> |

hello 🇵🇱! a bit about me:

phd student / ml researcher @ WUT and IDEAS
i love diffusion models ❤️
my goal is to better understand and use the representations within generative models
topics i'm currently excited about: activation steering, representational alignment & world models

News

Feb. 2026

🇧🇷 two papers accepted @ ICLR 2026: There and Back Again (main track) and TADA (re-align workshop)!
see you in Rio!

Oct. 2025

🎓 started my PhD @ Warsaw University of Technology, co-advised by Tomasz Trzciński and Joost van de Weijer within the ELLIS phd program!

Jun. 2025

🧠 joined IDEAS Research Institute as an ai researcher in the generative ai team!

Jan. 2025

🇸🇬 two papers accepted @ ICLR 2025: Precise Parameter Localization for Textual Generation (main track) and Low-Rank Continual Adaptation (scope workshop)!

Recent Work

TADA! Tuning Audio Diffusion Models through Activation Steering

We show that various musical concepts are controlled by subset of layers in audio diffusion models and steer activations within those layers for controllable audio generation.

There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models

Noise approximations produced with inversion methods exhibit input image patterns. We find the root cause and provide simple fix, improving inversion-based image editing, interpolation and style transfer.