Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2603. 12828v2 Announce Type: replace-cross Abstract: This paper addresses a missing capability in infrastructure resilience: turning fast, global AI weather forecasts into asset-scale, actionable risk intelligence.
arXiv:2608. 01599v1 Announce Type: new Abstract: Volatility forecasts are commonly evaluated with aggregate accuracy metrics such as RMSE and MAE, but these metrics can hide conditional failures that matter for risk management.
arXiv:2608. 00097v1 Announce Type: cross Abstract: Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local measurements.
arXiv:2608. 02595v1 Announce Type: new Abstract: Language models are playing an increasingly important role in laboratory science, performing tasks such as experiment planning, execution, and post-hoc analysis.
arXiv:2511. 19849v2 Announce Type: replace-cross Abstract: Recurrence objectives, where a target region must be visited infinitely often, are a fundamental class of specifications for Markov decision processes (MDPs) and form the core of $\omega$-regular and linear temporal logic (LTL) objectives.
arXiv:2608. 00320v1 Announce Type: new Abstract: Autonomous spacecraft swarms must plan fuel-efficient, collision-free maneuvers in increasingly congested orbits, yet classical trajectory optimization scales poorly as pairwise safety constraints multiply with swarm size, and learning-based planners rarely transfer across swarm sizes or debris densities.
arXiv:2608. 00877v1 Announce Type: new Abstract: Remote-sensing multimodal large language models (MLLMs) often assert facts that imagery cannot establish, such as a facility's identity or function.
arXiv:2608. 02332v1 Announce Type: new Abstract: In offline reinforcement learning (RL), the distribution shift between behavioral data and the learned policy can lead to erroneous \emph{Q}-value estimation, thereby misguiding the direction of policy optimization.
arXiv:2605. 27681v2 Announce Type: replace-cross Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences.
arXiv:2602. 01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs).
arXiv:2603. 07475v4 Announce Type: replace-cross Abstract: Autoregressive (AR) language models build representations incrementally via left-to-right prediction, while diffusion language models (dLLMs) are trained through full-sequence denoising.
arXiv:2608. 00419v1 Announce Type: new Abstract: Large language models deployed in real-time, regulated settings face knowledge staleness, catastrophic forgetting, hallucination, and weak feedback loops.
arXiv:2511. 11686v4 Announce Type: replace Abstract: Speech enhancement (SE) requires high-fidelity reconstruction of clean speech that preserves linguistic and paralinguistic cues while maintaining high perceptual quality.
arXiv:2603. 18540v2 Announce Type: replace Abstract: The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge devices.
arXiv:2608. 01585v1 Announce Type: cross Abstract: Language model benchmarking is a difficult task.
arXiv:2608. 02509v1 Announce Type: cross Abstract: Sequential decision-making in real-world applications often involves uncertainty about the environment's model.
arXiv:2605. 00762v2 Announce Type: replace Abstract: We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected set.
arXiv:2608. 02238v1 Announce Type: cross Abstract: Ensuring trust in AI systems is essential for the safe and ethical integration of machine learning systems into high-stakes domains such as digital health.
arXiv:2506. 22423v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control.
arXiv:2602. 21429v3 Announce Type: replace Abstract: Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions.