TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Learning Deep Representations of Data Distributions

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Cramming the training of a (BERT-type) language model into limited compute.

Practice your pandas skills!

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

Interpretable Evaluation for AI Systems

Official code for "VFlow: More Expressive Generative Flows with Variational Data Augmentation" (ICML 2020)

Binarize convolutional neural networks using pytorch 🔥

An elegant PyTorch deep reinforcement learning library.

ReActNet: Towards Precise Binary NeuralNetwork with Generalized Activation Functions. In ECCV 2020.

Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm. In ECCV 2018 and IJCV

code for the paper "A Statistical Framework for Low-bitwidth Training of Deep Neural Networks"

Zhusuan with backend PaddlePaddle

Refining continuous-in-depth neural networks

Keep an Eye on Defects Inspection.

Summary, Code for Deep Neural Network Quantization

Unofficial implementation of LSQ-Net, a neural network quantization framework

Low Precision Arithmetic Simulation in PyTorch

东北方言编程语言

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Open Machine Learning Compiler Framework

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

Code corresponding to the paper "Adversarial Examples are not Easily Detected..."

source code of the paper Graphical Generative Adversarial Networks

Big Topic Model is a fast engine for running large-scale Topic Models.

Population matching discrepancy