About me

I research machine learning methods, focusing on generative models for protein design, scalable distributed training, optimized inference, and benchmarking.

I am a ML Research Engineer at Absci, working on generative models for antibody design. I hold a Master’s degree in Advanced Computer Science from the University of Cambridge, where I worked on diffusion models under the supervision of Pietro Liò and José Miguel Hernández-Lobato. Before my Master’s, I was a Software Engineer at Morgan Stanley.

An up-to-date list of my publications is available below and on my Google Scholar.

Publications

• Origin-1: a generative AI platform for de novo antibody design against novel epitopes.
  Simon Levine*, Jonathan Edward King*, Jacob Stern*, David Grayson*, Raymond Wang*, Rui Yin*, Umberto Lupo*, Paulina Kulytė*, Ryan Matthew Brand*, Tristan Bertin*, et al. bioRxiv (2026). [pdf]

• Improving Antibody Design with Force-Guided Sampling in Diffusion Models.
  Paulina Kulytė, Francisco Vargas, Simon Valentin Mathis, Yu Guang Wang, José Miguel Hernández-Lobato, Pietro Liò. NeurIPS 2024 Workshop on Machine Learning in Structural Biology (2024). [pdf]

• Metric Learning for Clifford Group Equivariant Neural Networks.
  Paulina Kulytė*, Riccardo Ali*, Haitz Sáez de Ocáriz Borde, Pietro Liò. ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling (2024). [pdf]