YoungJoong Kim

Kimi-K3. Open Frontier Intelligence

2026-HAI-AdvancedLunarLander. Advanced Lunar Lander, Team 6, Project, 2026 HAI S1

Soft-Actor-Critic. Python

Reanchored-Auxiliary-Free-Data-Free-Step-Distillation. Python

rhwp. 아래한글 hwp viewer and editor by rust and wasm

DiffRatio. Official PyTorch Code for DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision

rl-env-benchmark. Reinforcement Learning Environment Benchmark - Native Python, C++, Rust and so on

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

cli. Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

paperclip. The open-source app everyone uses to manage agents at work

JiT. PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

MeanFlow. Pytorch implementation of MeanFlow on ImageNet and CIFAR10

flash-muon. Flash-Muon: An Efficient Implementation of Muon Optimizer

AI-Trader. "AI-Trader: 100% Fully-Automated Agent-Native Trading"

nanochat. The best ChatGPT that $100 can buy.

MrSteve. MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory

backtrader. Python Backtesting library for trading strategies

quarkdown. 🪐 Markdown with superpowers: from ideas to papers, presentations, websites, books, and knowledge bases.

rusty.hpp. Rust-like Traits & A Borrow Checker and Memory Ownership System for C++20 (heavily inspired from Rust)

maybe. The personal finance app for everyone

OLMo. Modeling, training, eval, and inference code for OLMo

FuzzingCapstone. Python

torchdyn. A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

candle. Minimalist ML framework for Rust

RetNet. An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

codon. A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

hwp-rs. A simple hwp parser for cross-platform written in Rust

radius2. radius2 is a fast binary emulation and symbolic execution framework using radare2

consistency_models. Official repo for consistency models.

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

pgrok. Poor man's ngrok - a multi-tenant HTTP/TCP reverse tunnel solution through SSH remote port forwarding

llama.cpp. LLM inference in C/C++

Text2LIVE. Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)

gcem. A C++ compile-time math library using generalized constant expressions

audio-ai-timeline. A timeline of the latest AI models for audio generation, starting in 2023!

dadaptation. D-Adaptation for SGD, Adam and AdaGrad

audio-diffusion-pytorch. Audio generation using diffusion models, in PyTorch.

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

vall-e. An unofficial PyTorch implementation of the audio LM VALL-E

pysptk. A python wrapper for Speech Signal Processing Toolkit (SPTK).

encodec. State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

pyrapt. A pitch tracker inspired by David Talkin's RAPT (Robust Algorithm for Pitch Tracking) written in Python.

Replication-Dataset-Scripts. Scripts for recreating the Replication Dataset for Fundamental Frequency Estimation. Part of the dissertation "Pitch of Voiced Speech in the Short-Time Fourier Transform". © 2020, Bastian Bechtold. All rights reserved.

praat.github.io. Praat: Doing Phonetics By Computer

cqt-pytorch. An invertible and differentiable implementation of the Constant-Q Transform (CQT).

NISQA. NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

phaseaug. ICASSP 2023 Accepted

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

pytorch-histogram-matching. Python

INDM. Official PyTorch implementation for Maximum Likelihood Training of Implicit Nonlinear Diffusion Model (INDM) in NeurIPS 2022.

GANFit. Project Page of 'GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction' [CVPR2019]

Analytic-DPM. Code for the paper Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models (ICLR 2022 Outstanding Paper Award)

FacePose_pytorch. 🔥🔥The pytorch implement of the head pose estimation(yaw,roll,pitch) and emotion detection with SOTA performance in real time.Easy to deploy, easy to use, and high accuracy.Solve all problems of face detection at one time.(极简，极快，高效是我们的宗旨)

repgan. RepVgg + HiFiGAN

i3DMM. Python

iSTFT-Avocodo-pytorch. Ultrafast GAN based Vocoder for Text to Speech

CAE. This is a PyTorch implementation of “Context AutoEncoder for Self-Supervised Representation Learning"

