arXiv:2502.01755v4 Announce Type: replace Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) optimize federated training by reducing computational and communication costs. We propose RoLoRA, a federated framework using alternating optimization to fine-tune LoRA adapters. Our approach emphasizes the importance…
arXiv:2505.17370v4 Announce Type: replace Abstract: Long-term time-series forecasting (LTSF) models are often presented as general-purpose solutions that can be applied across domains, implicitly assuming that all data is pointwise predictable. Using chaotic systems such as Lorenz-63 as a case study,…
arXiv:2510.11011v1 Announce Type: cross Abstract: Data prefetching–loading data into the cache before it is requested–is essential for reducing I/O overhead and improving database performance. While traditional prefetchers focus on sequential patterns, recent learning-based approaches, especially those leveraging data semantics, achieve…
arXiv:2510.11676v1 Announce Type: cross Abstract: We study convex composite optimization problems, where the objective function is given by the sum of a prox-friendly function and a convex function whose subgradients are estimated under heavy-tailed noise. Existing work often employs gradient…
arXiv:2510.09664v1 Announce Type: new Abstract: Recently, deep supervised cross-modal hashing methods have achieve compelling success by learning semantic information in a self-supervised way. However, they still suffer from the key limitation that the multi-label semantic extraction process fail to explicitly…
arXiv:2507.01613v2 Announce Type: replace-cross Abstract: Paired comparison data, where users evaluate items in pairs, play a central role in ranking and preference learning tasks. While ordinal comparison data intuitively offer richer information than binary comparisons, this paper challenges that conventional…
arXiv:2510.09660v1 Announce Type: new Abstract: Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biases into the training and sampling of diffusion models to better…
arXiv:2510.09662v1 Announce Type: new Abstract: Electrochemical impedance spectroscopy (EIS) data is typically modeled using an equivalent circuit model (ECM), with parameters obtained by minimizing a loss function via nonlinear least squares fitting. This paper introduces two new loss functions, log-B…
arXiv:2510.09659v1 Announce Type: new Abstract: NOvA is a long-baseline neutrino oscillation experiment that detects neutrino particles from the NuMI beam at Fermilab. Before data from this experiment can be used in analyses, raw hits in the detector must be matched…
arXiv:2510.09658v1 Announce Type: new Abstract: When a new release of a foundation model is published, practitioners typically need to repeat full fine-tuning, even if the same task has already been solved in the previous version. A promising alternative is to…
