Changmin Yu

AiM. Official PyTorch Implementation of "Scalable Autoregressive Image Generation with Mamba"

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

coinrun. Code for the paper "Quantifying Transfer in Reinforcement Learning"

understanding_dl. A lecture note for understanding deep learning

contextual_frogs. Jupyter Notebook

sr-project. Jupyter Notebook

Kinesis. [ICRA 2026] The official implementation of the paper "Reinforcement Learning-Based Motion Imitation for Physiologically Plausible Musculoskeletal Motor Control"

rnn_remapping_paper. Jupyter Notebook

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

DeepSeek-R1.

SIMPL. Fast optimisation of tuning curves by iterative fitting and decoding

sparse-coding. An implementation of Olshausen and Field (96) in PyTorch

PyIBP. NumPy implementation of infinite latent feature model (aka Indian Buffet Process or IBP)

hdpGLM. Hierarchical Dirichlet Process Generalized Linear Models

Kalman-and-Bayesian-Filters-in-Python. Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.

KalmanNet_TSP. code for KalmanNet

NCRP_HLDA. In this project, a simple Nested Chinese Restaurant Process is implemented. this is done by using HLDA for topic modeling with Gibbs Sampler. this project demonstrates the BBC Insight Dataset for evaluation.

Sanders-et-al-2020-Elife. Python

mamba. Mamba SSM architecture

structured-recognition-neurips-2022. Python

Conditional_Diffusion_MNIST. Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

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, ... 🧠

RePaint. Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022

neural_timeseries_diffusion. This repository contains research code for the paper "Generating realistic neurophysiological time series with denoising diffusion probabilistic models". @jsvetter

RL4LMs. A modular RL library to fine-tune language models to human preferences

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

llama. Inference code for Llama models

olfactory. olfactory (multi-trial GPLVM)

MIND. Implemenation of Manifold Inference from Neural Dynamics (MIND) from Low & Lewallen et. al, '18

models-and-analysis-of-theta-phase-coding. Python

diffusion-posterior-sampling. Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"

conformal-prediction. Lightweight, useful implementation of conformal prediction on real data.

scalable_agent. A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

GPy. Gaussian processes framework in python

paglm. Fast approximate inference for Poisson GLMs

structured-recognition-neurips2022. Python codes used in "Structured Recognition for Generative Models with Explaining Away"

count_based_exploration_sr. Python

online-hdp. Online inference for the Hierarchical Dirichlet Process. Fits hierarchical Dirichlet process topic models to massive data. The algorithm determines the number of topics.

dm_memorytasks. A set of 13 diverse machine-learning tasks that require memory to solve.

dreamer-torch. Pytorch version of Dreamer, which follows the original TF v2 codes.

mbpo_pytorch. A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

bnpy. Bayesian nonparametric machine learning for Python

replicate_kenny_analysis. Python

PP-SVGPFA. Code for Point Process Sparse Variational Gaussian Process Factor Analysis

DReG-PyTorch. A PyTorch re-implementation of "Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives"

Extended-Analytic-DPM. Official implementation for Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models (ICML 2022), and a reimplementation of Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models (ICLR 2022)

D4RL-Evaluations. Python

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

diffuser. Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

awesome-ai-residency. List of AI Residency Programs

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)

mpo. PyTorch Implementation of the Maximum a Posteriori Policy Optimisation

fourier-feature-networks. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

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

DeepKalmanFilter. Pytorch Implementation of Deep Kalman Filter

Normalizing-flow-and-deep-kalman-filter. Jupyter Notebook

GraphRicciCurvature. A python library to compute the graph Ricci curvature and Ricci flow on NetworkX graph.

gpar. Implementation of the Gaussian Process Autoregressive Regression Model

replay_trajectory_classification. State space models for decoding hippocampal trajectories and determining their type using sorted or clusterless data

gpytorch. A highly efficient implementation of Gaussian Processes in PyTorch

gym. A toolkit for developing and comparing reinforcement learning algorithms.

grid-cell-path. Official code for On Path Integration of Grid Cells: Group Representation and Isotropic Scaling (NeurIPS 2021)

hmws. Jupyter Notebook

gp-infer-net. Scalable Training of Inference Networks for Gaussian-Process Models, ICML 2019

pyprobml. Python code for "Probabilistic Machine learning" book by Kevin Murphy

pyro. Deep universal probabilistic programming with Python and PyTorch

intro-stan-python. Notebooks with introductory material on using Stan, from Python

compiled-inference. Train neural networks to use as SMC and importance sampling proposals

ssm. Bayesian learning and inference for state space models

VAELLS. Code for "Variational Autoencoder with Learned Latent Structure"

pytorch-sqrtm. Matrix square root with gradient support for PyTorch

awesome-variational-inference. A curated list of awesome variational inference

vi-hds. Variational inference for hierarchical dynamical systems

Rainbow. Rainbow: Combining Improvements in Deep Reinforcement Learning

BPNN. Python

EfficientZero. Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

autograd. Efficiently computes derivatives of NumPy code.