DALLE2-pytorch. Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

vdm. Jupyter Notebook

waveglow-vqvae. WaveGlow vocoder with VQVAE

DYGANVC. demo page https://MingjieChen.github.io/dygan-vc

denoising-diffusion-gan. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

rq-vae-transformer. The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

mup. maximal update parametrization (µP)

CLD-SGM. Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

functorch. functorch is JAX-like composable function transforms for PyTorch.

ncsn. Noise Conditional Score Networks (NeurIPS 2019, Oral)

Retriever. [ICLR2022] Code for "Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph"

DiffGAN-TTS. PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

HVM2. A massively parallel, optimal functional runtime in Rust

variational-diffwave. Python

liegroups. Python implementation of SO2, SE2, SO3, and SE3 matrix Lie groups using numpy or pytorch

JoJoGAN. Official PyTorch repo for JoJoGAN: One Shot Face Stylization

NR-GAN. NR-GAN: Noise Robust Generative Adversarial Networks

score_sde. Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

minitorch. The full minitorch student suite.

awesome-devteam. 좋은 개발팀을 만드는데 도움이 되는 자료

vision-transformer-tf. Reproduction of Vision Transformer in Tensorflow2. Train from scratch and Finetune.

Diffusion-Models-Seminar.

aioway. AI on the way. An auto deep learning pipe dream. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.

precision-recall-distributions. Assessing Generative Models via Precision and Recall (official repository)

alias-free-torch. Simple torch.nn.module implementation of Alias-Free-GAN style filter and resample

mmvae. Multimodal Mixture-of-Experts VAE

face3d. Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.

lyrebird-wav2clip. Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP

stylegan3. Official PyTorch implementation of StyleGAN3

flexflow-train. Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

python-jamo. Hangul syllable decomposition and synthesis using jamo.

speech-resynthesis. An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Comprehensive-Transformer-TTS. A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS

ic_gan. Official repository for the paper "Instance-Conditioned GAN" by Arantxa Casanova, Marlene Careil, Jakob Verbeek, Michał Drożdżal, Adriana Romero-Soriano.

denoiser. Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.

siren. Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

FastPitchFormant. PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

treex. A Pytree Module system for Deep Learning in JAX

guided-diffusion. Python

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

alias-free-gan. Alias-Free GAN project website and code

haste. Haste: a fast, simple, and open RNN library

cyclevae-vc-neuralvoco. Python

CuDDLE. This is a repository for the paper "Barcode: Topological Data Analysis-motivated Generative Model Evaluation Metric"

streamlit. Streamlit — A faster way to build and share data apps.

Temporal-Convolution-Resnet. [Not Official] Implementation of TC-Resnet, INTERSPEECH 2019

spe. Relative Positional Encoding for Transformers with Linear Complexity

parallelformers. Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

argmax_flows. Code for paper "Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions"

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

GradTTS. Pytorch implementation of "Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech"

alphafold. Open source code for AlphaFold 2.

VAENAR-TTS. PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

awesome-gan-papers. A curated list of GAN basics for tutorial, metrics and recent GAN papers (NIPS/CVPR/ICML)

fp-course. Functional Programming Course

S2VC. Python

icecream. 🍦 Never use print() to debug again.

AugLy. A data augmentations library for audio, image, text, and video.

pyfi. PYthon Function Interface for haskell

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

STYLER. Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech, INTERSPEECH 2021

helix. A post-modern modal text editor.

github. The github API for Haskell

stochastic-memoization. Haskell

Parallel-Tacotron2. PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

score_sde_pytorch. PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

awesome-nonsan. 🔫 논산 육군훈련소에 대한 정보와 팁

flaxmodels. Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.

improved-diffusion. Release for Improved Denoising Diffusion Probabilistic Models

guided-diffusion. Python

ViLT. Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

MLP-Mixer-Pytorch. Pytorch reimplementation of the Mixer (MLP-Mixer: An all-MLP Architecture for Vision)

vscode. Visual Studio Code

StyleMapGAN. Official pytorch implementation of StyleMapGAN (CVPR 2021)

tenet. A Trace Explorer for Reverse Engineers

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

g2ps. Data and code for grapheme-to-phoneme transducers in lots of languages

Phonetisaurus. Phonetisaurus G2P

Pytorch-MBNet. A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK

assem-vc. Official Code for Assem-VC @ICASSP2022

nuwave. NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling @ INTERSPEECH 2021

