activity
20242026
collaborators

5 papers

cs.CV2026

From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation

Dawid Malarz, Filip Manjak, Maciej Zięba +2

The rapid progress of text-to-image diffusion models raises significant concerns regarding the unauthorized reproduction of trademarked content. While prior work targets general co…

cs.CV2025

UnGuide: Learning to Forget with LoRA-Guided Diffusion Models

Agnieszka Polowczyk, Alicja Polowczyk, Dawid Malarz +4

Recent advances in large-scale text-to-image diffusion models have heightened concerns about their potential misuse, especially in generating harmful or misleading content. This un…

cs.LG2025

PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models

Tadeusz Dziarmaga, Marcin KÄ dziołka, Artur Kasymov +1

Deep generative models (DGMs) have caused a paradigm shift in the field of machine learning, yielding noteworthy advancements in domains such as image synthesis, natural language p…

cs.CV2025

Classifier-free Guidance with Adaptive Scaling

Dawid Malarz, Artur Kasymov, Maciej Zięba +2

Classifier-free guidance (CFG) is an essential mechanism in contemporary text-driven diffusion models. In practice, in controlling the impact of guidance we can see the trade-off b…

cs.CV2024

AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models

Artur Kasymov, Marcin Sendera, Michał Stypułkowski +2

Low-rank adaptation (LoRA) is a fine-tuning technique that can be applied to conditional generative diffusion models. LoRA utilizes a small number of context examples to adapt the…