Hello!I am Gabriel Mongaras Student Researcher

Student at SMU. I’m quadruple majoring in C.S. with a specialization in AI, Statistical Science, Data Science, and Math. I graduate in May, 2025. I plan on getting an MS in Computer Science after graduating while working. I am currently looking for my first full-time permanent job out of school starting in June, 2025

Scroll for more down
I am Gabriel Mongaras

My Skillset

C++ C CUDA Python Django Flask JavaScript Java PL/SQL Arduino ARM Assembly Android SDK HTML CSS
Neural Networks PyTorch JAX Huggingface Diffusion Models Attention... it's all you need Transformers CNNs GANs NEAT PPO scikit-learn NumPy YOLO Object Detection TensorFlow
Smart Contracts Solidity Remix IDE
AWS Linux Windows MacOS
down

My Projects

I am a Computer Science student currently working as an undergraduate researcher to help pay his way through college. I am particularly interested in the field of AI. Here are some of the projects which I have done.

My Github My Github
https://gabrielm.cc/wp-content/uploads/2021/09/gabriel.jpg
Stable Diffusion 3 From Scratch

Stable Diffusion 3 From Scratch

Cottention: Linear Transformers With Cosine Attention

Cottention: Linear Transformers With Cosine Attention

GRPO DAPO Tests

GRPO DAPO Tests

Latent Diffusion Model Imagenet 2012

Latent Diffusion Model Imagenet 2012

Diffusion Models From Scratch

Diffusion Models From Scratch

AI Girlfriend

AI Girlfriend

Token Merging Tests

Token Merging Tests

Rust Neural Network

Rust Neural Network

Causal Transformer Base

Causal Transformer Base

Matrix Gradient Calculator

Matrix Gradient Calculator

CudaKernelDemo

CudaKernelDemo

Reinforcement Learning Stuff

Reinforcement Learning Stuff

YOLOX From Scratch

YOLOX From Scratch

GAN TextGen

GAN TextGen

Resume Parser

Resume Parser

MetaU Capstone

MetaU Capstone

Transformers From Scratch

Transformers From Scratch

Vision Transformers From Scratch

Vision Transformers From Scratch

Dino Game AI V2

Dino Game AI V2

Gradient Descent For BCE Loss

Gradient Descent For BCE Loss

Cart Pole PPO

Cart Pole PPO

Anime StyleGAN

Anime StyleGAN

Dorahack Apr 2021 Project

Dorahack Apr 2021 Project

Data Structures Search Engine Project

Data Structures Search Engine Project

Career

Get Resume resume.pdf

Google

Student Researcher

EXPERIENCE
October 2024 - December 2024

Google

Summer Intern

EXPERIENCE
May 2024 – August 2024

Amazon

Summer Intern

EXPERIENCE
May 2023 – August 2023

Meta

Summer Intern

EXPERIENCE
May 2022 – August 2022

SMU

Student Technology Assistant in Residence Researcher

EXPERIENCE
August 2022 – Current

SMU

Undergraduate Research Assistant

EXPERIENCE
August 2021 – Current

SMU

Student Tutor

EXPERIENCE
August 2021 – January 2022

Freelancer

Freelance Programmer

EXPERIENCE
May, 2020 – August 2021

DoraHacks Hackathon

Smart Contract Developer

EXPERIENCE
May 2021

Brushy Creek MUD

Lifeguard

EXPERIENCE
Apr 2019 - Aug 2019

CTYLA

Lacrosse Referee

EXPERIENCE
Jan 2018 - Mar 2019

Education

2021 - 2025
Southern Methodist University

Master of Science

MS in Computer Science - Specialization in AI and ML; BS in Computer Science - AI Specialization; BS in Statistical Science; BS in Data Science; BA Mathematics

Education
2018 - 2021
Austin Community College

Associate of Applied Science in Computer Information Technology - Computer Programming

Took dual credit classes while at Gateway College Prep. I graduated with an Associate's degree in Computer Programming in the same semester that I graduated high school.

