Hi, I'm Shayan Jalalipour

AI/ML Researcher & Developer

I'm an AI/ML researcher based at Portland State University, where I dive into a wide range of problems at the intersection of data, vision, language, and maps. My professional experience includes data science, reinforcement learning, computer vision, multi‑modal & diffusion models, and Geographic Information Systems (GIS). Alongside these, I bring solid software development know‑how: Python, PyTorch, Pandas, SQL, and the full data-to-solution pipeline to build and deploy ML systems.

Currently working on cutting-edge research in artificial intelligence and computer vision, I enjoy tackling complex problems and turning ideas into reality. When I'm not coding or researching, you can find me exploring new technologies or collaborating with fellow researchers.

View My Skills See My Research

5+ Years Experience

3 Research Publications

My Mission

My passion for AI/ML stems from a deep curiosity about how we can leverage technology to solve real-world problems. Every research project I undertake is driven by the potential to make a meaningful impact on people's lives.

Whether it's developing computer vision systems that can assist in medical diagnosis, creating adversarially robust risk-critical AI agents, or building GIS applications that help communities make better decisions, I believe technology should serve humanity.

I get energized by solving interdisciplinary challenges. Projects that sit at the crossroads of AI, vision, language, and more. I'm driven to connect theory with practical impact, whether that's visual scene understanding, generative modeling, or building RL agents for real‑world environments. I thrive when I'm stretching across domains to build something that matters.

The intersection of data, vision, language, represents a frontier where we can create systems that not only understand our world better but also help us navigate and improve it. This is where I want to make my mark.

Innovation

Pushing boundaries in AI research

Impact

Creating solutions that matter

Global Reach

Technology that serves humanity

Let's Collaborate

Ready to Work Together?

I'm always excited to explore new opportunities for collaboration, whether it's research projects, industry partnerships, or academic initiatives. My expertise spans multiple domains, and I love working with teams that share a passion for innovation and impact.

Whether you want to explore new ML methods, build pipelines for spatial or visual data, or just geek out about the possibilities of AI, I'd love to connect. I'm always open to research ideas, collaborations, and curious conversations.

Research Partnerships

Technical Consulting

Academic Collaboration

Startup Projects

Interested in working together? Let's discuss how we can create something amazing.

Get In Touch

Skills & Experience

Programming Languages

Python

JavaScript

SQL

C++

Technologies & Frameworks

React.js

Node.js

TensorFlow

PyTorch

Data Science & ML

Machine Learning

Deep Learning

Data Analysis

Statistical Modeling

Tools & Platforms

Git & GitHub

Docker

AWS & GCP

Jupyter Notebooks

Research Areas

Computer Vision

Adversarial Robustness

Reinforcement Learning

Diffusion Models

Soft Skills

Research & Analysis

Problem Solving

Technical Writing

Team Collaboration

Research Papers

OSA-Diff: An Origin Sampling Based Adversarial Attack Using Diffusion Models

We show that diffusion models can be used to create end-to-end hidden adversarial perturbations with high rate of success, and propose a novel diffusion based adversarial attack that allows for substantially faster training time (through improved convergence on high quality images) and with substantially less computational overhead than typical diffusion model training

2025 19th International Conference on Semantic Computing (ICSC)

Read Paper

Noisy-Defense Variational Auto-Encoder (ND-VAE): An Adversarial Defense Framework to Eliminate Adversarial Attacks

This paper presents a robust adversarial defense mechanism, Noisy-Defense Variational Auto-Encoder (ND-VAE), that combines the strengths of Nouveau VAE (NVAE) and Defense-VAE to effectively eliminate adversarial attacks from contaminated images

2023 Fifth International Conference on Transdisciplinary AI (TransAI)

Read Paper

Deep Learning-Based Spatial Detection of Drainage Structures using Advanced Object Detection Methods

The paper explores multiple advanced deep learning-based object detection models, including Faster RCNN, DINO, DETR:DINO and YOLOv5, to analyze the distinctive patterns exhibited by drainage structures.

2023 Fifth International Conference on Transdisciplinary AI (TransAI)

Read Paper

Get In Touch

Let's Connect

I'm always interested in new opportunities, collaborations, and interesting discussions. Feel free to reach out!

Fill out the form with your info and I will get back to you as soon as possible!

Portland, OR, USA

My LinkedIn Profile

My GitHub Profile

Download My Resume