Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 07387v1 Announce Type: new Abstract: State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages.
arXiv:2606. 07271v1 Announce Type: cross Abstract: Understanding what generative models retain from training data remains challenging, with implications for copyright and privacy.
arXiv:2606. 07474v1 Announce Type: new Abstract: Unsupervised Continual Learning (UCL) aims to enable neural networks to learn sequential tasks without labels or access to past data.
arXiv:2606. 07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification.
arXiv:2508. 02039v2 Announce Type: replace Abstract: Increasing concerns for data privacy and other difficulties associated with retrieving source data for model training have created the need for source-free transfer learning, in which one only has access to pre-trained models instead of data from the original source domains.
arXiv:2604. 17948v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching.
arXiv:2606. 06554v1 Announce Type: cross Abstract: Reliable polymer identification is essential for ensuring the quality and safety of recycled plastics, yet conventional sorting and spectroscopic techniques often struggle to deliver robust discrimination.
arXiv:2606. 06972v1 Announce Type: new Abstract: Ensuring that agent behaviours are aligned with human moral values inevitably raises the problem of how to account for the plurality of moral perspectives that societies -- and even individuals -- typically adopt.
arXiv:2606. 06786v1 Announce Type: new Abstract: This paper presents a forward-looking vision for integrating the emerging multi-modal multi-task federated foundation models (M3T FedFMs) into vehicular networks, with the goal of unifying the expressive power of multi-modal multi-task foundation models (M3T FMs) with the privacy-preserving and distributed learning capabilities of federated learning (FL).
arXiv:2605. 00369v4 Announce Type: replace-cross Abstract: We study how large language models can be used to generate inventory policies in online settings with non-stationary demand.
arXiv:2603. 20990v3 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation.
arXiv:2606. 07000v1 Announce Type: new Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs).
arXiv:2606. 06833v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information.
arXiv:2606. 07196v1 Announce Type: new Abstract: Classical sparse Type-II Bayesian methods for M/EEG brain imaging support joint estimation of source and noise hyperparameters, but rely on fixed iterative update rules.
arXiv:2606. 06957v1 Announce Type: cross Abstract: Predicting outputs that are located in non-Euclidean spaces, such as probability distributions, networks, and symmetric positive-definite matrices, is becoming increasingly important in modern data analysis, particularly when inputs are high-dimensional.
arXiv:2606. 06514v1 Announce Type: new Abstract: Machine learning systems deployed in high stakes socioeconomic settings routinely display bias.
arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.
arXiv:2604. 23025v2 Announce Type: replace-cross Abstract: Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actual release times, inflating accuracy and weakening real-world robustness.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
arXiv:2606. 06853v1 Announce Type: cross Abstract: The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding.