Simon Wang

who am I?


Hello! I'm Simon!

I just recently completed my Master's in Computer Science at UMD (May 2025), and I'm so excited to use what I've learned over the past few years to make a real impact!

do I have interests?


Aside from creating AI tools, studying deep learning, and developing webpages (like this one), in my free time I love to...

pursuing research interests in:

Generative AI

I'm a Computer Science Master's Student at the University of Maryland (UMD). I love applying what I study to create impactful tools that show the amazing potential of technology to engage and assist everyone! Check out the links below and look through this site to find out more. Thanks :)

My Skills

Programming languages, AI/ML tools, and software I've picked up over the years!

Python Java HTML Javascript (Vanilla/React/Node) C# (Unity) C/C++ SQL Autogen PyTorch Ollama Huggingface Transformers/Datasets OpenAI API LangChain FER OpenCV Gradio Tensorflow GitHub Vercel VSCode MS Office Unity Fusion 360 Arduino Docker

Project Highlights

Check out some of my project highlights! See my Projects page and my GitHub for complete details and code.


Understanding Agentic AI Systems for Data Analysis: Techniques, Components, and Considerations

agentic-AI llms data-analysis research

May, 2025

AI generated using gpt-4o

A survey paper exploring state of the art agentic AI systems for data analysis. In this work I also provide an overview of the most common LLM-based approaches to general workflows, and also propose a component framework for understanding agentic AI systems inspired by the The Project Management Lifecycle.

MMO - Multi-modal Multi-agent Organization & Robust Benchmarking

llms mllms benchmarking Python

December 18, 2024

AI generated using DALL-E

Course research project for CMSC848K - Multimodal Foundation Models. Developed a multi-modal multi-agent system and investigated how to improve multimodal large language model (MLLM) benchmarking.


Monte Carlo Rendering and Disney BRDF in PyTorch

computer-graphics PyTorch monte-carlo path-tracing

December 14, 2024

Two spheres with Disney style shading!

An implementation of Monte Carlo path tracing and Disney "principled" BRDF in PyTorch. An extension of an assignment codebase from CMSC740 - Advanced Graphics course. Implemented advanced computer graphics concepts such as Monte Carlo integration, neural radiosity, and multiple importance sampling. As a final project, I also implemented the Disney shading system in the existing renderer with fine-grained control of object appearance using 10 parameters.

Personalized RAG Quiz System using OpenAI Structured Outputs

llms structured-outputs retrieval-augmented-generation web-scraping

May, 2024

AI generated using DALL-E

A demonstration of using retrieval augmented generation and structured outputs through OpenAI API. Exploring how AI can be used to help us learn, automatically creating and testing us on custom uploaded knowledge from documents and webpages.


Improving Control and Consistency of Diffusion-Generated Video

deep-learning stable-diffusion controlnet video-gen

May 2, 2024

jeep
Selected frames from a video I generated

Semester-long course project created for CMSC720: Foundations of Deep Learning. Investigated state of the art diffusion-based video generation methods, and experimented with various approaches to improving their quality in terms of consistency and controllability. Wrote and submitted a NEURIPS format paper for a mock-conference within our class.

Virtual Classroom

AR/VR Unity c# education user-study

May 17, 2024

vector
A scene from our VR vector math lecture

This is a virtual reality (VR) project created in the Unity game engine throughout the Spring 2024 semester for the course CMSC838C: Advances in XR. I led a group of 5 classmates to design a virtual classroom environment, and we conducted a user study to investigate the benefits of XR education over traditional remote learning mediums such as video.