RunzheYang

S5

audio-diffusion

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

R-NaD

Experimentation with Regularized Nash Dynamics on a GPU accelerated game

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

connected-components-3d

Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)

manim

A community-maintained Python framework for creating mathematical animations.

mindall-e

PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs

navis

Python library for analysis of neuroanatomical data.

hopfield-layers

Hopfield Networks is All You Need

word2gm

Word to Gaussian Mixture Model

wuhan2020

新型冠状病毒防疫信息收集平台

cocoa

Framework for learning dialogue agents in a two-player game setting.

PsyNeuLink

A block modeling system for cognitive neuroscience

seqNMF

An algorithm for unsupervised discovery of sequential structure

clip-as-service

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

mario_rl

gym-super-mario-bros

An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES

neuroglancer

WebGL-based viewer for volumetric data

ffn

Flood-Filling Networks for instance segmentation in 3d volumes.

fine-tuning.pytorch

Pytorch implementation of fine tuning pretrained imagenet weights

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

DeepReinforcementLearningThatMatters

Accompanying code for "Deep Reinforcement Learning that Matters"

Stein-Variational-Gradient-Descent

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

visdom

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

pytorch-semseg

Semantic Segmentation Architectures Implemented in PyTorch

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

C51DQN

A TensorFlow implementation of DeepMind's A Distributional Perspective on Reinforcement Learning.(C51-DQN)

language-grounding-experiments

To do experiments on language grounding.

MARL-Papers

Paper list of multi-agent reinforcement learning (MARL)

facets

Visualizations for machine learning datasets