Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 12864v1 Announce Type: cross Abstract: Public blockchain data enables large-scale DeFi-related analysis, but many existing approaches are application-specific, difficult to scale, or hard to interpret.
arXiv:2608. 13087v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every instance.
arXiv:2608. 13450v1 Announce Type: cross Abstract: Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking, or other control decisions.
arXiv:2605. 08519v2 Announce Type: replace Abstract: Learning from scarce labeled data with a larger pool of unlabeled samples, known as semi-supervised few-shot learning (SS-FSL), remains critical for applications involving tabular data in domains like medicine, finance, and science.
arXiv:2608. 12962v1 Announce Type: new Abstract: Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models.
arXiv:2608. 12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only.
arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.
arXiv:2608. 13039v1 Announce Type: new Abstract: The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand forecasting in intelligent control of District Heating Systems, with motivation to facilitate their interpretability and trustworthiness, hence addressing the challenges related to adherence to communal standards, customer satisfaction and liability risks.
arXiv:2608. 12912v1 Announce Type: new Abstract: This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods.
arXiv:2608. 12419v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable breakthroughs across various applications.
arXiv:2608. 13136v1 Announce Type: cross Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention.
arXiv:2607. 27995v2 Announce Type: replace-cross Abstract: Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency.
arXiv:2602. 05379v2 Announce Type: replace-cross Abstract: Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data to improve sample efficiency and accelerate policy optimization.
arXiv:2510. 15076v2 Announce Type: replace Abstract: The $\ell_p$-norm objectives for correlation clustering present a fundamental trade-off between minimizing total disagreements (the $\ell_1$-norm) and ensuring fairness to individual nodes (the $\ell_\infty$-norm).
arXiv:2603. 19703v2 Announce Type: replace-cross Abstract: Estimating covariance matrices is fundamental to a wide range of statistical applications.
arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.
arXiv:2608. 13256v1 Announce Type: cross Abstract: As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical.
arXiv:2608. 12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success.
arXiv:2608. 13029v1 Announce Type: cross Abstract: The field of bioinformatics struggles with legacy code - old code that is commonly used but may no longer have a maintainer, or may be written in an now-unfamiliar language (e.
arXiv:2608. 12843v1 Announce Type: cross Abstract: Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language descriptions.