction in bachelor (Ben Gurion @ CS department)

2021 - Department Distinction for 3rd year achievements in bachelors (Ben Gurion @ CS department)

Page updated

Google Sites

Report abuse