My research journey spans both academia and industry, unified by a central interest in low-dimensional principles of intelligence - a high-level overview is available in my writeup for the CPAL conference, for those interested: https://cpal.cc/vision/.

 

At the university level, we currently revisit classical sparse and low-rank optimization through the lens of modern AI, developing theory-driven algorithms that accelerate training and inference in large-scale models. We also investigate how algebraic and logical structures emerge during learning, uncovering the interplay between neural and symbolic computation across streamlined architectures, reasoning pipelines, and multi-agent systems. Our latest research efforts are organized into four thematic thrusts, outlined below.

 

Historically, my work has included deep learning theory, learning-augmented optimization, sparse coding & inverse problems, and visual restoration & understanding — areas in which I remain (somehow) engaged.

​

In parallel, my industry experiences have opened several new, distinct research directions inspired by practical deployments and large-scale systems: geometry deep learning and graphs (with Amazon),  video generation (with Picsart), and foundation model training for trading (with XTX Markets)