antithetic-vae-public

Providing reproducibility in deep learning frameworks

Official implementation for the paper "Model-based Diffusion for Trajectory Optimization". Model-based diffusion (MBD) is a novel diffusion-based trajectory optimization framework that employs a dynamics model to run the reverse denoising process to generate high-quality trajectories.

PyTorch implementation for "Parallel Sampling of Diffusion Models", NeurIPS 2023 Spotlight

Lightweight library of stochastic gradient MCMC algorithms written in JAX.

Official Code for "Non-Probability Sampling Network for Stochastic Human Trajectory Prediction (CVPR 2022)"

Can we predict accurately on the skewed data? What are the sampling techniques that can be used. Which models/techniques can be used in this scenario? Find the answers in this code pattern!

RRT Star path planning for dynamic obstacle avoidance for the F110 Autonomous Car

Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (TMLR2024)

Know Your Boundaries: Constraining Gaussian Processes by Variational Harmonic Features

A collection of various LLM sampling methods implemented in pure Pytorch