[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"

Figure sizes, font sizes, fonts, and more configurations at minimal overhead. Fix your journal papers, conference proceedings, and other scientific publications.

A unified multi-task time series model.

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Graph-linked unified embedding for single-cell multi-omics data integration

DANCE: a deep learning library and benchmark platform for single-cell analysis

Codebase for PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs.

🏠[ECCV 2024] GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting

[CVPR'23] Video Probabilistic Diffusion Models in Projected Latent Space

NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine learning, exposed to end-users in pure Python/NumPy.

A library for Koopman Neural Operator with Pytorch.

Memory mapped numpy arrays of varying shapes

A high-level, easy-to-deploy non-uniform Fast Fourier Transform in PyTorch.

A Library for Advanced Neural PDE Solvers.

UCE is a zero-shot foundation model for single-cell gene expression data

PyTorch implementation of the diffusion-based method for CFD data super-resolution proposed in the paper "A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction".

Characterizing possible failure modes in physics-informed neural networks.

Code for the paper Universal Physics Transformers

CVPR 2024-Improved Implicit Neural Representation with Fourier Reparameterized Training

[Neurips 2024] A benchmark suite for autoregressive neural emulation of PDEs. (≥46 PDEs in 1D, 2D, 3D; Differentiable Physics; Unrolled Training; Rollout Metrics)

[AAAI2025] This repo holds the code for work "GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution"

[NeurIPS 2023 Spotlight] Separable Physics-Informed Neural Networks

InverseBench (ICLR 2025 spotlight)

[ICML 2024] LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery

Official implementation of Diffusion Graph Networks (DGNs)

Diffusion for climate downscaling

Agustinus' very opiniated publication-ready plotting library

The official repository for Neural Fourier Filter Bank (CVPR 2023)

Code for "DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training"