Education
2012 - 2021
Gateway College Preparatory School

High School Distinguished Level of Achievement Diploma

Valedictorian Endorsements: STEM, Arts and Humanities, Multi Disciplinary Studies

Education

Papers

https://gabrielm.cc/wp-content/uploads/2025/01/gradient.png

Cottention: Linear Transformers With Cosine Attention

Papers

Certifications

Udacity

AI Programming With Python
Issued May 2023
Certificate

NVIDIA DLI

Accelerating Data Engineering Pipelines
Issued Oct 2022
Certificate

NVIDIA DLI

Fundamentals of Deep Learning for Multi-GPUs
Issued Oct 2022
Certificate

Coursera

Generative Adversarial Networks Specialization
Issued Aug 2021
Certificate

Coursera

Google Project Management: Specialization
Issued Aug 2021
Certificate

Coursera

Deep Learning Specialization
Issued Jul 2021
Certificate

Coursera

Google Data Analytics Specialization
Issued Jun 2021
Certificate

Coursera

Google IT Automation with Python Specialization
Issued Jun 2021
Certificate

NSHSS

Intern Readiness Program Certificate
Issued Jun 2021
Certificate

University at Buffalo

Blockchain Basics
Issued May 2021
Certificate

Yale University

The Science of Well-Being
Issued Apr 2021
Certificate

edX

edX Verified Certificate for CS50's Introduction to Artificial Intelligence with Python
Issued Mar 2021
Certificate

Phi Theta Kappa Honor Society International

Five Star Competitive Edge
Issued Oct 2020
Certificate

edX

edX Verified Certificate for CS50's Introduction to Computer Science
Issued Jul 2020
Certificate

Illinois Institute of Technology

Game Design: Interactive Storytelling
Issued May 2020
Certificate

Harvard University

CS50 AI - Introduction to Artificial Intelligence with Python
Issued Aug 2021
Certificate

