Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 19935v1 Announce Type: new Abstract: Humanoid robots require co-speech motions that are not only expressive and speech-aligned, but also physically executable under embodiment constraints.
arXiv:2606. 20376v1 Announce Type: cross Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving.
arXiv:2606. 19658v1 Announce Type: new Abstract: Implicit feedback is widely used in recommender systems due to its accessibility and generality, yet it usually presents noisy samples (e.
arXiv:2606. 20045v1 Announce Type: cross Abstract: UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly.
arXiv:2606.
arXiv:2606. 19643v1 Announce Type: cross Abstract: Motivated by the privacy, sensitivity and sharing limitations of health data, we present a comprehensive pipeline for inference of Bayesian mixture models within a federated learning setting, i.
arXiv:2606. 20482v1 Announce Type: cross Abstract: To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text.
arXiv:2602. 05533v3 Announce Type: replace Abstract: We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one.
arXiv:2606. 20037v1 Announce Type: new Abstract: Alzheimer's disease (AD) is an irreversible neurodegenerative disorder and a leading cause of death worldwide.
arXiv:2606. 20292v1 Announce Type: new Abstract: The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains.
arXiv:2606. 19734v1 Announce Type: new Abstract: Federated bilevel optimization is widely used for nested learning problems across distributed clients, such as federated hyperparameter tuning and meta-learning under privacy and communication constraints.
arXiv:2606. 19542v1 Announce Type: new Abstract: Large language models are commonly aligned through supervised fine-tuning, yet little is known about how their internal representations evolve during this process.
arXiv:2503. 17386v2 Announce Type: replace-cross Abstract: Crashworthiness is a key performance measure in the design of safety-critical vehicle panel components such as B-pillars.
arXiv:2606. 20523v1 Announce Type: cross Abstract: Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited.
arXiv:2606. 20174v1 Announce Type: new Abstract: Cell-free DNA (cfDNA) is a promising avenue for non-invasive multicancer early detection (MCED), in that, it can enable multiple cancer detection simultaneously from a single blood draw, with particular sensitivity to cancers that currently lack established screening programs.
arXiv:2606. 20467v1 Announce Type: new Abstract: Mathematicians understand a PDE solution through mathematical structures rather than tables of computed values.
arXiv:2606. 19382v1 Announce Type: cross Abstract: While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.
arXiv:2606. 20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized.
arXiv:2509. 25148v2 Announce Type: replace Abstract: Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback.
arXiv:2606. 20470v1 Announce Type: cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.