About Me

Hello, I am Chuangji Li (李创基), an undergraduate student in Statistics and Machine Learning at Carnegie Mellon University in Pittsburg. I am currently working with Eason Chen in LearnLab.

My research interests lie at machine learning and natural language processing. In particular, I am interested in improving generative models' reasoning and problem solving ability. My goal is to build the AGI. I am susceptible about the ability of large language model and working to different architecture to excel its limits. My most recent attempt was to improve model's ability to generate code, which is a crucial measure of model's reasoning ability.

Currently, I am working on math-solving models on university-level math which helps student's process of learning.

Contact Info

Skills

  • Math: Multivariate Calculus, Linear Algebra, Probability and Statistics Theory, Real Analysis, Measure Theory
  • Programming Languag: C, C++, Python*, Java, Rust, R, HTML5, CSS, Javascript, MySQL.
  • Cloud Service: AWS, Docker
  • AI Frameworks: PyTorch, Sklearn, Pandas, Numpy, Matplotlib
  • Machine Learning: Linear/Logistic Regression, MLE/MAP, Dimensionality Reduction, Recommender Systems, Non-parametric Regression, Learning Theory, Ensemble, SVM, Gaussian Processes
  • Deep Learning Architectures: CNN, RNN, Transformer, GAN, VAE, Stable Diffusion, YOLO,

Ongoing Projects

  • Math-solver
  • Probabilistic Graphical Models
  • Deep Learning System

Past Projects

  1. Handwritten English Recognition System
  2. End-to-End Retrieval Augmented Generation Question-Answering System
  3. Dexcom Jira Ticket Clustering System
  4. Sui-GPT

More about Me

My most recent hobbies include:

  • Badminton
  • Billiard
  • Gym

Music

I also LOVE music. Despite I have not played for a long time, I still listen everyday. Below is a non-exhaustive list of music I like.

  • Music Genre: Citypop, Jazz, Bossa Nova, Classical, Pop, Synthewave, R & B, Indie, ...
  • Musicians: Eason Chan (陈奕迅), Jay Chou (周杰伦), Ringo Sheena (椎名林檎), Hacken Lee (李克勤), David Tao (陶喆), Anri (杏里), Mariya Takeuchi (竹内玛莉亚), Yamashita Tatsuro (山下达郎), Queens, C418, Laufey, Joe Hisaishi (久石让), ...

Courses

This page records the courses that are relavent. The links are for reference only.

  • 10-315 Introduction to Machine Learning (SCS majors) by Pat Virtue
  • 36-401 Modern Regression by Alex Reinhart
  • 36-402 Advanced Data Analysis by Cosma Shalizi
  • 16-385 Computer Vision by Matthew P. O'Toole
  • 10-423 Generative AI by Mattrew Gormley
  • 10-701 Introduction to Machine Learning (Ph.D) by Henry Chai
  • 11-711 Advanced Natural Language Processing by Graham Neubig
  • 36-700 Probability and Mathematical Statistics by Anne Lee
  • 10-708 Probablistic Graphical Models by Tianqi Chen & Zico Kolter
  • 10-714 Deep Learning Systems: Algorithms and Implementation Albert Gu & Andrej Risteski

Courses that I am planing to take

  • 10-703 Deep Reinforcement Learning
  • 11-777 Multimodal Machine Learning
  • 15-319 Cloud Computing

Projects

This section holds all my projects

Ongoing Projects

  1. Math-solver
  2. Probabilistic Graphical Models
  3. Deep Learning System

Past Projects

  1. Handwritten English Recognition System
  2. End-to-End Retrieval Augmented Generation Question-Answering System
  3. Dexcom Jira Ticket Clustering System
  4. Sui-GPT
  5. Math-solver

Handwritten English Recognition System

End-to-End Retrieval Augmented Generation Question-Answering System

Dexcom Jira Ticket Clustering System

Sui-GPT

Math

Calculus

Multi-variate Calculus

Linear Algebra

Real Analysis

Measure Theory

Probability and Statistics

  • Probability
  • Statistical Inference
    • Point Estimation
    • Hypothesis Test
    • Confidence Interval
    • Bayesian Inference
  • Statistical Models and Methods
    • Regression and Its Generalizations
      • Regression Basics
      • Diagnostics
      • Model and Variable Evaluation
      • Smoothing
      • Simulation and Bootstrap
      • Nonparametric Regression
      • Splines
      • Generalized Linear Models
    • Latent Structures and Models
      • Mixture Models
      • Factor Models
    • Causal Inference
      • Directed Graphs
      • Undirected Graphs
      • Casual Effects
    • Simulation Methods
      • Monte Carlo
      • Markov Chain Monte Carlo
      • Stochastic Calculus
    • Time Series Analysis

Machine Learning

KNNs & Model Selection

Regressions

MLE and Regularization

Naive Bayes and Discriminant Analysis

Recommender System

Unsupervised Learning: Clustering

Unsupervised Learning: Dimensionality Reduction

Ensemble Methods

SVMs

Kernels

Learning Theory

Gaussian Process

Adaptive Basis Function Models


Probabilistic Graphical Models

Deep Learning

Neural Network

Optimization Algorithms

Convolutional Neural Network

Recurrent Neural Network

Attention and Transformer

Generative Adversarial Networks

Variational Autoencoders

Diffusion

CLIP / ViT

Neural Radiance Fields