My Projects

I tried a lot, and I failed a lot too. Here I proudly present my previous projects, no matter whether they were successful or not, for each of them helped me learn and grow.

Generating Uncommon Relations

Left: "boat filled with water"; Right: "vase made of flowers"

Text-to-image diffusion models are not always good at composing objects with relations (inside, filled with, etc.), something humans do easily. This comes from biases they learn from the training data, which only associate such objects with relations common between them. During my internship at Geometric AI Lab in the summer of 2023, I proposed a method that finds relation token embeddings which resolve this problem on top of pretrained diffusion models. The gifs above show some example outputs.

A NeRF trained on my kitty stress ball on Nerfstudio

As part of the internship, I also implemented PointNet, NeRF, and diffusion models in Pytorch.

Robotic Arm System

Left: components of the system; Right: picking task

As part of the coursework in Electronic Design Lab at KAIST in Spring 2023, I designed and implemented a 4-link manipulator robotic system with pick-and-place capability using C++. The system incorporated a BeagleBone Black processor, WiFi communication, a magnetic end effector, and a camera for teleoperation. Through the project, I learned a lot about inverse kinematics, motor control, and embedded systems.

Interpretable Summarisation of Hypergraphs

Decomposition on Math Stack Exchange tag network

This project was for my Undergraduate Research Participation (URP) program at KAIST in Spring 2022. I formulated a new problem in hypergraph data mining and developed an information-theoretic algorithm. My practical contribution includes the implemention and evaluation various strategies for hypergraph clustering as a subroutine of the algorithm on 5 real-world datasets of different domains using SciPy, networkx, and the PyData stack.

< back to homepage