arXiv:2604.03388v1 Announce Type: new Abstract: When deploying large language models (LLMs) to safety-critical applications, uncertainty quantification (UQ) is of utmost importance to self-assess the reliability of the LLM-based decisions. However, such decisions typically suffer from overconfidence, particularly after parameter-efficient fine-tuning…
arXiv:2512.14190v3 Announce Type: replace Abstract: This paper motivates the use of random-bridges — stochastic processes conditioned to take target distributions at fixed timepoints — in the realm of generative modelling. Herein, random-bridges can act as stochastic transports between two probability…
arXiv:2604.03417v1 Announce Type: new Abstract: Network visualization has traditionally relied on heuristic metrics, such as stress, under the assumption that optimizing them leads to aesthetic and informative layouts. However, no single metric consistently produces the most effective results. A data-driven…
arXiv:2603.20189v2 Announce Type: replace Abstract: Steering large-scale swarms with only limited control updates is often needed due to communication or computational constraints, yet most learning-based approaches do not account for this and instead model instantaneous velocity fields. As a result,…
arXiv:2604.03419v1 Announce Type: new Abstract: Submodular maximization under matroid constraints is a fundamental problem in combinatorial optimization with applications in sensing, data summarization, active learning, and resource allocation. While the Sequential Greedy (SG) algorithm achieves only a $frac{1}{2}$-approximation due to…
arXiv:2311.00855v3 Announce Type: replace-cross Abstract: Human immunodeficiency virus (HIV) is a major public health concern in the United States (U.S.), with about 1.2 million people living with it and about 35,000 newly infected each year. There are considerable geographical disparities…
arXiv:2604.03427v1 Announce Type: new Abstract: State-space model (SSM) for time-series forecasting have demonstrated strong empirical performance on benchmark datasets, yet their robustness under adversarial perturbations is poorly understood. We address this gap through a control-theoretic lens, focusing on the recently…
arXiv:2604.03436v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single coherent concept…
arXiv:2602.23013v2 Announce Type: replace-cross Abstract: Detecting visual anomalies in industrial inspection often requires training with only a few normal images per category. Recent few-shot methods achieve strong results employing foundation-model features, but typically rely on memory banks, auxiliary datasets, or…
arXiv:2604.03444v1 Announce Type: new Abstract: Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention. Yet there is no consensus on whether the potential benefits of…
