4 papers
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs
Seyed Alireza Molavi, Zhan Su, Yan Hu +3
Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original training data cannot be shared.…
Attribution Upsampling should Redistribute, Not Interpolate
Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat +2
Attribution methods in explainable AI rely on upsampling techniques that were designed for natural images, not saliency maps. Standard bilinear and bicubic interpolation systematic…
Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation
Guojun Liang, Najmeh Abiri, Atiye Sadat Hashemi +3
Accurate imputation is essential for the reliability and success of downstream tasks. Recently, diffusion models have attracted great attention in this field. However, these models…
Expected Grad-CAM: Towards gradient faithfulness
Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat +2
Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla grad…