Liangming Chen's repositories
DI-engine
OpenDILab Decision AI Engine
PythonRobotics
Python sample codes for robotics algorithms.
awesome-neural-ode
A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.
Sophia
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
Neural-ODE-Robot-Learning
Cartpole dynamics prediction using neural ode solver with Gym space.
SE3HamDL
Code for our RSS'21 paper: "Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control"
sonode
Experiments from the paper "On Second Order Behaviour in Augmented Neural ODEs"
DM-Improves-AT
Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)
DeIT-CIFAR
Data Effiecient Image Transformers Implemented on a smaller Scale, using the CIFAR100 dataset and downsampled Imagenet ImageNet32
suppression-connection
Code for the paper "Robustness Requires Different Structures Than Residual Connection"
consistency_models
Official repo for consistency models.
ODE4RobustViT
Understanding Adversarial Robustness of Vision Transformers via Cauchy Problem
QPyTorch
Low Precision Arithmetic Simulation in PyTorch
pytorch-cifar-models
Pretrained models on CIFAR10/100 in PyTorch
hlb-CIFAR10
Train to 94% on CIFAR-10 in less than 7 seconds on a single A100, the current world record. Or ~95.80% in ~120 seconds (or less!).
yuketangHelper
大学研究生院雨课堂的脚本仓库,该仓库下的脚本经过小改动后也适用于其他院校的雨课堂网课作业和视频。
vision-transformers-cifar10
Let's train vision transformers (ViT) for cifar 10!
torchxai
Visualzation methods that help developers to realize the deep network (Explainable AI)
Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
gradient-descent-the-ultimate-optimizer
Code for our NeurIPS 2022 paper
mae_st
Official Open Source code for "Masked Autoencoders As Spatiotemporal Learners"
deep-learning-dynamics-paper-list
This is a list of peer-reviewed representative papers on deep learning dynamics (optimization dynamics of neural networks). The success of deep learning attributes to both network architecture and stochastic optimization. Thus, deep learning dynamics play an essentially important role in theoretical foundation of deep learning.
Deformable-Convolution-V2-PyTorch
Deformable ConvNets V2 (DCNv2) in PyTorch
functorch
functorch is JAX-like composable function transforms for PyTorch.
torchdyn
A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
SALR
SALR: Sharpness-aware Learning Rate Scheduler for Improved Generalization
auto-attack
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
LeViT
LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference