activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

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…

cs.LG2026

ELROND: Exploring and decomposing intrinsic capabilities of diffusion models

Paweł Skierś, Tomasz Trzciński, Kamil Deja

A single text prompt passed to a diffusion model often yields a wide range of visual outputs determined solely by stochastic process, leaving users with no direct control over whic…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…