Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605. 20247v2 Announce Type: replace-cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).
arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.
arXiv:2608. 05995v1 Announce Type: new Abstract: Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential.
arXiv:2608. 05157v1 Announce Type: cross Abstract: Double blind peer review serves as the scientific community primary defense against status and affiliation bias.
arXiv:2608. 05737v1 Announce Type: cross Abstract: Local Differential Privacy (LDP) provides strong privacy guarantees for collecting numerical data.
arXiv:2608. 02616v2 Announce Type: replace-cross Abstract: We present what is, to our knowledge, the first systematic evaluation of OpenAI's Privacy Filter (OPF), a 1.
arXiv:2608. 06250v1 Announce Type: cross Abstract: In overparameterised classification, training data can be linearly separable even when the underlying distribution is not.
arXiv:2605. 23971v2 Announce Type: replace-cross Abstract: This work presents a physics-guided machine-learning framework for carbon monoxide concentration inference from experimentally measured resistance transients of a mixed-phase SnO-SnO$_2$ material gas sensor exhibiting temperature-dependent p-n switching behavior.
arXiv:2608. 05265v1 Announce Type: new Abstract: Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in recently burned areas.
arXiv:2608. 05892v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly nonlinear problems.
arXiv:2608. 06246v1 Announce Type: new Abstract: Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning.
arXiv:2608. 06353v1 Announce Type: cross Abstract: We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent.
arXiv:2608. 05656v1 Announce Type: cross Abstract: Safety risks of AI are becoming increasingly evident in human interactions with AI technologies.
arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).
arXiv:2608. 06206v1 Announce Type: cross Abstract: Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscalibration, while exact distribution-free conditional coverage is finite-sample unattainable.
arXiv:2510. 22021v3 Announce Type: replace Abstract: Safety-critical applications of machine learning require uncertainty estimates that support reliable worst-case analysis.
arXiv:2604. 28065v2 Announce Type: replace-cross Abstract: Although intersections are the most complex parts of the roadway network, pedestrian crashes at non-intersection locations are disproportionately frequent, highlighting a serious traffic safety concern.
arXiv:2608. 06179v1 Announce Type: new Abstract: Preference optimisation has proven effective for improving large language models but typically relies on costly human preference annotations.
Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences.
Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation. Mixture-of-Recursions (MoR) improves efficiency through adaptive token-choice or expert-choice routing.