Stars
TerDiT: Ternary Diffusion Models with Transformers
A unified ensemble framework for PyTorch to improve the performance and robustness of your deep learning model.
Neural Networks with low bit weights on low end 32 bit microcontrollers such as the CH32V003 RISC-V Microcontroller and others
EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
Normalizing Flows with a resampled base distribution
PyTorch implementation of normalizing flow models
Instant neural graphics primitives: lightning fast NeRF and more
Establishing Quantified Uncertainty in Neural Networks
PyTorch-centric library for evaluating and enhancing the robustness of AI technologies
Create powerful Hydra applications without the yaml files and boilerplate code.
Monotone operator equilibrium networks
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
A simple and efficient Mamba implementation in pure PyTorch and MLX.
Tools for easing the handoff between AI/ML and App/SRE teams.
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
[ICLR 2024] Official implementation of Bellman Optimal Stepsize Straightening of Flow-Matching Models
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
A summary of related works about flow matching, stochastic interpolants
TorchCFM: a Conditional Flow Matching library
A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.
Structured state space sequence models
Repository related to the manuscript "Automatic Gemstone Classification Using Computer Vision" by Bona Hiu Yan Chow and Constantino Carlos Reyes-Aldasoro published in Minerals MDPI, 2022, 12(1), 60…
Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness
A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.