6 papers
Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk +2
Diffusion models generate realistic images but often fail on visual reasoning tasks, such as filling in a Sudoku or drawing the path through a maze. When a discrete symbolic repres…
Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models
Muhammad Atif Butt, Paweł Skierś, Joost Van De Weijer +1
Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear directions in activation space…
ELROND: Exploring and decomposing intrinsic capabilities of diffusion models
Paweł Skierś, Tomasz Trzciński, Emilia Kaczmarczyk +1
A single text prompt passed to a diffusion model yields a wide range of visual outputs determined solely by a stochastic process, leaving users with no direct control over which se…
Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image Generation
Joanna Kaleta, Paweł Skierś, Jan Dubiński +2
We introduce Mediffusion -- a new method for semi-supervised learning with explainable classification based on a joint diffusion model. The medical imaging domain faces unique chal…
Joint Diffusion models in Continual Learning
Paweł Skierś, Kamil Deja
In this work, we introduce JDCL - a new method for continual learning with generative rehearsal based on joint diffusion models. Neural networks suffer from catastrophic forgetting…
Symbotunes: unified hub for symbolic music generative models
Paweł Skierś, Maksymilian Łazarski, Michał Kopeć +1
Implementations of popular symbolic music generative models often differ significantly in terms of the libraries utilized and overall project structure. Therefore, directly compari…