[WWW 25] Graph Neural Controlled Differential Equations For Collaborative Filtering

[ICML 2024] Official implementation of: "Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling".

PDE Preserved Neural Network

Efficient Zero-Knowledge Proofs for LoRA Verification

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

We study toy models of skill learning.

[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

Sky-T1: Train your own O1 preview model within $450

Artificial Kuramoto Oscillatory Neurons

The implementation of paper "Preference Diffusion for Recommendation" published in ICLR 2025.

A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

Code of “STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Prediction”.

An up-to-date list of time-series related papers in AI venues.

Official implementation of the paper "FilterNet: Harnessing Frequency Filters for Time Series Forecasting"

[ICLR 2024 Spotlight] SNIP on Symbolic Regression: Deep Symbolic Regression with Multimodal Pretraining

Official Code for "CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecasting"

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

FLD

Official Implementation of DINO-Foresight: Looking into the Future with DINO

[KDD'24] Official code for our paper "Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting".

Multimodal contrastive pretraining for astronomical data

A 15TB Collection of Physics Simulation Datasets

Short intro to scientific machine learning using physics informed neuronal networks. I used PyTorch as a framework.

Tooling for creating, visualising and storing data-driven weather-model graphs

[SIGKDD'2025] Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.