RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition

3D ResNets for Action Recognition (CVPR 2018)

Official implementation for NerVE CVPR2023

OctNet: Learning Deep 3D Representations at High Resolutions

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

SMPL-X

Code release for ConvNeXt model

This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T