Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.00365v1 Announce Type: new Abstract: Recent advances in distillation and flow-map models have enabled deterministic one- or few-step genera…
arXiv:2610.00363v1 Announce Type: new Abstract: Ensuring safe and reliable operation of modern railway systems increasingly relies on data-driven moni…
arXiv:2610.00346v1 Announce Type: new Abstract: Software that hands branching decisions to a model needs a declared option and a probability it can th…
arXiv:2610.00332v1 Announce Type: new Abstract: Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a centr…
arXiv:2610.00329v1 Announce Type: new Abstract: Selective state space models (SSMs), such as Mamba, S4D, and LRU, are bounded by transition matrix com…
arXiv:2610.00325v1 Announce Type: new Abstract: Continuous policy optimization may spread an update across many states, even when deployment permits o…
arXiv:2610.00284v1 Announce Type: new Abstract: The partial area under the receiver operating characteristic curve (pAUC) is an important performance…
arXiv:2610.00280v1 Announce Type: new Abstract: A world model learns to forecast how a physical system evolves from recorded trajectories, yet the sys…
arXiv:2610.00277v1 Announce Type: new Abstract: Federated multimodal graph foundation models (GFMs) aim to adapt pretrained multimodal models to decen…
arXiv:2610.00268v1 Announce Type: new Abstract: Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, whil…
arXiv:2610.00265v1 Announce Type: new Abstract: Large Language Bayes (LLB) answers an informal modelling question by sampling candidate probabilistic…
arXiv:2610.00257v1 Announce Type: new Abstract: In standard transformer attention, a source token sends the same value vector to every receiver. The q…
arXiv:2610.00256v1 Announce Type: new Abstract: External verification can correct individual outputs while leaving a self-reinforcing population in th…
arXiv:2610.00254v1 Announce Type: new Abstract: We characterize the regret attainable in online convex optimization when access to the feasible set is…
arXiv:2610.00251v1 Announce Type: new Abstract: Memorization audits of generative models read similarity scores against thresholds, with no null distr…
arXiv:2610.00239v1 Announce Type: new Abstract: Model failover restores availability, but changes which financial institutions share decision errors.…
arXiv:2610.00236v1 Announce Type: new Abstract: Few-shot anomaly detectors are judged by ranking metrics, yet deployment requires an alarm threshold w…
arXiv:2610.00232v1 Announce Type: new Abstract: Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on t…
arXiv:2610.00221v1 Announce Type: new Abstract: What kind of data does a model need in order to learn? Coreset selection makes this question concrete:…
arXiv:2610.00209v1 Announce Type: new Abstract: Reliable recovery of missing measurements is important for monitoring and analysis in energy time-seri…