Hanke Chen
Prev R&D @Midjourney | Ugrad @CMU(CS+Art)_
I am Hanke
Chen
, an undergraduate student at Carnegie Mellon University persuing Computer Science and Art. Currently, I am working on Katzuki. Before this, I was doing research for Midjourney. I was also doing research related to Neural Radiance Field in WiSELab @ CMU advised by Prof. Anthony Rowe and Tianshu Huang.
Previously, in 2014, I founded KokiCraft: a commercial video game played by 300,000+ players. In 2018, I got into Deep Learning and created RedstoneTorch: a large computer vision toolkit for competitive programming and got 1st place in Kaggle's Histopathologic Cancer Detection and wrote my shitty research paper on Computer Vision . 2018 summer, when taking Stanford's cs123, I SQL injected their website & reported. From 2020 to 2022, I worked on Android/IOS app DeepVocab on AppStore: a vocabulary memorization app aided by Deep Learning. From 2021, I joined GCS and published many games: Winter, Empyrean, CryptoEggs, SwingSimulator, ThatTimeIGotReincarnatedAsAFerretAndForcedToClimbForMyFreedom, and Teledot. In 2022, I deployed an experimental social media app 2ch3 on Gnosis blockchain and designed and manufactured a Printed Circuit Board KokiPad that became my personal keyboard. I got into quantum computing theory and coded quantum computer simulator.
I do:
Some selected articles:
- CUDA: All-in-One Tutorial for CUDA Programming
- NeRF: Research about Neural Radiance Field
- Kubernetes: Practical Kubernetes
- CPP: Hacks in C++ Programming
- PCB: Circuit Board Design and Manufacture Tutorial
- Keyboard: Tutorial on Designing Keyboard Hardware and Software
- FPV: Recipe for Assembling and Flying Your Own Drone
- Diffusion: Random Notes about Diffusions
- Blockchain All-in One: All You Need to Know About Blockchain
Research
Artists sell ideas. The best artists are researchers. My interest is too broad for me to write a single one down, but building democratizable human-like AI regardless of the methods is one of them. I do whatever it takes to get things done and NOT STUCK IN ONE FIELD. Some hard problems interests me:
- ML aided fault-tolerance quantum accelerator for simulated annealing;
- 3D-aware intelligence from 2D images w/ NeRF;
- large on-chain swarm learning with proofs;
- Observational Learning.
 |
FART-NeRF: Fast Accumulative Realtime Traning of Neural Radiance Field Dead Project 2023 @ CMU WiSELab
Concurrent work Gaussian Splatting beat me on explicit NeRF, so not gonna publish. |
|
 |
Practical NeRFology: A Brief Commentary on Neural Radiance Fields Technical Report 2023 @ CMU WiSELab
|
|
 |
Extracting Cellular Location of Human Proteins Using Deep Learning arXiv 2018 @ SSFS
Code | This is something written by a dumb high-schooler under no guidance. Don't look at it. |
Talks & Teaching
Teaching: 98-205 Introduction to Minecraft (@ CMU StuCo, Spring 2023, Fall 2023, Spring 2024)
Talk: Neural Radiance Field (@ WiSE Lab, Aug.8 2022)
Artwork
TODO. Currently making vocaloid musics (timeline = this summer). I will add other artwork to my page once I have time.
Sanity
If you actually care about me. Switch off my sanity on the top left corner.
Anime Paper Collection
Anime Paper Collection is a academic paper collection that references Japanese anime, manga, music, games, and more (ACG+). We as tech otaku, are all about sharing what we love without feeling shy. Join us and add your paper to the mix, and let's enjoy our passions together! Contact me to add yours!
 |
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing Chenyang Qi, Xiaodong Cun, Yong Zhang, Chenyang Lei, Xintao Wang, Ying Shan, and Qifeng Chen arXiv 2023 Featuring: Fate/Zero
Paper | Project Page | Code |
|
 |
Generating Manga from Illustrations via Mimicking Manga Workflow Lvmin Zhang, Xinrui Wang, Qingnan Fan, Yi Ji, and Chunping Liu CVPR 2021 Featuring: 炭治郎 (鬼滅の刃), 初音ミク (VOCALOID), レム (Re:ゼロから始める異世界生活), 御坂美琴 (とある魔術の禁書目録)
|
|
 |
More Kawaii than a Real-Person Live Streamer: Understanding How the Otaku Community Engages with and Perceives Virtual YouTubers Zhicong Lu, Chenxinran Shen, Jiannan Li, Hong Shen, and Daniel Wigdor CHI 2021 Featuring: Kanae, Kuzuha, Roi, Nekomiya Hinata, Tsukino Mito, Sasaki Saku, Natsuiro Matsur, Kizuna Ai, Minato Aqua, Kagura Nana, and Tsukudani Norio
|
|
 |
Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN Lvmin Zhang, Yi Ji, and Xin Lin ACPR 2017 Featuring: 初音ミク (VOCALOID), レム (Re:ゼロから始める異世界生活)
|
