Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2611.06677v1 Announce Type: new Abstract: We study the classical apple-tasting setting, a partial feedback model in which the learner observes the true label only when it predicts $1$. A combin...
arXiv:2611.06759v1 Announce Type: new Abstract: We study logistic regression for continual learning with linear predictors in a high-dimensional statistical setting. Existing theoretical work has lar...
arXiv:2611.05781v1 Announce Type: cross Abstract: Continual model updating has become a common practice in the deployment of machine learning systems. However, the dynamic training behaviors give ris...
arXiv:2611.06159v1 Announce Type: cross Abstract: We study adversarial market making with orders that remain active until execution. The maker operates on two markets: a primary market where orders a...
arXiv:2611.06342v1 Announce Type: cross Abstract: The records that could train the most useful models, such as a hospital's patient files, are often the ones an institution cannot share. We propose C...
arXiv:2508.09275v3 Announce Type: replace Abstract: Collaborative multi-agent reinforcement learning (MARL) is increasingly deployed in critical domains, yet its vulnerability to adversarial perturba...
arXiv:2602.20698v2 Announce Type: replace Abstract: Modern data systems often require aggregating information from multiple sources: some might be entirely untrustworthy, while the remaining presumab...
arXiv:2605.05436v2 Announce Type: replace-cross Abstract: Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizi...
arXiv:2611.05384v1 Announce Type: new Abstract: Generalisability is a central question for deep neural networks, including the cross-language generalisation of speaker embeddings. This study examined...
arXiv:2611.06517v1 Announce Type: new Abstract: The massive permeability of intelligent systems in every sphere of human activities have greatly enhanced clarity, ease of work, and increased general...
arXiv:2611.06806v1 Announce Type: new Abstract: Psychological harms from interactions with large language models cannot be monitored directly because they may emerge over repeated interactions and de...
arXiv:2611.06848v1 Announce Type: new Abstract: Common methods for monitoring features in large language models (LLMs) such as linear probes and sparse autoencoders (SAEs) assume that features mainta...
arXiv:2611.05403v1 Announce Type: new Abstract: In Bangladesh, much localized misinformation spreads as photocards: single-image news summaries that imitate the branding of well-known news organizati...
arXiv:2611.06046v1 Announce Type: new Abstract: In recent years, AIGC technologies are capable of generating hyper-realistic forged facial images, posing severe threats to facial security safety. To...
arXiv:2611.06415v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable progress on cross-modal reasoning tasks, yet they continue to suffer from halluci...
arXiv:2611.06844v1 Announce Type: new Abstract: A central yet under-explored question in Multimodal Large Language Models (MLLMs) is where to connect---how visual information from a hierarchical visi...
arXiv:2611.05398v1 Announce Type: cross Abstract: Colony counting is commonly used to evaluate microbial populations in food safety testing and microbiological studies. Despite its wide application,...
arXiv:2602.11499v3 Announce Type: replace Abstract: Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Op...
arXiv:2611.05723v1 Announce Type: cross Abstract: Covariate balancing is widely used for estimating causal effects in observational studies. A central challenge is determining which covariate feature...
The paper studies how epistemic uncertainty estimates can be used in different ways—either as an additional input feature or as a per‑sample confidence weight in the loss function—to improve 3D LiDAR point cloud segmentation. Experiments on four large‑scale LiDAR benchmarks (ISPRS Vaihingen, AHN3, Paris‑Lille‑3D, and Toronto‑3D) show that uncertainty‑aware models outperform a baseline ANN in mean Intersection over Union, recover minority classes, and better align prediction error with estimated uncertainty. The results suggest that uncertainty can serve multiple roles in the segmentation pipeline beyond merely boosting accuracy.