StyleCLIP. Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

madgrad. MADGRAD Optimization Method

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

speechbrain. A PyTorch-based Speech Toolkit

npu_examples. HTML

wit. WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

AdaSpeech. AdaSpeech: Adaptive Text to Speech for Custom Voice

awesome-mlops. A curated list of references for MLOps

highway. Performance-portable, length-agnostic SIMD with runtime dispatch

hsthrift. The Haskell Thrift Compiler. This is an implementation of the Thrift spec that generates code in Haskell. It depends on the fbthrift project for the implementation of the underlying transport.

silero-models. Silero Models: pre-trained text-to-speech models made embarrassingly simple

binaryanalysis-ng. Binary Analysis Next Generation (BANG)

lightning-flash. Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains

pororo. PORORO: Platform Of neuRal mOdels for natuRal language prOcessing

pyinstrument. 🚴 Call stack profiler for Python. Shows you why your code is slow!

nflows. Normalizing flows in PyTorch

PerceptualAudio. Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM

BVAE-TTS. Official implementation of BVAE-TTS

Theseus. Theseus is a modern OS written from scratch in Rust that explores 𝐢𝐧𝐭𝐫𝐚𝐥𝐢𝐧𝐠𝐮𝐚𝐥 𝐝𝐞𝐬𝐢𝐠𝐧: closing the semantic gap between compiler and hardware by maximally leveraging the power of language safety and affine types. Theseus aims to shift OS responsibilities like resource management into the compiler.

workDiary. 병특 재택근무 수행내역서를 채워주는 util

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

survae_flows. Code for paper "SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows"

einops. Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

fc_malloc. Super Fast, Lock-Free, Wait-Free, CAS-free, thread-safe, memory allocator.

rustboot. A tiny 32 bit kernel written in Rust

lexy. C++ parsing DSL

bokeh. Interactive Data Visualization in the browser, from Python

lrmr. Less-Resilient MapReduce for Go

pytorch_sound. Sound Related Deep Learning Tasks boosting repository with pytorch

julius. Fast PyTorch based DSP for audio and 1D signals

auraloss. Collection of audio-focused loss functions in PyTorch

Tacotron. A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis

klox. An interpreter

tensorflow_macos. TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.

WavAugment. A library for speech data augmentation in time-domain

Glow_TTS. An implement of GlowTTS model. Several modes are added: speaker embedding, prosody encoder(GST), and gradient reversal.

Co-dfns. High-performance, Reliable, and Parallel APL

WG-WaveNet. Real-Time High-Fidelity Speech Synthesis without GPU

deepspeech.pytorch. Speech Recognition using DeepSpeech2.

deepspeech.pytorch.ko. Python

python-Levenshtein. The Levenshtein Python C extension module contains functions for fast computation of Levenshtein distance and string similarity

fastdtw. A Python implementation of FastDTW

DeepSpeech2Korean. DeepSpeech2 model for Korean keyword recognition

pytorch-softdtw. An implementation of SoftDTW for PyTorch.

pytorch-softdtw-cuda. Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

google-research. Google Research

phonemizer. Simple text to phones converter for multiple languages

hifi-gan. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Adabelief-Optimizer. Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"

rv6. C

NanoFlow. PyTorch implementation of the paper "NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity." (NeurIPS 2020)

speechmetrics. A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

stan. 🕵️ Haskell STatic ANalyser

genforce. An efficient PyTorch library for deep generative modeling.

ocean. A C/C++ build system/project manager written in Rust

gaugan-gui. A GUI for Nvidia's GauGAN/SPADE like shown in the tech demo.

fast-transformers. Pytorch library for fast transformer implementations

stylegan2-ada. StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation

mgbench. Multi-GPU Computing Benchmark Suite (CUDA)

libcudacxx. [ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl