Albert Catalan Tatjer – Machine Learning Efficiency

Albert Catalan-Tatjer

Profile Picture

I am a first year PhD student at the safety- & efficiency- aligned learning (🦭) group advised by Jonas Geiping funded by IMPRS-IS and Amazon Science Hub. I am excited about most things deep learning, especially optimization and inference efficiency. Fundamental to my research is the implementation of mathematical ideas on computer technologies. On my free time I enjoy literature, science, and sports.

I am currently working on inference for multi-agent systems, continual learning, and reasoning.

News

  • Mar 2026: Gave a talk of my work at Friday Talks Tübingen and at MILA.
  • Jan 2026: First first-author paper accepted at ICLR 🇧🇷
  • Dec 2025: Presenting a paper at a workshop at San Diego 🇺🇸
  • Sep 2025: Paper accepted at the Efficient Reasoning workshop @NeurIPS 2025.
  • Jul 2025: Started my PhD 🎉

Selected Publications

Decoding class dynamics in learning with noisy labels.

Albert Catalan-Tatjer, Bhalaji Nagarajan, Ricardo Marques, Petia Radeva. Pattern Recognition Letters 2024

CCLM: Class-conditional label noise modelling.

Albert Catalan-Tatjer, Bhalaji Nagarajan, Ricardo Marques, Petia Radeva. IbPRIA 2023 Best Paper
© Albert Catalan-Tatjer 2026 · Last updated: May 25, 2026