Evgenii Zheltonozhskii

Technion – Israel Institute of Technology.


Lidow Complex, room 309


Haifa, 3200003

I’m a Physics Ph.D. student in Technion, advised by Netanel Lindner. You can find more details about my experience in resume.

Research interests: I’m interested in condensed matter theory of strongly correlated materials and, in particular, topological phases as well as application of deep learning and self-supervised learning in physics. Currently, I focus on edge modes and interfaces in topological states, e.g., fractional quantum Hall, Kitaev spin liquid, p+ip superconductors. I also have a Telegram channel where I post links to research I find interesting.

Previously: I finished CS M.Sc. in Technion, advised by Alex Bronstein, Avi Mendelson, and Chaim Baskin, and studied reduced supervision in computer vision (in particular, self-supervised and semi-supervised learning). I was a research intern in Creative Vision team in Snap Research in Summer 2020, working on 3D reconstruction trained on single 2D views with Olly Woodford and Sergey Tulyakov. Before that, I was part of Rothschild Technion Program for Excellence and received double B.Sc. (CS and Physics+Math, Cum Laude) from Technion. In 2017, I participated in Google Summer of Code under OpenCV organization.


Jun 10, 2022 The Beyond the Imitation Game Benchmark (BIG-bench) pre-print is finally on arxiv! This is one of the most important recent developments in LLMs, and I’m very happy I contributed to it.
Mar 28, 2022 Our team “Barren plateau inhabitants” with project “Simulation of anyons within the toric code model” based on “Realizing topologically ordered states on a quantum processor” won second place at (out of 46 submitted projects) at QHack 2022 Open Hackathon IBM Qiskit Challenge.
Mar 2, 2022 Our paper “End-to-End Referring Video Object Segmentation with Multimodal Transformers” (MTTR) got accepted to CVPR 2022.
Jan 13, 2022 Our paper “Weakly Supervised Recovery of Semantic Attributes” got accepted to CLeaR 2022.
Oct 4, 2021 Our paper “Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels” (C2D) got accepted to WACV 2022.

selected publications

  1. CVPR’22
    End-to-End Referring Video Object Segmentation with Multimodal Transformers
    Adam Botach,  Evgenii Zheltonozhskii, and Chaim Baskin
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2022
  2. WACV’22
    Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
    Evgenii ZheltonozhskiiChaim BaskinAvi MendelsonAlex M. Bronstein, and Or Litany
    In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Jan 2022
  3. NeurIPS
    Self-Supervised Learning for Large-Scale Unsupervised Image Clustering
    Evgenii ZheltonozhskiiChaim BaskinAlex M. Bronstein, and Avi Mendelson
    NeurIPS Self-Supervised Learning Workshop Aug 2020