1 citations · 2 across the 13 of their papers we have counts for
16 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…
Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models
Jonas Kneifl, Jakub Skalski, Bartłomiej Twardowski +1
Video generation models produce strikingly realistic sequences and are increasingly proposed as world models, yet recent benchmarks reveal pronounced deficits in their physical rea…
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
Katarzyna Zaleska, Łukasz Popek, Monika Wysoczańska +1
Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling prompts that are not fully descri…
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…
TADA! Tuning Audio Diffusion Models through Activation Steering
Łukasz Staniszewski, Katarzyna Zaleska, Mateusz Modrzejewski +1
Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remains challenging, as their internal mech…
Membership and Dataset Inference Attacks on Large Audio Generative Models
Jakub Proboszcz, Paweł Kochanski, Karol Korszun +5
Generative audio models, based on diffusion and autoregressive architectures, have advanced rapidly in both quality and expressiveness. This progress, however, raises pressing copy…
ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts
Patryk Będkowski, Jan Dubiński, Filip Szatkowski +3
Simulating detector responses is a crucial part of understanding the inner workings of particle collisions in the Large Hadron Collider at CERN. Such simulations are currently perf…
Precise Parameter Localization for Textual Generation in Diffusion Models
Łukasz Staniszewski, Bartosz Cywiński, Franziska Boenisch +2
Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less th…
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
Bartosz Cywiński, Kamil Deja
Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches o…
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…
Low-Rank Continual Personalization of Diffusion Models
Łukasz Staniszewski, Katarzyna Zaleska, Kamil Deja
Recent personalization methods for diffusion models, such as Dreambooth and LoRA, allow fine-tuning pre-trained models to generate new concepts. However, applying these techniques…
GUIDE: Guidance-based Incremental Learning with Diffusion Models
Bartosz Cywiński, Kamil Deja, Tomasz Trzciński +2
We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastro…
Adapt & Align: Continual Learning with Generative Models Latent Space Alignment
Kamil Deja, Bartosz Cywiński, Jan Rybarczyk +1
In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from ab…
Bayesian Flow Networks in Continual Learning
Mateusz Pyla, Kamil Deja, Bartłomiej Twardowski +1
Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type. The…
Automatic Evaluation of Speaker Similarity
Deja Kamil, Sanchez Ariadna, Roth Julian +1
We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vas…