Classes

STAT 4363

Applied Time Series Analysis
SMU
Classes

STAT 3341

Sports Analytics
SMU
Classes

MATH 3311

Intro. to Proof and Analysis
SMU
Classes

CS 8321

Mach Lrng & Neural Ntwrks
SMU (Graduate)
Classes

CS 7350

Algorithm Engineering
SMU (Graduate)
Classes

CS 5393

Undergraduate Research
SMU
Classes

STAT 6311

Intro to Math Stat I
SMU (Graduate)
Classes

STAT 6307

Intro. to Stat. Computing
SMU (Graduate)
Classes

STAT 6301

Experimental Statistics I
SMU (Graduate)
Classes

MATH 4325

Dynamical Systems
SMU
Classes

CS 5393

Advanced C++
SMU
Classes

CS 5393

Machine Learning
SMU
Classes

UHP 3100

Honors Junior Seminar
SMU
Classes

STAT 3366

Regression & Visualization
SMU
Classes

PHIL 1319

Technology, Society, and Value
SMU
Classes

MATH 4339

Complex Variables
SMU
Classes

CS 7324

Machine Learning in Python
SMU (Graduate)
Classes

CS 5393

Undergraduate Research (Cottention)
SMU
Classes

CS 5344

Computer Ntwks & Distr Systems
SMU
Classes

ARHS 3305

Art of American Southwest
SMU
Classes

PRW 2135

PRW2: Mountain Sports
SMU
Classes

MATH 4377

Math of Machine Learning
SMU
Classes

MATH 4334

Mathematical Modeling
SMU
Classes

GEOL 1313

Earthquakes and Volcanoes
SMU
Classes

CS 5351

Senior Design
SMU
Classes

CS 5328

Software Engineering
SMU
Classes

CS 3341

Foundations Modern Computing
SMU
Classes

CS 7320

Artificial Intelligence
SMU (Graduate)
Classes

CS 7343

Operating System and System Software
SMU (Graduate)
Classes

EPL 3302

Comparative Leadership
SMU
Classes

MATH 3313

Differential Equations
SMU
Classes

STAT 3304

Intro. to Stat. Computing
SMU
Classes

SOCI 2300

Social Problems
SMU
Classes

CS 4381

Digital Computer Design
SMU
Classes

UHP 2100

Honors Sophomore Seminar
SMU
Classes

CS 3381

Digital Logic Design
SMU
Classes

UHP 2367

Greater Dallas Experience
SMU
Classes

MATH 3304

Linear Algebra
SMU
Classes

HIST 3368

Digital History
SMU
Classes

CS 5394

Applied Machine Learning
SMU
Classes

STAT 3300

Applied Statistics
SMU
Classes

AGAN

Apply Generative Adversarial Networks (GANs)
Coursera
Classes

CS 2240

Assembly Language Programming And Machine Organization
SMU
Classes

ARWTR

Automating Real-World Tasks with Python
Coursera
Classes

BBGAN2

Build Better Generative Adversarial Networks (GANs)
Coursera
Classes

BBGAN1

Build a Basic General Adversarial Network (GAN)
Coursera
Classes

CS50x

CS50's Introduction to Computer Science
Harvard
Classes

MATH 1338

Calculus 2
SMU
Classes

MATH 3302

Calculus 3
SMU
Classes

CMC

Configuration Management and the Cloud
Coursera
Classes

CNN

Convolutional Neural Networks
Coursera
Classes

DARP

Data Analysis with R Programming
Coursera
Classes

CS 2341

Data Structures
SMU
Classes

COSC 2436

Data Structures
ACC
Classes

ITSE 2309

Database Programming
ACC
Classes

CS 2353

Discrete Computational Structures
SMU
Classes

CS 3353

Fundamentals Of Algorithms
SMU
Classes

ITNW 1325

Fundamentals of Networking
SMU
Classes

WRTR 2304

Hilltop Scholars Program Critical Reasoning
SMU
Classes

WRTR 2303

Hilltop Scholars Program Academic Writing
SMU
Classes

IDRR

Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
Coursera
Classes

ITSE 1345

Intro to Oracle and PL/SQL
ACC
Classes

ITSE 1359

Intro To Python
ACC
Classes

ITSE 1303

Intro to MySQL
ACC
Classes

ENGR 1357

Introduction To Engineering Design
SMU
Classes

SPAN 1402

Spanish 2
SMU
Classes

SPAN 1401

Spanish 1
SMU
Classes

CS50AI

Introduction to Artificial Intelligence with Python
Harvard
Classes

EPL 3102

Leadership in Action
SMU
Classes

NNDL

Neural Networks and Deep Learning
Coursera
Classes

ITSC 1325

PC Hardware
ACC
Classes

PDDC

Process Data from Dirty to Clean
Coursera
Classes

EPL 3101

Rediscovering Leadership
SMU
Classes

PRW 3303

Self, Identity, and Community Engagement
SMU
Classes

SM

Sequence Models
Coursera
Classes

SDAV

Share Data Through the Art of Visualization
Coursera
Classes

MATH 1342

Statistics
ACC
Classes

STAT 4340

Statistics For Engineers
SMU
Classes

SMLP

Structuring Machine Learning Projects
Coursera
Classes

ENGL 2311

Technical Writing
ACC
Classes

TDT

Troubleshooting and Debugging Techniques
Coursera
Classes

ITSC 1307

UNIX Operating System
ACC
Classes

UPIOP

Using Python to Interact with the Operating System
Coursera
Classes

Articles

https://gabrielm.cc/wp-content/uploads/2023/03/Studio_Project-2-1.gif

Diffusion Models — DDPMs, DDIMs, and Classifier Free Guidance

Articles
https://gabrielm.cc/wp-content/uploads/2023/02/0_hRdo8H8ycSnDuyF-.gif

Coding a Virtual AI Girlfriend

Articles
https://gabrielm.cc/wp-content/uploads/2022/10/1_cN_YLD_CNPam6oWPje2juw.png

How Do Self-Attention Masks Work?

Articles
https://gabrielm.cc/wp-content/uploads/2022/10/Screenshot-2022-10-10-155307.png

Integrating Custom PyTorch Models Into an Android App

Articles
https://gabrielm.cc/wp-content/uploads/2022/05/1_NZJ4atofWqxC8OaEjQWfZQ.png

YOLOX Explanation — What is YOLO and What Makes It Special?

Articles
https://gabrielm.cc/wp-content/uploads/2022/05/tmp.png

YOLOX Explanation — How Does YOLOX Work?

Articles
https://gabrielm.cc/wp-content/uploads/2022/05/tmp-1.png

YOLOX Explanation — SimOTA For Dynamic Label Assignment

Articles
https://gabrielm.cc/wp-content/uploads/2022/05/tmp-2.png

YOLOX Explanation — Mosaic and Mixup For Data Augmentation

Articles
https://gabrielm.cc/wp-content/uploads/2022/01/how-do-neural-networks-work.png

How Do Neural Networks Work?

