arXiv:2509.18093v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become a standard technique for parameter-efficient fine-tuning of large language models, enabling large libraries of LoRAs, each for a specific task or domain. Efficiently selecting the correct LoRA adapter for a…
arXiv:2509.16354v1 Announce Type: new Abstract: Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and limited label-preserving augmentations. As a result, ensemble models based…
arXiv:2502.10691v3 Announce Type: replace Abstract: Out-of-distribution (OOD) detection and OOD generalization are widely studied in Deep Neural Networks (DNNs), yet their relationship remains poorly understood. We empirically show that the degree of Neural Collapse (NC) in a network layer is…
arXiv:2509.16357v1 Announce Type: new Abstract: Therapeutic antibody candidates often require extensive engineering to improve key functional and developability properties before clinical development. This can be achieved through iterative design, where starting molecules are optimized over several rounds of in vitro…
arXiv:2506.17475v2 Announce Type: replace Abstract: Low-rank pre-training and fine-tuning have recently emerged as promising techniques for reducing the computational and storage costs of large neural networks. Training low-rank parameterizations typically relies on conventional optimizers such as heavy ball momentum methods…
arXiv:2509.16379v1 Announce Type: new Abstract: We introduce EMPEROR (Efficient Moment-Preserving Representation of Distributions), a mathematically rigorous and computationally efficient framework for representing high-dimensional probability measures arising in neural network representations. Unlike heuristic global pooling operations, EMPEROR encodes a feature distribution…
arXiv:2509.16391v1 Announce Type: new Abstract: Machine unlearning (MU) aims to remove the influence of specific “forget” data from a trained model while preserving its knowledge of the remaining “retain” data. Existing MU methods based on label manipulation or model weight…
arXiv:2501.08406v2 Announce Type: replace-cross Abstract: Optimization models have been applied to solve a wide variety of decision-making problems. These models are usually developed by optimization experts but are used by practitioners without optimization expertise in various application domains. As a…
arXiv:2509.16393v1 Announce Type: new Abstract: This paper studies Federated Learning (FL) for binary classification of volatile financial market trends. Using a shared Long Short-Term Memory (LSTM) classifier, we compare three scenarios: (i) a centralized model trained on the union of…
arXiv:2506.00455v4 Announce Type: replace-cross Abstract: Navigation by scent is a capability in robotic systems that is rising in demand. However, current methods often suffer from ambiguities, particularly when robots misattribute odours to incorrect objects due to limitations in olfactory datasets…
