most citedContinual Learning of Diffusion Models with Generative Distillation

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability

Sergi Masip, Gido M. van de Ven, Javier Ferrando +1

Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms. We introduce a mechani…

cs.LG2023★ 1 cited

Continual Learning of Diffusion Models with Generative Distillation

Sergi Masip, Pau Rodriguez, Tinne Tuytelaars +1

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computa…