“Lord of the recommendation models, Two Tower for All(egro)” Building effective recommendation systems for a massive e-commerce platform like Allegro.com—with over 20 million active buyers and a highly dynamic catalog —presents formidable challenges. How do you deliver diverse, high-relevance suggestions […]
“Lord of the recommendation models, Two Tower for All(egro)” Building effective recommendation systems for a massive e-commerce platform like Allegro.com—with over 20 million active buyers and a highly dynamic catalog —presents formidable challenges. How do you deliver diverse, high-relevance suggestions […]
“The revolution of formal reasoning with AI” 2026 is the year of the agents and the year where formal methods are taking the lead. Driven by the AI progress we are seeing glimpses of the future where autonomous systems will […]
“Post-hoc prototype explanations for classification models” Explainable AI traditionally forces a choice between flexible but vague post-hoc methods (like saliency maps) and intuitive but rigid prototype-based architectures. This talk introduces a framework that bridges this gap: post-hoc prototype explanations. We […]
“Post-hoc prototype explanations for classification models” Explainable AI traditionally forces a choice between flexible but vague post-hoc methods (like saliency maps) and intuitive but rigid prototype-based architectures. This talk introduces a framework that bridges this gap: post-hoc prototype explanations. We […]
“Explainability of Vision-Language Models” In this talk, I will introduce the methodology for explaining vision-language models and discuss the key challenges associated with this research domain. The presentation will highlight our recent scientific results concerning the FIxLIP algorithm published at […]
“Projected Compression: Trainable Projections for Efficient Transformer Compression” Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Consequently, there is rising interest in model […]
“hexDAG (soon to be) – new open source agentic framework” HexDAG is a framework for building deterministic workflows with AI agents. It combines the simplicity of rules with the flexibility of AI, imposing rigorous validation and controlling model stochasticity. Instead […]
“Adaptive and Efficient Computation in Deep Neural Networks” The continuous growth of machine learning models means that their efficiency is crucial to ensure sustainability and broad access to new technologies. This talk will highlight how emergent modularity in deep neural […]
“AI on production. What’s the catch?” During the talk, I will explore some of the challenges you face when deploying AI-based services worldwide. Of course, it’s nice to see high numbers in fancy LLM benchmarks, but when it comes to […]