torch_tem. Implementation of the Tolman Eichenbaum Machine in pytorch

Awesome-VAEs. A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.

mpnn. Open source implementation of "Neural Message Passing for Quantum Chemistry"

pylds. some tools for gaussian linear dynamical systems

Stein-Variational-Gradient-Descent. code for the paper "Stein Variational Gradient Descent (SVGD): A General Purpose Bayesian Inference Algorithm"

google-research. Google Research

TwoStageVAE. Python

lagvae. Lagrangian VAE

vae_vampprior. Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling

gitstats. A lightweight/pretty visualizer for recent work on a git code base in multiple branches. Helps stay up to date with teams working on one git repo in many branches.

drqv2. DrQ-v2: Improved Data-Augmented Reinforcement Learning

procgen. Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

mjrl. Reinforcement learning algorithms for MuJoCo tasks

rad. RAD: Reinforcement Learning with Augmented Data

HPC_manifolds. Analysis of hippocampal activity in the towers task

V-MPO_Lunarlander. Simple implementation of V-MPO proposed in https://arxiv.org/abs/1909.12238

t-vae. Transformer Variational Autoencoder experiment

dmc2gym. OpenAI Gym wrapper for the DeepMind Control Suite

decision-transformer. Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

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

deep-protein-generation. Python

pytorch-normalizing-flows. Normalizing flows in PyTorch. Current intended use is education not production.

awesome-normalizing-flows. Awesome resources on normalizing flows.

normalizing_flows. Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows

deep_control. Deep Reinforcement Learning for Continuous Control in PyTorch

hindsight-experience-replay. This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

mbpo. Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

ai-edu. AI education materials for Chinese students, teachers and IT professionals.

mbpo_pytorch. A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

controllable_agent. Python

batch_rl. Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games

dopamine. Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

optimaltransport.github.io. Web site of the Computational Optimal Transport book

FlexModEHC. Flexible modulation of sequence generation in the entorhinal-hippocampal system.

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

deep-Q-networks. Implementations of algorithms from the Q-learning family. Implementations inlcude: DQN, DDQN, Dueling DQN, PER+DQN, Noisy DQN, C51

CompGCN. ICLR 2020: Composition-Based Multi-Relational Graph Convolutional Networks

generative-models. Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

PyTorch-VAE. A Collection of Variational Autoencoders (VAE) in PyTorch.

gans-awesome-applications. Curated list of awesome GAN applications and demo

sa-vae. Python

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

pytorch-template. PyTorch deep learning projects made easy.

vmp-for-svae. Variational Message Passing for Structured VAE (Code for ICLR 2018 paper)

cule. CuLE: A CUDA port of the Atari Learning Environment (ALE)

distributional_SF. Python

spr. Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

dreamer. Dream to Control: Learning Behaviors by Latent Imagination

upn. Python

Imagination-Augmented-Agents. Building Agents with Imagination: pytorch step-by-step implementation

pytorch_sac. PyTorch implementation of Soft Actor-Critic (SAC)

sac. Soft Actor-Critic

rlpyt. Reinforcement Learning in PyTorch

dm_control. Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

dreamer. Dream to Control: Learning Behaviors by Latent Imagination

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

deepul. Jupyter Notebook

TensorLayer. Deep Learning and Reinforcement Learning Library for Scientists and Engineers

RLcode. Python

higgsfield. Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

pytorch-a2c-ppo-acktr-gail. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

ML-Murphy. Complete solutions for exercises and MATLAB example codes for "Machine Learning: A Probabilistic Perspective" 1/e by K. Murphy

dlwpt-code. Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

bayesian-machine-learning. Notebooks about Bayesian methods for machine learning

course-content. NMA Computational Neuroscience course

sonnet. TensorFlow-based neural network library

grid-cells. Implementation of the supervised learning experiments in Vector-based navigation using grid-like representations in artificial agents, as published at https://www.nature.com/articles/s41586-018-0102-6

generalising-structural-knowledge. Python

144006. Grid cell spatial firing models (Zilli 2012)

Recurrent-Neural-Networks. Jupyter Notebook

IncSFA. Incremental Slow Feature Analysis

Reinforcement-Learning. Jupyter Notebook

Dordek-et-al.-Matlab-code. This repository contains the Matlab code for "Extracting grid characteristics from spatially distributed place cell inputs using non-negative PCA" by Yedidyah Dordek, Daniel Soudry, Ron Meir and Dori Derdikman

the-elements-of-statistical-learning. My notes and codes (jupyter notebooks) for the "The Elements of Statistical Learning" by Trevor Hastie, Robert Tibshirani and Jerome Friedman