Pinned Repositories
M2T2
M2T2: Multi-Task Masked Transformer for Object-centric Pick and Plac
curl
RL spring 2020 course project
deepgmr
PyTorch implementation of DeepGMR: Learning Latent Gaussian Mixture Models for Registration (ECCV 2020 spotlight)
emoji-prediction
it-net
Implementation of Iterative Transformer Network for 3D Point Cloud
LLaVA
pcd_seg
Semantic point cloud segmentation with graph convolutional network
pcn
Code for PCN: Point Completion Network in 3DV'18 (Oral)
RoboPoint
A Vision-Language Model for Spatial Affordance Prediction in Robotics
sornet
Code for SORNet: Spatial Object-Centric Representations for Sequential Manipulation in CoRL 2021 (Best Systems Paper Finalist)
wentaoyuan's Repositories
wentaoyuan/pcn
Code for PCN: Point Completion Network in 3DV'18 (Oral)
wentaoyuan/deepgmr
PyTorch implementation of DeepGMR: Learning Latent Gaussian Mixture Models for Registration (ECCV 2020 spotlight)
wentaoyuan/RoboPoint
A Vision-Language Model for Spatial Affordance Prediction in Robotics
wentaoyuan/sornet
Code for SORNet: Spatial Object-Centric Representations for Sequential Manipulation in CoRL 2021 (Best Systems Paper Finalist)
wentaoyuan/it-net
Implementation of Iterative Transformer Network for 3D Point Cloud
wentaoyuan/pcd_seg
Semantic point cloud segmentation with graph convolutional network
wentaoyuan/emoji-prediction
wentaoyuan/curl
RL spring 2020 course project
wentaoyuan/LLaVA
wentaoyuan/ddg-exercises-js
wentaoyuan/dqn
wentaoyuan/neural-localization
Active neural localization in noisy environments
wentaoyuan/rl3
wentaoyuan/lightning-bolts
Toolbox of models, callbacks, and datasets for AI/ML researchers.
wentaoyuan/peract
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
wentaoyuan/r3m
Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data
wentaoyuan/RLBench
A large-scale benchmark and learning environment.
wentaoyuan/sornet-website
wentaoyuan/SUNCGtoolbox
C++ based toolbox for the SUNCG dataset
wentaoyuan/YARR
Yet Another Robotics and Reinforcement (YARR) learning framework for PyTorch.