sample

Omri Puny

Deep Learning Researcher at NVIDIA


I am a Deep Learning Researcher at NVIDIA. I completed my PhD in Computer Science and Applied Mathematics at the Weizmann Institute of Science in 2026, advised by Prof. Yaron Lipman. My research focuses on geometric deep learning for generative modeling, with an emphasis on symmetry and structured data.

 

 

Publications



Animated crystal-generation trajectory from SGFM.

Space Group Conditional Flow Matching

Omri Puny, Yaron Lipman, Benjamin Kurt Miller

Conference on Neural Information Processing Systems (NeurIPS 2026)

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Akhiad Bercovich*, Mohammad Dabbah*, Omri Puny*, Ido Galil, Amnon Geifman, Yonatan Geifman, Izhak Golan, Ehud Karpas, Itay Levy, Zach Moshe, Najeeb Nabwani, Tomer Ronen, Itamar Schen, Elad Segal, Ido Shahaf, Oren Tropp, Ran Zilberstein, Ran El-Yaniv

Conference on Neural Information Processing Systems (NeurIPS 2025) Spotlight

FFN Fusion Diagram

D-Flow: Differentiating through Flows for Controlled Generation

Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman

International Conference on Machine Learning (ICML 2024)

Mosaic-SDF for 3D Generative Models

Lior Yariv, Omri Puny, Natalia Neverova, Oran Gafni, Yaron Lipman

Conference on Computer Vision and Pattern Recognition (CVPR) 2024

Equivariant Polynomials for Graph Neural Networks

Omri Puny*, Derek Lim*, Bobak T. Kiani*, Haggai Maron, Yaron Lipman (*equal contribution)

International Conference on Machine Learning (ICML 2023) Oral

Frame Averaging for Invariant and Equivariant Network Design

Omri Puny*, Matan Atzmon*, Heli Ben-Hamu*, Edward J. Smith, Ishan Misra, Aditya Grover, Yaron Lipman (*equal contribution)

International Conference on Learning Representations (ICLR 2022) Oral

Global Attention Improves Graph Networks Generalization

Omri Puny, Heli Ben-Hamu, Yaron Lipman

Graph Representation Learning and Beyond Workshop (ICML) 2020