Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2603. 28956v2 Announce Type: replace-cross Abstract: The minimum-norm interpolator (MNI) framework has recently attracted considerable attention as a tool for understanding generalization in overparameterized models, such as neural networks.
arXiv:2607. 22367v1 Announce Type: new Abstract: Feature-attribution methods assign scores relating input variables to a model's output, but do not by themselves characterize how explicitly defined interaction operators compose across its intermediate layers.
arXiv:2607. 21623v1 Announce Type: new Abstract: We present EaaS, a cloud-native reference architecture that operationalizes AI evaluation methods as six stateless Kubernetes microservices: conformal prediction with finite-sample-corrected Adaptive Prediction Sets, calibration assessment, drift detection via RFF-approximated Maximum Mean Discrepancy, fairness monitoring with bootstrap confidence intervals, a DAG-based pipeline orchestrator, and a result storage API.
arXiv:2607. 18292v2 Announce Type: replace Abstract: As language models scale, answers start truer but degrade faster: scaling buys capability but erodes reliability.
arXiv:2601. 04268v3 Announce Type: replace Abstract: Weather and climate models rely on parametrisations to represent unresolved sub-grid processes.
arXiv:2607. 21842v1 Announce Type: cross Abstract: Research on political polarization on social media depends on the ability to reliably measure partisanship in user-generated content.
arXiv:2607. 21839v1 Announce Type: cross Abstract: Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data.
arXiv:2607. 22264v1 Announce Type: new Abstract: Autoregressive foundation models trained on tokenized electronic health records (EHRs) can support zero-shot clinical prediction, yet most operate on structured event codes alone, and do not incorporate multiple modalities in a principled way.
arXiv:2607. 22516v1 Announce Type: cross Abstract: A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data.
arXiv:2605. 11017v2 Announce Type: replace Abstract: Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and clinical dosing.
arXiv:2503. 07869v4 Announce Type: replace Abstract: Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.
arXiv:2505. 00473v2 Announce Type: replace Abstract: We explore the promising performance of a transformer model in predicting outputs of parametric dynamical systems with external time-varying input signals.
arXiv:2607. 22508v1 Announce Type: new Abstract: Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks.
arXiv:2607. 22514v1 Announce Type: new Abstract: Dysphagia is a debilitating late effect of head and neck cancer (HNC) treatment, yet timely identification of at-risk patients remains challenging in survivorship care.
arXiv:2607. 22518v1 Announce Type: cross Abstract: In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems.
arXiv:2607. 21804v1 Announce Type: cross Abstract: Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model.
arXiv:2607. 21646v1 Announce Type: new Abstract: Ensuring safety in reinforcement learning under nonstationarity requires determining whether a learning system can safely adapt to forecasted environmental change within the required recovery horizon.
arXiv:2604. 16763v3 Announce Type: replace Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goals of care, and mental status are documented in free-text notes but absent from structured data.
arXiv:2601. 12311v2 Announce Type: replace-cross Abstract: The emergence of 6G-enabled vehicular metaverses enables Autonomous Vehicles (AVs) to operate across physical and virtual spaces through space-air-ground-sea integrated networks.
arXiv:2607. 21660v1 Announce Type: cross Abstract: Artificial intelligence (AI) is accelerating materials prediction and design by enabling efficient exploration of chemical and structural spaces, with particular promise for novel materials discovery.