Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608.25200v2 Announce Type: replace-cross Abstract: We study learning a mixture of $k$ Plackett-Luce models from multi-way ranking responses from annotators that may represent heterogeneous und...
arXiv:2608.28840v1 Announce Type: new Abstract: Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible,...
arXiv:2608.28905v1 Announce Type: new Abstract: Generative recommenders increasingly emit semantic IDs (SIDs): each item is a short sequence of hierarchical discrete codes from a residual quantizer,...
arXiv:2608.29360v1 Announce Type: new Abstract: Spatiotemporal graphs underpin applications such as traffic forecasting, weather forecasting, and healthcare monitoring. Privacy regulations such as th...
arXiv:2608.29369v1 Announce Type: new Abstract: Spatio-temporal graphs are widely used in modeling complex dynamic processes such as temporal forecasting, molecular dynamics, and healthcare monitorin...
arXiv:2608.29428v1 Announce Type: new Abstract: Single-trial EEG analyses are often organized around events and latencies, yet EEG-based reaction-time (RT) prediction is posed as scalar regression on...
arXiv:2608.29635v1 Announce Type: new Abstract: We study unsupervised hypergraph alignment, where the goal is to infer node correspondences between two hypergraphs using only structural information,...
arXiv:2608.30597v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data oft...
arXiv:2608.30695v1 Announce Type: new Abstract: Real-world time series often exhibit irregular sampling and extended temporal horizons, requiring models to capture continuous-time dynamics across arb...
arXiv:2608.30720v1 Announce Type: new Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied...
arXiv:2608.30750v1 Announce Type: new Abstract: Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content in...
arXiv:2608.30804v1 Announce Type: new Abstract: Monitoring the health of heterogeneous industrial robot fleets is severely challenged by the multi-modal nature of their operational cycles and a persi...
arXiv:2608.30946v1 Announce Type: new Abstract: Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adapt...
arXiv:2608.30978v1 Announce Type: new Abstract: Modularity in deep neural networks has been proposed as a means of improving both interpretability and training by promoting disentangled representatio...
arXiv:2608.31079v1 Announce Type: new Abstract: Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycoph...
arXiv:2608.20118v1 Announce Type: cross Abstract: The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as l...
arXiv:2608.28778v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) rely on accurate camera-LiDAR calibration for multimodal sensor fusion. In practice, calibration can drift due to vibration...
arXiv:2608.28931v1 Announce Type: cross Abstract: Matching users to interest categories at scale is central to personalized shopping, but the task is challenging in large e-commerce platforms, where...
arXiv:2608.29097v1 Announce Type: cross Abstract: This paper studies the problem of proportionally fair clustering, where the goal is to select $k$ ``centers'' from a metric space that fairly represe...
arXiv:2608.29923v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment i...