CV

This section includes my curriculum vitae. For a PDF version, see here.

Curriculum Vitae

Borna Khodabandeh

Hi! I am Borna Khodabandeh, I am currently an independent researcher, and a prospective graduate student. I have received my B.Sc. in Electrical Engineering with a minor in Physics from Sharif University of Technology.

I aim to apply rigorous theoretical and mathematical approaches in crucial areas of machine learning, that have practical value. As I am still exploring, I am broadly interested in generative modelling, adversarial robustness and optimization, reinforcement learning, and understanding learning systems through the lens of information theory, statistics and optimization theory.

Research Interests

  • Mathematical foundations of machine learning and optimization
  • Adversarial robustness and strategic behavior in learning systems
  • Information theory and statistical learning, and statistical physics in machine learning
  • Reinforcement learning and online decision-making
  • Generative modelling, epecially vector field generative models (diffusion models, flow models, etc.)

Education

  • Stanford University — Ph.D. in Electrical Engineering (Deferred Admission), Stanford, CA, USA (2026–present)

  • Sharif University of Technology — B.Sc. in Electrical Engineering, Minor in Physics, Tehran, Iran (2021–2025) — Overall GPA: 19.65/20, Major GPA: 19.93/20

  • Young Scholars Club (IPhO Training) — International Physics Olympiad Training

Research Experience

  • Summer Internship, E3 Program (BIG | EPFL), Advised by Prof. Dr. Michael Unser (2024)
    • Designed 1-Lipschitz-constrained (Parseval) convolutional operators and neural networks
    • Applied to inverse problems and denoising with theoretical bounds on stability and robustness
    • Reduced parameters via symmetry
  • Bachelor's Project — Adversarially Robust Embeddings in Contrastive Learning, Advised by Prof. Sajjad Amini (in collaboration with Prof. Moosavi-Dezfooli) (2024)
  • Study Sessions and Reading Groups
    • Causality and bandit algorithms (with BAN at EPFL)
    • Optimization on graphs and learning weights from smooth signals on Erdős–Rényi graphs
    • Designing a chatbot for our universities department with Dr. Arash Amini.
    • Exploring Tsallis-entropy–regularized MDPs for preference optimization in language models
    • Exploring applying preference optimization to consistency models, see Project repository.
    • Coordinated meetings and tracked project progress

Publications

2025 — LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad, Shahabeddin Mousavi, Sanjay Lall, Sajjad Amini, Seyed-Mohsen Moosavi-Dezfooli
NeurIPS 2025
arXiv link
— Conducted as Bachelor’s project. Improves robustness of visual encoders (e.g., CLIP, DinoV2) via constrained optimization while maintaining clean accuracy.
LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
2024 — Aligning Visual Contrastive learning models via Preference Optimization
Amirabbas Afzali, Borna Khodabandeh, Ali Rasekh, Mahyar JafariNodeh, Sepehr Kazemi Ranjbar, Simon Gottschalk
ICLR 2025
arXiv link
— Policy-optimization-based fine-tuning of contrastive models (e.g., CLIP) using human preferences; improves performance and robustness.
Aligning Visual Contrastive learning models via Preference Optimization
2023 — Counter Histogram-Based Forensics using Mean Structural Similarity Index Metric
R. Kazemi, A. Amini, B. Khodabandeh, M. Alikhani
SIAM J. Imaging Sci. (to appear, 2025)
paper link

Selected Course Projects

  • 2025 — Phase transitions in LoRA (High Dimensional Probability (SUT)) — GitHub · Report · Slides:
    Explained LoRA vs full FT via RMT; linked intruder dimensions to BBP transition.

  • 2024 — Information geometry (Information theory, statistics & learning (SUT)) — GitHub · Report · Slides:
    Explored differential geometry in statistical learning; manifolds, divergences, NGD.

  • 2024 — Game theoretic network design (Game theory (SUT)) — GitHub:
    Simulated stable matching and optimal selling mechanisms in network scenarios.

  • 2024 — GAN-BERT (Deep learning (SUT)) — GitHub:
    Implemented GAN-BERT for detecting LLM-generated text and source model.

Teaching

  • Engineering Probability and Statistics — Teaching assistant: Designing projects and problem sets
  • Engineering Mathematics — Teaching assistant: Holding practice sessions
  • Linear Algebra — Teaching assistant: Holding practice sessions
  • Signal Processing — Teaching assistant: Holding practice sessions
  • Deep Learning — Teaching assistant: Designing course project ; practice sessions
  • Machine Learning — Head teaching assistant: Designing problem sets and project ; Holding practice sessions ; Managing the teaching assistant group ; course homepage: https://ml-sut-amini.github.io/

Recordings of my teaching sessions and technical discussions are available here.

Coursework

  • Graduate: Deep Learning, Graph Signal Processing, Game Theory, Information theory, statistics & learning, High Dimensional Probability, Deep Generative Models, Graphical Models
  • Undergraduate: Linear Algebra, Signal Processing, Convex Optimization, Probability and Statistics, Signals and Systems

Activities

  • Participant in the 24th ADFOCS (Max Planck), Algorithmic Game Theory
  • Competitor in international math contests (WMTC 2016, IMC 2018, WMC 2018)
  • Physics Olympiad tutor at top high schools
  • Part of a research group of; organized meetings and tracked project progress

Skills

  • Technical: Advanced mathematics (High dimentional probability and statistics, stochastic calculus, differential equations); Signal processing, information theory, Machine learning and Deep learning
  • Tools: PyTorch, TensorFlow, OpenCV, scikit-learn, NumPy, pandas, matplotlib, DSPy, einops
  • Programming languages: Python, Java, C/C++, Go, MATLAB
  • Languages: Persian (native); English (advanced; TOEFL iBT 113/120 (Reading 30, Listening 29, Speaking 25, Writing 29)); French (basic)
  • Misc: Problem-solving, collaboration, communication, teaching