Articles
https://gabrielm.cc/wp-content/uploads/2022/02/Multi-Layer-Backprop-Example.png

Coding A Neural Network From Scratch Using Python

Articles
https://gabrielm.cc/wp-content/uploads/2022/04/0_tij3m2V1nKziOhmC.png

Community Detection With Neural Networks

Articles

VIDEOS

RWKV-7 "Goose" with Expressive Dynamic State Evolution

RWKV-7 "Goose" with Expressive Dynamic State Evolution

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

https://www.youtube.com/watch?v=8nZbTvES11Y

https://www.youtube.com/watch?v=8nZbTvES11Y

DeepSeek-V3

DeepSeek-V3

Titans: Learning to Memorize at Test Time

Titans: Learning to Memorize at Test Time

MiniMax-01: Scaling Foundation Models with Lightning Attention

MiniMax-01: Scaling Foundation Models with Lightning Attention

Memory Layers at Scale

Memory Layers at Scale

Byte Latent Transformer: Patches Scale Better Than Tokens

Byte Latent Transformer: Patches Scale Better Than Tokens

Scaling up Masked Diffusion Models on Text

Scaling up Masked Diffusion Models on Text

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Round and Round We Go! What makes Rotary Positional Encodings useful?

Round and Round We Go! What makes Rotary Positional Encodings useful?

Deterministic Image Editing with DDPM Inversion, DDIM Inversion, Null Inversion and Prompt-to-Prompt

Deterministic Image Editing with DDPM Inversion, DDIM Inversion, Null Inversion and Prompt-to-Prompt

Attending to Topological Spaces: The Cellular Transformer

Attending to Topological Spaces: The Cellular Transformer

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Learning to (Learn at Test Time): RNNs with Expressive Hidden States

WARP: On the Benefits of Weight Averaged Rewarded Policies

WARP: On the Benefits of Weight Averaged Rewarded Policies

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Mamba 2 - Transformers are SSMs: Generalized Models and Efficient Algorithms Through SSS Duality

Mamba 2 - Transformers are SSMs: Generalized Models and Efficient Algorithms Through SSS Duality

CoPE - Contextual Position Encoding: Learning to Count What's Important

CoPE - Contextual Position Encoding: Learning to Count What's Important

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

xLSTM: Extended Long Short-Term Memory

xLSTM: Extended Long Short-Term Memory

KAN: Kolmogorov-Arnold Networks

KAN: Kolmogorov-Arnold Networks

LADD: Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

LADD: Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

Visual AutoRegressive Modeling:Scalable Image Generation via Next-Scale Prediction

Visual AutoRegressive Modeling:Scalable Image Generation via Next-Scale Prediction

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Q* AGI Achieved (Apr Fools)

Q* AGI Achieved (Apr Fools)

Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits and BitNet

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits and BitNet

DoRA: Weight-Decomposed Low-Rank Adaptation

DoRA: Weight-Decomposed Low-Rank Adaptation

OpenAI Sora and DiTs: Scalable Diffusion Models with Transformers

OpenAI Sora and DiTs: Scalable Diffusion Models with Transformers

A Decoder-only Foundation Model For Time-series Forecasting

A Decoder-only Foundation Model For Time-series Forecasting

Lumiere: A Space-Time Diffusion Model for Video Generation

Lumiere: A Space-Time Diffusion Model for Video Generation

Exphormer: Sparse Transformers for Graphs

Exphormer: Sparse Transformers for Graphs

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Boundary Attention: Learning to Find Faint Boundaries at Any Resolution

Boundary Attention: Learning to Find Faint Boundaries at Any Resolution

Cached Transformers: Improving Transformers with Differentiable Memory Cache

Cached Transformers: Improving Transformers with Differentiable Memory Cache

Translatotron 3: Speech to Speech Translation with Monolingual Data

Translatotron 3: Speech to Speech Translation with Monolingual Data

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Adversarial Diffusion Distillation

Adversarial Diffusion Distillation

Unsupervised Discovery of Semantic Latent Directions in Diffusion Models

Unsupervised Discovery of Semantic Latent Directions in Diffusion Models

DALL-E 3 - Improving Image Generation with Better Captions

DALL-E 3 - Improving Image Generation with Better Captions

LRM: Large Reconstruction Model for Single Image to 3D

LRM: Large Reconstruction Model for Single Image to 3D

CodeFusion: A Pre-trained Diffusion Model for Code Generation

CodeFusion: A Pre-trained Diffusion Model for Code Generation

Matryoshka Diffusion Models Explained

Matryoshka Diffusion Models Explained

UniAudio: An Audio Foundation Model Toward Universal Audio Generation

UniAudio: An Audio Foundation Model Toward Universal Audio Generation

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

StreamingLLM - Efficient Streaming Language Models with Attention Sinks Explained

