Jungsub Lim

ai-hedge-fund. An AI Hedge Fund Team

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

boltz. Official repository for the Boltz biomolecular interaction models

Protenix. Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

ta-lib-python. Python wrapper for TA-Lib (http://ta-lib.org/).

Tictactoe-Multiplayer-Game. Dart

AlphaFold3. Open source implementation of AlphaFold3

rl_algorithms. Structural implementation of RL key algorithms

pg-is-all-you-need. Policy Gradient is all you need! A step-by-step tutorial for well-known PG methods.

NOS. Protein Design with Guided Discrete Diffusion

2023-python-coding-test. Python

drl-rubiks-cube. Solving Rubik's Cube with Deep Reinforcement Learning, A* and visualize with PyQt5.

variado. Python

gpt-crawler. Crawl a site to generate knowledge files to create your own custom GPT from a URL

chroma. A generative model for programmable protein design

protpardelle. Diffusion-based all-atom protein generative model.

molformer. Repository for MolFormer

diffab-pytorch. An unofficial re-implementation of DiffAb, a diffusion-based generative model for antigen-specific antibody design and optimization.

latexify_py. A library to generate LaTeX expression from Python code.

ScoreDiffusionModel. The Pytorch Tutorial of Score-based and Diffusion Model

RoseTTAFold2. Python

ema-pytorch. A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model

transformer-evolution. Transformer 이후 나온 Pretrained Language Model을 간단하게 구현하였음.

foldingdiff. Diffusion models of protein structure; trigonometry and attention are all you need!

Uni-Core. an efficient distributed PyTorch framework

pychimera. Use UCSF Chimera Python API in a standard interpreter

minimal-diffusion. A minimal yet resourceful implementation of diffusion models (along with pretrained models + synthetic images for nine datasets)

RFdiffusion. Code for running RFdiffusion

RFDesign. Protein hallucination and inpainting with RoseTTAFold

deepchem. Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

se3-transformer-public. code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503

alphafold2. To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

axial-attention. Implementation of Axial attention - attending to multi-dimensional data efficiently

FlutterWithMediaPipe. Flutter with MediaPipe ML models

trajectory-transformer. Code for the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem"

gnolang-101. An introductory course in Gnolang for developers.

trax. Trax — Deep Learning with Clear Code and Speed

GiraffeDet. Python

lightweight-neural-architecture-search. This is a collection of our zero-cost NAS and efficient vision applications.

loss-landscape. Code for visualizing the loss landscape of neural nets

super-gradients. Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

Python-Algorithm-Solving. 알고리즘 파이썬 풀이

MXMNet. Source code for "Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures" (NeurIPS 2020 Workshop)

stat479-deep-learning-ss19. Course material for STAT 479: Deep Learning (SS 2019) at University Wisconsin-Madison

Transformers-Tutorials. This repository contains demos I made with the Transformers library by HuggingFace.

Environmental-Issues-Text-Mining. 텍스트 마이닝을 이용한 KEI 연구동향 분석

text_classification. all kinds of text classification models and more with deep learning

speech_to_text_and_text_to_speech. Dart

stable-diffusion. A latent text-to-image diffusion model

PytorchGeometricTutorial. Pytorch Geometric Tutorials

dimenet. DimeNet and DimeNet++ models, as proposed in "Directional Message Passing for Molecular Graphs" (ICLR 2020) and "Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules" (NeurIPS-W 2020)

dl4chem-mgm. Python

reaction-translation. organic chemistry reaction prediction using NMT

Samsung-AI-Challenge-for-Scientific-Discovery. 🥇Samsung AI Challenge 2021 1등 솔루션입니다🥇

fastapi-best-practices. FastAPI Best Practices and Conventions we used at our startup

grover. This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data

MolecularTransformer. Python

study-flutter. C++

brain-agent. Brain Agent for Large-Scale and Multi-Task Agent Learning

ktrain. ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

basic-algo-lecture. 바킹독의 실전 알고리즘 강의 자료

bookclub. Having a good time with your fellow intellectuals

flutter-state-management. A collection of Flutter apps with various state management services implemented.

sac. Soft Actor-Critic

flutter_voice. https://youtu.be/wDWoD1AaLu8

binance-spot-api-docs. Official Documentation for the Binance Spot APIs and Streams

binance-official-api-docs. Official Documentation for the Binance APIs and Streams

HighwayEnv. A collection of environments for autonomous driving and tactical decision-making tasks

neural_testbed. Jupyter Notebook

educational. Jupyter Notebook

neural-processes. This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

alphafold. Open source code for AlphaFold 2.

cafemate. JavaScript

6th-camp_us-be. 떠나고 싶을 땐 CampUs🏕️

modern-unix. A collection of modern/faster/saner alternatives to common unix commands.

