Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604. 20711v2 Announce Type: replace Abstract: Artificial intelligence is increasingly deployed to synthesize large-scale public input in policy consultations and participatory processes.
arXiv:2607. 06612v1 Announce Type: cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing user privacy.
arXiv:2601. 21433v2 Announce Type: replace Abstract: Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing.
arXiv:2607. 06776v1 Announce Type: new Abstract: We introduce an efficient Bayesian deep ensemble method for predictive regression designed to enhance interpretability while maintaining competitive predictive performance and computational efficiency.
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
arXiv:2503. 15581v2 Announce Type: replace Abstract: Real-time safety assessment is critical for ensuring the reliable operation of complex dynamic systems.
arXiv:2601. 16529v4 Announce Type: replace Abstract: Large language models (LLMs) deployed in clinical decision support may acquiesce to patient requests for care that conflicts with evidence-based guidelines.
arXiv:2607. 06608v1 Announce Type: cross Abstract: We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.
arXiv:2607. 06856v1 Announce Type: cross Abstract: Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics.
arXiv:2607. 06954v1 Announce Type: new Abstract: Wearable and mobile sensing technologies have demonstrated strong potential for health inference; however, most sensor models are designed for specific disease types, limiting their transferability across different health risks.
arXiv:2607. 07156v1 Announce Type: new Abstract: Different optimizers have different update biases, but these biases are usually implicit.
arXiv:2304. 03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural language processing, and speech recognition.
arXiv:2607. 07318v1 Announce Type: cross Abstract: Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections.
arXiv:2607. 07671v1 Announce Type: new Abstract: Probabilistic circuits (PCs) can model complex joint distributions while supporting exact and efficient computation of many inference queries.
arXiv:2603. 15685v2 Announce Type: replace-cross Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive.
arXiv:2607. 07101v1 Announce Type: cross Abstract: Proprioception is fundamental to robotic manipulation, yet standard fusion methods often treat it as an isolated vector lacking explicit alignment with visual tokens.
arXiv:2607. 07196v1 Announce Type: cross Abstract: Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world, and returning a success or safety verdict.
arXiv:2607. 06603v1 Announce Type: cross Abstract: The notion of algorithmic fairness has been actively explored from various aspects of fairness, such as counterfactual fairness (CF) and group fairness (GF).
arXiv:2211. 14966v2 Announce Type: replace Abstract: Deep neural networks (DNNs) are highly vulnerable to adversarial attacks.
arXiv:2607. 06831v1 Announce Type: cross Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio.