Talks, announcements, and milestones from my research and open-source work.
Updates
40 updates
Neural Operators: Applications
HACE 2026 Workshop on HPC/AI Hybridization, IRIT, Toulouse
Invited applications talk on neural operators in a session examining AI-based surrogate models for solving partial differential equations.
Definition of AI for Science and Engineering
National Institute for Defense Health Cooperation at the Uniformed Services University in Bethesda, Maryland, USA
NeuralOperator joins the PyTorch Ecosystem: Learning in Infinite Dimension with Neural Operators
Neural Operators for Scientific Applications: Learning on Function Spaces
Mechanical Engineering Seminar, University of California, Santa Barbara
Invited seminar introducing neural operators for scientific computing, with applications to weather forecasting and other physics-based problems, tensor methods, and open-source implementations.
Neural Operators: A Scalable Framework for AI-Driven Scientific Discovery
LSSDA Workshop, SLAC National Accelerator Laboratory
Workshop talk on neural operators as a scalable framework for scientific discovery, including function-space learning, operator architectures, and open-source tools.
Neural Operators for Scientific Applications: Learning on Function Spaces
AI & Scientific Discovery Seminar, University of Chicago
Introduced the fundamentals of neural operators, which learn mappings between function spaces, their application to problems such as weather forecasting, and how tensor algebraic methods further improve computational efficiency.
Neural Operators: A Framework for Scalable Scientific Computing
VOILA!, AIDA AI Doctoral Academy, Université Côte d’Azur
Presented a framework for scalable scientific computing using neural operators, discussing their theoretical foundations and practical applications.
Accelerating Science and Engineering Simulation with Neural Operators
AI for Science Symposium, Royal Swedish Academy of Sciences, Stockholm
Invited keynote on where AI is heading in scientific discovery, discussing neural operators and tensor methods for physics-based simulation.
Neural Operators for Scientific Applications: Learning on Function Spaces
Artificial Intelligence Expo, Oak Ridge National Laboratory
Invited talk on neural operators for scientific applications, explaining how learning mappings between function spaces can accelerate simulation, prediction, and scientific computing.
Neural Operators for Scientific Applications: Learning on Function Spaces
SILO Seminar, University of Wisconsin–Madison
Introduced the fundamentals of neural operators, which generalize deep learning to mappings between function spaces, and demonstrated their application to concrete problems such as weather forecasting, including how tensor algebraic methods improve computational efficiency.
Real-World Applications of Physics-Enhanced ML
Institute of Physics, London
A discussion of real-world applications of Physics-Enhancing Machine Learning (PEML) at the IOP conference.
AI for Science Symposium
ML Foundry, San Francisco
A gathering focused on the intersection of machine learning and scientific discovery.
Tensor Decompositions in Modern AI
TRICAP 2025, Ålesund, Norway
Invited talk at this interdisciplinary meeting on tensor decompositions and algorithms, discussing their increasing relevance in modern AI.
Infrastructure for Large-Scale Scientific Data
SLAC National Accelerator Laboratory, Palo Alto
A discussion on the infrastructure needed for large-scale scientific data processing and machine learning at scale.
Co-organized workshop with Topal team at INRIA Bordeaux on efficient scaling of neural architectures, covering re-materialization, offloading, scheduling and model pipelining
Co-organizer, ICML Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization
Co-authored a book chapter, "Tensor methods in deep learning", in the book Signal Processing and Machine Learning Theory
Invited speaker at the Scale by the Bay, bay area AI, 2023, hosted by IBM on AI for Science with Neural Operators
Organizer, NeurIPS Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization
We set a new world record, for the largest quantum circuit simulation, using TensorLy-Quantum, NVIDIA's cuQuantum library and a new methodology we developed. Using 896 GPUs to simulate 1,688 qubits, we were able to solve the MaxCut problem for a graph with 3,375 vertices!
Our paper on emotion analysis in the wild was published in Nature Machine Intelligence: Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Our method jointly estimates categorical emotions and continuous valence and arousal. It was the first system to match or outperform expert human annotators on continuous valence and arousal estimation in the wild: on AffectNet and SEWA, its agreement with the reference annotations matched or exceeded the agreement between expert annotators.
Accepted paper at CVPR 2020: Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation
New AAAI paper: Incremental multi-domain learning with network latent tensor factorization
Invited speaker at the Third International Workshop on “Robust Subspace Learning and Applications in Computer Vision” at ICCV 2019
Paper SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild accepted at TPAMI!
Co-organizer of the CVPR tutorial Cause-and-Effect in a Tensor Framework with Alex Vasilescu and Lieven De Lathauwer
Delivered a tutorial on advanced deep learning, tensor methods and quantization at Caltech
Delivered a GTC talk “Take Your Machine Learning to Higher Dimensions with Tensor Methods”, together with my colleague Chris Choy
Paper on T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor accepted at CVPR'19
Co-organizing the ICCV 2017 Workshop on Matrix and Tensor Factorization Methods for Computer Vision
Paper on Tensor Contraction Layers for Parsimonious Deep Nets accepted at CVPR'17 Workshop on Tensor Methods in Computer Vision
No matching updates.