Misc-Cheatsheet. A collection of development and research tips from experience

Bybit-Trading-Bot-Integrated-with-TradingView-Webhook-Alerts. Python based Trading Bot that uses TradingView.com webhook JSON alerts to place orders(buy/sell/close/manage positions/TP/SL/TS etc.) on Bybit.com.

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

dotfiles. :house: Personal dotfiles for *NIX systems

latex-examples. LaTeX examples, adapted from old assignments

LG_Plant_Disease_Diagnosis. DACON AI Competition for Plant Disease Classification

LG_plant_disease_diagnosis_competition. Python

transformer-time-series-prediction. proof of concept for a transformer-based time series prediction model

growneuron. Jupyter Notebook

Machine-Learning-Collection. A resource for learning about Machine learning & Deep Learning

hififace. Unofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)

AerialDetection. Jupyter Notebook

mmdetection. OpenMMLab Detection Toolbox and Benchmark

ttach. Image Test Time Augmentation with PyTorch!

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

bulbea. :boar: :bear: Deep Learning based Python Library for Stock Market Prediction and Modelling

AYolov2. Python

h-baselines. A repository of high-performing hierarchical reinforcement learning models and algorithms.

Hierarchical-Attention-Reinforcement-Learning. Hierarchical Attention in Reinforcement Learning for Stock Order Executions

data-efficient-gans. [NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

T2I_CL. Python

Text-to-Image-Synthesis. Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper

FNA. Fast Neural Network Adaptation via Parameter Remapping and Architecture Search (ICLR2020 & TPAMI)

gym-anytrading. The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)

ilgizar-candlestick-panel. Grafana candlestick panel plugin

support_resistance. Small package that helps to find support and resistance levels and plot them on chart

Recommendations_with_IBM. HTML

JORLDY. Repository for Open Source Reinforcement Learning Framework JORLDY

binance-trade-bot. Automated cryptocurrency trading bot

binance-trading-bot. Automated Binance trading bot - Trade multiple cryptocurrencies. Buy low/sell high with Grid Trading. Integrated with TradingView technical analysis

pytorch-cifar. 95.47% on CIFAR10 with PyTorch

gpt3_book_sandbox. Python

EAS. Efficient Architecture Search by Network Transformation, in AAAI 2018

rliable. [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

cs231n. Jupyter Notebook

research-advice-list. A compilation of research advice.

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

DeepReinforcementLearning. A replica of the AlphaZero methodology for deep reinforcement learning in Python

Binance-CCXT-Data-Downloader. Python

LMkor. Pretrained Language Models for Korean

NAS-With-Code. Neural Architecture Search (NAS) papers with code

tpunicorn. Babysit your preemptible TPUs

NetReform. Network Reformation using Tensorflow

Net2Net. Tensorflow and Numpy Implementation of Net2Net (http://arxiv.org/abs/1511.05641)

Net2Net_Cifar10. Implementation of Net2Net method and application on Cifar10 dataset

cvar-algorithms. Risk-Averse Distributional Reinforcement Learning: Code

Binance-api-step-by-step-guide. These are the code snippets used in the Binance Python API - A step-by-step guide on the AlgoTrading101 website

rlai-exercises. Exercise Solutions for Reinforcement Learning: An Introduction [2nd Edition]

Rainbow. Rainbow: Combining Improvements in Deep Reinforcement Learning

rainbow-iqn-apex. Distributed Rainbow-IQN for Atari

Deep_RL_with_pytorch. A pytorch tutorial for DRL(Deep Reinforcement Learning)

sac. Soft Actor-Critic

MARL-Algorithms. Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II

pymarl2. Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

maddpg. Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

multiagent-particle-envs. Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Minigrid. Simple and easily configurable grid world environments for reinforcement learning

pymarl. Python Multi-Agent Reinforcement Learning framework

SMAC. StarCraft II Multi Agent Challenge : QMIX, COMA, LIIR, QTRAN, Central V, ROMA, RODE, DOP, Graph MIX

pytorch-r2d2. PyTorch implementation of R2D2 (Recurrent Reply Distributed DQN)

vel. Velocity in deep-learning research

Multi-Agent-Deep-Deterministic-Policy-Gradients. A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm

never-give-up. PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies

snuon-assistant. eTL SNUON에 배속 재생, 탐색, 단축키 등 강의 시청을 도와주는 여러 도구를 추가합니다.

