Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2601.06641v4 Announce Type: replace Abstract: Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard...
arXiv:2602.04093v3 Announce Type: replace Abstract: Concept-based Models (CMs) enhance interpretability in deep learning by grounding predictions in human-understandable concepts. However, concept an...
arXiv:2605.10822v2 Announce Type: replace Abstract: Cyber-physical system (CPS) forecasting models depend on sensor streams with noisy, biased, missing, or temporally misaligned readings, yet standar...
arXiv:2605.21849v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainer...
arXiv:2606.23496v2 Announce Type: replace Abstract: Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpi...
arXiv:2610.38970v2 Announce Type: replace Abstract: Current and emerging mobile networks face increasing privacy, scalability, and performance challenges as distributed learning becomes essential for...
arXiv:2611.02170v2 Announce Type: replace Abstract: Diffusion models are often inaccurate in critical, data-sparse regions of the target distribution. Sampling from restrained distributions, biased d...
arXiv:2611.03623v2 Announce Type: replace Abstract: Non-invasive brain-to-text interfaces offer alternative communication pathways for people with communication disabilities. However, sentence-level...
arXiv:2611.04501v2 Announce Type: replace Abstract: Machine unlearning aims to erase the influence of a designated forget set from a trained model while preserving strong utility on the retain set. A...
arXiv:2611.04667v2 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative training of machine learning models across distributed clients while preserving data privacy. In prac...
arXiv:2107.12636v5 Announce Type: replace-cross Abstract: Detection transformers have recently shown promising object detection results and attracted increasing attention. However, how to develop eff...
arXiv:2605.21139v4 Announce Type: replace-cross Abstract: Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While rei...
arXiv:2611.05720v1 Announce Type: new Abstract: Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use. Drawing on cognitive-bias paradi...
arXiv:2611.06384v1 Announce Type: new Abstract: Typed decision models offer structured choices, scores, and probabilities for low-cost automated evaluation. We present a controlled audit of presentat...
arXiv:2611.06402v1 Announce Type: new Abstract: QA-based text embeddings represent texts as vectors consisting of 1/0 answers to yes/no questions. Although these embeddings provide detailed informati...
arXiv:2611.06501v1 Announce Type: new Abstract: Simultaneous Speech Translation (SimulST) requires balancing translation quality and latency. While Large Language Models (LLMs) excel in offline trans...
arXiv:2611.06812v1 Announce Type: new Abstract: With the growing need for evaluating Large Language Models (LLMs) and their applications to speech, challenges persist in summarizing and evaluating co...
arXiv:2611.06839v1 Announce Type: new Abstract: Large language model (LLM) assistants increasingly help users with everyday activities that involve time-dependent constraints. However, users may not...
arXiv:2611.05730v1 Announce Type: cross Abstract: Two foundational aspects of human cognition, abstractness and gender, are typically examined as separable. Here, we find they are systematically link...
arXiv:2611.05954v1 Announce Type: cross Abstract: Pedestrians increasingly encounter robots in urban public spaces without interacting with them, but how robots change the perceived safety of a stree...