Open-source libraries and research tools.
I created TensorLy to make tensor methods easier to use and extend. It provides a consistent Python API for tensor decomposition, regression, and tensorized neural networks, and is used across research and industry.
ATLAS
I co-lead NeuralOperator, an open-source PyTorch library for training neural operators. Part of the PyTorch Ecosystem, it provides tested implementations and training utilities for operator learning.
Easy configuration of Python projects with minimal boilerplate. A clean, Pythonic approach to configuration management, particularly adapted for deep learning research.
The AFEW-VA dataset provides per-frame valence and arousal labels, together with 68 facial landmarks, for 600 challenging video clips drawn from feature films. The clips complement the discrete emotion annotations available in the AFEW database.
Deep tensorized neural networks in PyTorch. Provides out-of-the-box tensor layers, decomposition methods, and utilities for building efficient deep learning models.
A Python annotation tool built with Flask and MongoDB for collecting remote, per-frame valence and arousal labels from multiple annotators. It can also be extended to support additional annotation tasks, such as discrete emotion labeling.
Quantum machine learning with tensor methods. Bridging quantum computing and tensor decomposition for scalable quantum algorithms.