arXiv:2512.09829v1 Announce Type: cross Abstract: The massive scale of modern AI accelerators presents critical challenges to traditional fault assessment methodologies, which face prohibitive computational costs and provide poor coverage of critical failure modes. This paper introduces RIFT (Reinforcement Learning-guided Intelligent…
arXiv:2510.20690v2 Announce Type: replace-cross Abstract: Language models continue to hallucinate despite increases in parameters, compute, and data. We propose neural diversity — decorrelated parallel representations — as a principled mechanism that reduces hallucination rates at fixed parameter and data budgets.…
arXiv:2512.09678v1 Announce Type: cross Abstract: In this article, we explore the use of various matrix norms for optimizing functions of weight matrices, a crucial problem in training large language models. Moving beyond the spectral norm underlying the Muon update, we…
arXiv:2512.07873v2 Announce Type: replace Abstract: Recent studies show that using diffusion models for time series signal reconstruction holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the physiological time…
arXiv:2503.18309v4 Announce Type: replace-cross Abstract: Gaussian process state-space models (GPSSMs) offer a principled framework for learning and inference in nonlinear dynamical systems with uncertainty quantification. However, existing GPSSMs are limited by the use of multiple independent stationary Gaussian processes (GPs),…
arXiv:2506.16659v2 Announce Type: replace Abstract: Training large language models (LLMs) typically relies on adaptive optimizers such as Adam, which introduce extra operations and require significant more memory to maintain first- and second-order moments than SGD. While recent works such as…
arXiv:2510.16443v2 Announce Type: replace Abstract: This report presents the winning solution for Task 2 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The goal of the challenge was to design and…
arXiv:2512.08960v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks. Our analysis reveals that this degradation is primarily driven by antagonistic directional updates where new task…
arXiv:2512.08964v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) achieve strong performance on graph-structured data, but are notoriously vulnerable to small, carefully crafted perturbations of the graph structure. Most existing structure-based attacks rely on gradient-based heuristics or local connectivity patterns,…
arXiv:2512.08957v1 Announce Type: new Abstract: User behavior prediction at scale remains a critical challenge for online B2C platforms. Traditional approaches rely heavily on task-specific models and domain-specific feature engineering. This is time-consuming, computationally expensive, and requires domain expertise and therefore…