StreamingLLM - Efficient Streaming Language Models with Attention Sinks Explained

FreeU: Free Lunch in Diffusion U-Net Explained

FreeU: Free Lunch in Diffusion U-Net Explained

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation Explained

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation Explained

Llama/Wizard LM Finetuning with Huggingface on RunPod

Llama/Wizard LM Finetuning with Huggingface on RunPod

2x Faster Language Model Pre-training via Masked Structural Growth

2x Faster Language Model Pre-training via Masked Structural Growth

Bayesian Flow Networks (BFN) Explained

Bayesian Flow Networks (BFN) Explained

WizardLM: Empowering Large Language Models to Follow Complex Instructions Explained

WizardLM: Empowering Large Language Models to Follow Complex Instructions Explained

From Sparse to Soft Mixtures of Experts Explained

From Sparse to Soft Mixtures of Experts Explained

BK-SDM: Architecturally Compressed Stable Diffusion for Efficient T2I Generation Explained

BK-SDM: Architecturally Compressed Stable Diffusion for Efficient T2I Generation Explained

Direct Preference Optimization (DPO): Your Language Model is Secretly a Reward Model Explained

Direct Preference Optimization (DPO): Your Language Model is Secretly a Reward Model Explained

Universal and Transferable Adversarial Attacks on Aligned Language Models Explained

Universal and Transferable Adversarial Attacks on Aligned Language Models Explained

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis Explained

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis Explained

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations Explained

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations Explained

ReLoRA: Stack More Layers Differently: High-Rank Training Through Low-Rank Updates Explained

ReLoRA: Stack More Layers Differently: High-Rank Training Through Low-Rank Updates Explained

MiniLLM: Knowledge Distillation of Large Language Models

MiniLLM: Knowledge Distillation of Large Language Models

RetNet: A Successor to Transformer for Large Language Models Explained

RetNet: A Successor to Transformer for Large Language Models Explained

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Explained

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Explained

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for LLMs Explained

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for LLMs Explained

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale Explained

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale Explained

LongNet: Scaling Transformers to 1,000,000,000 Tokens Explained

LongNet: Scaling Transformers to 1,000,000,000 Tokens Explained

Extending Context Window of Large Language Models via Positional Interpolation Explained

Extending Context Window of Large Language Models via Positional Interpolation Explained

RoFormer: Enhanced Transformer with Rotary Position Embedding Explained

RoFormer: Enhanced Transformer with Rotary Position Embedding Explained

RoboCat: A Self-Improving Foundation Agent for Robotic Manipulation Explained

RoboCat: A Self-Improving Foundation Agent for Robotic Manipulation Explained

MusicGen: Simple and Controllable Music Generation Explained

MusicGen: Simple and Controllable Music Generation Explained

Encodec: High Fidelity Neural Audio Compression Explained

Encodec: High Fidelity Neural Audio Compression Explained

QLoRA: Efficient Finetuning of Quantized LLMs Explained

QLoRA: Efficient Finetuning of Quantized LLMs Explained

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold Explained

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold Explained

LoRA: Low-Rank Adaptation of LLMs Explained

LoRA: Low-Rank Adaptation of LLMs Explained

Align your Latents - High-Resolution Video Synthesis Explanation

Align your Latents - High-Resolution Video Synthesis Explanation

Attention Is All You Need Explanation

Attention Is All You Need Explanation

ViT: An Image is Worth 16x16 Words Explained

ViT: An Image is Worth 16x16 Words Explained

Organizations

Hunt Leadership Scholars Program
Member
Hunt Leadership Scholars Program
Hilltop Scholars
Member
Hilltop Scholars Program
Rotunda Scholars
Member
Rotunda Scholars
SMU AI Club
President
SMU AI Club
Math Club
Member
SMU Computer Science Club
Member
Computer Science Club

Contact Me

If you’d like to talk about a project you want help with or need advice about product design, just drop me a message at gabriel@mongaras.com

Linkedin Linkedin Email Email Youtube Youtube X X