Name: Xingyuan Zhang
Type: User
Company: Machine Learning Research Lab, Volkswagen AG
Bio: An intelligent machine who wants to understand himself. Doing PhD in world models.
Twitter: xyzhang42
Location: Munich, Germany
Blog: https://icaruswizard.github.io/
Xingyuan Zhang's Projects
Awesome work on hand pose estimation/tracking
A curated list of awesome model based RL resources (continually updated)
Codebase of Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
Collection of PyTorch implementation for several deep generative models.
Python package for the Distracted Control Suite
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Dream to Control: Learning Behaviors by Latent Imagination
Mastering Atari with Discrete World Models
Mastering Diverse Domains through World Models
The repository for the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).
exploration on building general intelligent machine
Config files for my GitHub profile.
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)
PyTorch implementation of Masked Autoencoder
Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
Reinforcement learning algorithms for MuJoCo tasks
PaddlePaddle Implementation of Monodepth
PaddlePaddle Implementation of Monodepth2
Multi-Joint dynamics with Contact. A general purpose physics simulator.
PaddlePaddle implementation of OctConv
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)
Implementation of PatchAIL in the ICLR 2023 paper <Visual Imitation with Patch Rewards>
PyTorch release for paper "Pixel-wise Regression: 3D Hand Pose Estimation via Spatial-form Representation and Differentiable Decoder"
PaddlePaddle implementation of PredNet.
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
A Configurable Recommender Systems Simulation Platform