Hossein Goli
About Me
Hello! I’m Hossein Goli, a recent Graduate in Computer Engineering at Sharif University of Technology and an Incoming PhD student at the University of Toronto CS department.
I generally relish mathematically inspired fields. Because of my roots in Physics, One of the things i most enjoy is to combine beautiful mathematical concepts coming from physics and the perespectives of a physicist into Computer Science. I enjoy both the theoretical and practical side of Computer Science, as the enjoyment of seeing your algorithm work is like no other.
Honors and Awards
GPA: 19.7/20.0 — Ranked 2nd out of 192 students
Publications
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
STITCH-OPE is a model-based generative framework that leverages denoising diffusion for long-horizon OPE in
high-dimensional state and action spaces via trajectory stitching and combination of positive and negative guided diffusion.
NeurIPS 2025
Spotlight
Soft Super-Pixel Partitioning for Certified Adversarial Robustness
In collaboration with Prof. Farzan Farnia, we propose a new method for the certified robustness problem that leverages the spatial correlation of image pixels using superpixel algorithms such as SLIC. Our method improves image visibility and reduces the effective noise by a factor proportional to the square root of the average superpixel size. The paper is currently available on arXiv and we plan to complete some of our proofs and submit it soon.
arXiv GitHub
Detecting Viral Social Events with Deep Survival Analysis in Complex Networks
In this project we developed a framework for early detection of viral events in complex networks using statistical methods such as survival analysis. To learn a good survival function, we proposed using RNNs on time-series data. We evaluated our work on multiple datasets including Twitter, Weibo, and Digg.
arXiv GitHubCoursework Projects
Computer Vision Course Project
Developed a graph-based image segmentation algorithm using superpixels to group similar pixels by spatial and color features. After constructing the graph, Disjoint Set Union (DSU) iteratively merges vertices until final segmentation. Leveraging SLIC superpixels, a k-means variant, this method enhances robustness without requiring adversarial training. In the second part of the project, we implemented Tiny-NeRF, a simplified version of the famous NeRF paper.
Project Report GitHub
Advanced Programming Project - YuGiOh Game
In this project, we designed the famous trading card game, YuGiOh, from scratch, utilizing various design patterns such as Singleton, Factory, Observer, and more. The programming language used was Java. The project was divided into three phases: implementing the core game logic, developing the graphical user interface, and adding network capabilities to allow peer-to-peer gameplay.
Watch Trailer GitHub
System Analysis Design Project - Kafka from Scratch
In this project, we designed a fully dockerized, distributed message queue system from scratch, similar to Kafka. The project involved building and configuring a fault-tolerant, scalable messaging system using Docker containers, allowing message passing across distributed nodes.
GitHubTeaching Experience and Community Involvement
Teaching Assistant at Sharif University of Technology
- Machine Learning (Graduate), Spring 2024, Prof. Fatemeh SeyedSalehi — Head Teaching Assistant
- Machine Learning (Graduate), Fall 2023, Prof. Abolfazl Motahari — Theoretical Head Teaching Assistant
- Probability and Statistics, Spring 2023, Prof. Ali Sharifi Zarchi — Head of Midterm Exam
- Linear Algebra, Fall 2022, Prof. Hamid R. Rabiee — Recitation Class and Homeworks
- Advanced Programming, Spring 2022, Prof. Amin Fazli — Project Design Team
Physics Olympiad Teacher
Prepared students to participate in the Physics Olympiad, teaching multiple subjects such as Multivariate Calculus, Electromagnetics, and Newtonian Mechanics.
Rasta Summer School - Game Theory Mentor
We organized and led a workshop for high school students, introducing fundamental concepts of game theory in an engaging manner. The workshop was divided into three sections: Market Sharing, Braess’s Paradox, and the Development of Trust. My primary responsibility was the Development of Trust Section.
Scientific Staff of Sharif AI-Challenge
As a scientific staff member, I was involved with the design and implementation of the scientific part of the challenge.
Hobbies
Outside of academia, I enjoy engaging in activities that help me relax and find inspiration for my work. Here are some of my hobbies:
- History Exploring - I enjoy reading history, especially from the Sengoku era (Japan) and the Three Kingdoms (China). I fantasize about different paths that history could have unfolded and write and draw some paintings from those eras
- Gardening and Flowering - I used to enjoy gardening and taking care of flowers. I plan to take up this hobby again in the near future.
Some of my mexican Peppers