Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2507. 03423v2 Announce Type: replace-cross Abstract: Developing algorithms for real-life problems that perform well in practice depends on the availability of realistic data for testing.
arXiv:2607. 08234v1 Announce Type: cross Abstract: Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes.
arXiv:2607. 07775v1 Announce Type: new Abstract: The human body is at the center of a growing family of technologies designed to tightly and persistently couple biological and digital systems.
arXiv:2607. 08561v1 Announce Type: new Abstract: A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks.
arXiv:2603. 19186v3 Announce Type: replace Abstract: Randomized controlled trials (RCTs) are the gold standard for estimating treatment effects, yet they are often underpowered for detecting effect heterogeneity.
arXiv:2603. 23667v2 Announce Type: replace-cross Abstract: We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions.
arXiv:2605. 21917v2 Announce Type: replace-cross Abstract: Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support.
arXiv:2607. 08659v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information.
arXiv:2607. 08375v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving.
arXiv:2604. 11530v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information.
arXiv:2607. 08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one.
arXiv:2607. 07761v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care.
arXiv:2607. 08545v1 Announce Type: cross Abstract: End-to-end neural audio models achieve high-fidelity compression and generation.
arXiv:2607. 08409v1 Announce Type: cross Abstract: LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic text-to-speech (TTS) an attractive substitute.
arXiv:2602. 18396v2 Announce Type: replace Abstract: We propose PRISM-FCP (Partial shaRing and robust calIbration with Statistical Margins for Federated Conformal Prediction), a communication-efficient Byzantine-robust federated conformal prediction framework that uses partial model sharing to mitigate stochastic model-poisoning attacks during training and histogram-based filtering to mitigate adversarial calibration submissions.
arXiv:2510. 12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide.
arXiv:2607. 07918v1 Announce Type: cross Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives.
arXiv:2602. 04718v2 Announce Type: replace-cross Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activation space.
arXiv:2607. 07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them.
arXiv:2607. 08711v1 Announce Type: cross Abstract: Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards.