arXiv:2605.00936v1 Announce Type: new Abstract: Anomaly detection and localization (ADL) is critical for maintaining reliability and availability in cloud systems. Recent ADL developments focus on metric and log data, leaving event data unexplored. To address this gap, we propose EventADL,…
arXiv:2603.05228v3 Announce Type: replace Abstract: Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypotheses a priori by modifying architectural topology to observe training dynamics. We study grokking – delayed generalization in…
arXiv:2605.00938v1 Announce Type: new Abstract: Accurate modeling of commuting flows is important for urban governance, traffic planning, and resource allocation. However, the combined influence of individual intentions, geographic constraints, and social dynamics leads to considerable heterogeneity in commuting patterns, making…
Dwai Banerjee’s new book examines the visionaries who wanted to turn India into a world power at making computers.
New measurements of a hot Jupiter and its mini-Neptune companion suggest both planets formed surprisingly far away from their host star.
arXiv:2504.20605v2 Announce Type: replace-cross Abstract: Moral stories are a time-tested vehicle for transmitting values, yet modern NLP lacks a large, structured corpus that couples coherent narratives with explicit ethical lessons. We present TF1-EN-3M, to our knowledge the first open dataset…
arXiv:2601.17616v2 Announce Type: replace Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters uniformly, failing to distinguish between…
arXiv:2604.11835v2 Announce Type: replace Abstract: Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine, where electronic…
arXiv:2605.02765v1 Announce Type: cross Abstract: LLMs are increasingly used for end-user task planning, yet their black-box nature limits users’ ability to ensure reliability and control. While recent systems incorporate verification techniques, it remains unclear how users can effectively apply such…
arXiv:2507.15774v2 Announce Type: replace Abstract: While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time-series forecasting task. Our hypothesis is that models should learn a direct link…
