3 accepted papers
In this paper, we propose FreqTS, a novel Frequency-Aware Token Selection approach for accelerating diffusion models without requiring retraining. Diffusion models have gained significant attention in the field of image synthesis due to their impressive generative capabilities. However, these models…
Large Multimodal Models (LMMs) are increasingly essential in various real-time applications, yet their substantial parameter counts and complex architectures pose significant challenges. Traditional global compression methods often rely on trial-and-error experimentation, leading to inefficiencies.…
Existing feature distillation methods commonly adopt the One-to-one Representation Matching between any pre-selected teacher-student layer pair. In this paper, we present $N$-to-$O$ne $R$epresentation $M$atching (NORM), a new two-stage knowledge distillation method, which relies on a simpleFeature T…