Offical implementation of "QKFormer: Hierarchical Spiking Transformer using Q-K Attention" (NeurIPS 2024 Spotlight)

✨✨Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Spike-Driven Transformer

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Deep and online learning with spiking neural networks in Python

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

PyTorch implementation of Spatial-Temporal Synchronous Graph Convolutional Networks

Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs" by Boris Ivanovic and Marco Pavone.

A selection of state-of-the-art research materials on trajectory prediction

Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction"

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018

SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints

吴恩达老师的机器学习课程个人笔记

deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by Mathieu, Couprie & LeCun.

Frame interpolation

An open autonomous driving platform