A framework for discovering which inputs shape the full conditional law of a target—beyond the conditional mean—for parsimonious digital-twin surrogates.
A public multi-echelon logistics digital twin for simulation, dataset generation, and forecasting benchmarks, with interpretable controls and verification tools.
CHONKNORIS achieves machine-precision operator learning by regressing Cholesky factors of Newton–Kantorovich updates rather than the solution operator itself.
A computational-token framework with RL-guided search that rediscovers and invents algorithms for combinatorial optimization and quantum computing.
We use Random Matrix Theory and regularization to prune deep neural networks, achieving state-of-the-art results on ImageNet with Vision Transformers. We also provide theoretical justification for our approach.
We present a general framework to combine existing models in a robust manner. Our method is flexible, places few assumptions on the models aggregated, and performs well in our experiments.
This paper introduces Computational Hypergraph Discovery (CHD), a novel method for uncovering unknown functional relationships between variables within datasets, and represent them using a hypergraph.
My first paper! This paper describes the work we did at Doc.ai for ShareCare on Myasthenia gravis (MG) with UCB. We developed a Deep Learning model based on ResNet50 to predict a key symptom of MG via selfie. This would allow clinical trials to accept more patients as part of a study in order to scale it, as well as follow almost in real time the evolution of a patient's symptoms using an app on their phone.