distributed_reinforcement_learning. implementation of distributed reinforcement learning with distributed tensorflow

NAS-FCOS. NAS-FCOS: Fast Neural Architecture Search for Object Detection (CVPR 2020)

single-path-nas. Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

Reinforcement-Learning-Q-learning-8puzzle-Pytorch. This is a project using neural-network reinforcement learning to solve the 8 puzzle problem (or even N puzzle)

dcnet. Jupyter Notebook

alpha-zero-general. A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

cloudml-hypertune. Python

Efficient-AI-Backbones. Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

stock_market_reinforcement_learning. This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.

Hierarchical-Attention-Network. A PyTorch implementation of the document classification by Hierarchical Attention Network

neptune-client. 📘 The experiment tracker for foundation model training

Hierarchical-attention-networks-pytorch. Hierarchical Attention Networks for document classification

blog. SCSS

DANN-pytorch. Implementation of DANN with pytorch

netron. Visualizer for neural network, deep learning and machine learning models

S3NAS. Fast NPU-aware Neural Architecture Search

MIPS_SIMULATOR. MIPS simulator in C++

pytorch-lambdapack. Serving PyTorch Models on AWS Lambda

python-for-coding-test. [한빛미디어] "이것이 취업을 위한 코딩 테스트다 with 파이썬" 전체 소스코드 저장소입니다.

fiber. Distributed Computing for AI Made Simple

react-firebase-blog. JavaScript

React-Redux-Firebase-App. All course files for the React, Redux & Firebase App playlist on The Net Ninja YouTube channel.

django-quickstarter. Tool for quickly creating Django projects

monaco-editor-samples. Moved to https://github.com/microsoft/monaco-editor

prismagram-frontend. Frontend for Instaclone 2.0 (GraphQL + Hooks)

django-blog-app. Django Blog App

JoyurIZ-WEB. JavaScript

dream_blog. A simple blog built with Django and Bootstrap4

influx-prompt. An interactive command-line InfluxDB cli with auto completion.

fc-js-project. HTML

influxdb-python. Python client for InfluxDB

workshop-k8s-basic. 쿠버네티스 기본 실습 가이드 kubernetes basic

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

GIGAgenie-AutoQuizGeneration. HTML

181215_AIBootCamp_Azure_ML_StudioHOL. 2018년 12월 15일 AIBootCamp 친절한 Azure ML Studio HOL입니다 :)

my-django-blog. Python

gcp-dfpnewco. Google Cloud (GCP) Dataflow Implementation to Ingest data into BigQuery

Kaggle-knowhow. Kaggle-Knowhow(Korean Ver) 한국분들을 위한 Kaggle 자료 모음입니다

nni. An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

TIL. Today I Learned

buffalo. TOROS Buffalo: A fast and scalable production-ready open source project for recommender systems

neural_collaborative_filtering. Neural Collaborative Filtering

elastic. Elastic Stack (6.2.4) 을 활용한 Dashboard 만들기 Project

TradingZoo-Dynamic-fee-simulation. Simulate binance fee mechanism by RL agents

deep-reinforcement-learning. Repo for the Deep Reinforcement Learning Nanodegree program

distributional_rl. Repository for studying distributional rl

rl_pytorch. Deep Reinforcement Learning Algorithms Implementation in PyTorch

minimalRL. Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

geth-ELK. :ferris_wheel: Geth + Elastic

PRML-Solution-Manual. My Own Solution Manual of PRML

meme-glossary. Meme serving with NLP

flask-crud. flask-crud exercise for sqlite3

flask-intro. flask, sql basic exercise

django-crud. Python

django-intro. first using Django

Ape-X. PyTorch Implementation of Distributed Prioritized Experience Replay(Ape-X)

RL-Adventure. Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL

eth-ghost-sol. the GHOST protocol implementation on solidity.

kaggleml.

balance-hero. 'balance-hero' simulation

slacker. Full-featured Python interface for the Slack API