arXiv:2502.04416v3 Announce Type: replace Abstract: Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consuming the majority of computational resources. While Mixture-of-Experts (MoE) architectures can reduce this cost through sparse activation, restructuring existing…
arXiv:2604.20985v1 Announce Type: new Abstract: In machine learning applications, privacy requirements during inference or deployment time could change constantly due to varying policies, regulations, or user experience. In this work, we aim to generate a magnitude of models to satisfy…
arXiv:2509.18629v3 Announce Type: replace Abstract: Foundation models excel across diverse tasks, but adapting them to specialized applications often requires fine-tuning, an approach that is memory and compute-intensive. Parameter-efficient fine-tuning (PEFT) methods mitigate this by updating only a small subset of…
arXiv:2601.18714v2 Announce Type: replace-cross Abstract: Localization in agricultural environments is challenging due to their unstructured nature and lack of distinctive landmarks. Although agricultural settings have been studied in the context of object classification and segmentation, the place recognition task for…
arXiv:2604.19738v2 Announce Type: replace-cross Abstract: We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on the d-dimensional sphere . We show that the asymptotic behaviour of these functionals…
arXiv:2604.20688v2 Announce Type: replace Abstract: Storm surge forecasting remains a critical challenge in mitigating the impacts of tropical cyclones on coastal regions, particularly given recent trends of rapid intensification and increasing nearshore storm activity. Traditional high fidelity numerical models such…
arXiv:2508.11354v3 Announce Type: replace-cross Abstract: Purpose: This study introduces the first adaptation of RETFound for joint optic disc (OD) and optic cup (OC) segmentation. RETFound is a well-known foundation model developed for fundus camera and optical coherence tomography images, which…
arXiv:2601.10863v3 Announce Type: replace Abstract: Traditional time series forecasting methods optimize for accuracy alone. This objective neglects temporal consistency, in other words, how consistently a model predicts the same future event as the forecast origin changes. We introduce the forecast…
arXiv:2604.20921v1 Announce Type: new Abstract: We evaluated whether a glaucoma risk assessment (GRA) model trained on All of Us national data can identify patients at high probability of glaucoma using only systemic electronic health records (EHR) at an independent institution.…
arXiv:2407.19664v3 Announce Type: replace Abstract: Previous research on selective protection for neural network components typically exploits only static vulnerability differences. Although these methods improve upon classical modular redundancy, they still incur substantial overhead for neural network workloads that are both…
