Search: “safety”

arXiv:2605.31204v1 Announce Type: new Abstract: Accurate weather forecasts are essential across various domains and are safety-critical in extreme weather conditions. Compared to simulation-based fore

arXiv:2605.30854v1 Announce Type: cross Abstract: Language models fine-tuned with reinforcement learning typically optimize for task reward, ignoring multi-agent strategic structure. Because these age

arXiv:2605.30837v1 Announce Type: cross Abstract: Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still

arXiv:2605.29901v1 Announce Type: cross Abstract: Large language models (LLMs) can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using me

arXiv:2605.29827v1 Announce Type: new Abstract: Medical image analysis models can exhibit performance disparities across patient subgroups, threatening clinical safety and fairness. Existing methods t

arXiv:2605.28848v1 Announce Type: cross Abstract: Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all ch

arXiv:2605.29473v1 Announce Type: cross Abstract: Language models are increasingly being deployed for conversational support in informal caregiving contexts, where interactions often extend beyond inf

arXiv:2605.29114v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between

arXiv:2403.09441v2 Announce Type: replace Abstract: As deep learning (DL) models are increasingly being integrated into our everyday lives, ensuring their safety by making them robust against adversar

An experimental gene-editing therapy called VERVE-102 aims to lower bad cholesterol long-term after a single infusion and showed promising results in a Phase I safety trial published in the New Englan

arXiv:2605.27796v1 Announce Type: cross Abstract: Ultrasound is widely used in obstetric care due to its safety, accessibility, and real-time imaging. However, interpretation remains operator-dependen

Mistral AI announced its participation in or perspective on the AI Now Summit 2026, likely discussing developments in AI safety, ethics, or industry trends relevant to the conference. The announcement

arXiv:2605.28025v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to provide public-facing health information, yet existing safety evaluations overlook whether respons

arXiv:2605.26438v1 Announce Type: cross Abstract: Large language models can recognize when they are being evaluated (evaluation awareness) and behave differently because of that, which undermines the

arXiv:2511.20586v4 Announce Type: replace Abstract: Trustworthiness has become a key requirement for the deployment of artificial intelligence systems in safety-critical applications. Conventional eva

arXiv:2605.26348v1 Announce Type: new Abstract: Mobile robots can fail before they collide: a velocity that is safe now may commit the robot to a passage that moving obstacles will soon close. We stud

arXiv:2605.26463v1 Announce Type: cross Abstract: Data consistency between unstructured clinical notes and structured tables in Electronic Health Records (EHRs) is essential for patient safety and cli

arXiv:2605.24583v1 Announce Type: cross Abstract: We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qw

arXiv:2605.24503v1 Announce Type: cross Abstract: As AI-powered compliance monitoring becomes increasingly important in public governance and industrial safety, the ability to provide verifiable evide

arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cos

arXiv:2605.26047v1 Announce Type: new Abstract: AI coding scaffolds like Claude Code and Codex use extit{retrying}: blocking actions flagged as risky and continuing the trajectory. We study retrying f

arXiv:2605.25420v1 Announce Type: cross Abstract: Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed g

arXiv:2605.23055v1 Announce Type: cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet t

arXiv:2605.22826v1 Announce Type: cross Abstract: Quantifying the deceptive potential of Large Language Models (LLMs) is critical for AI safety, yet difficult to achieve in uncontrolled environments.

arXiv:2605.22437v1 Announce Type: cross Abstract: Vision processing units and other commercial neural-network inference accelerators are increasingly deployed in safety-relevant edge applications, but

arXiv:2605.21500v1 Announce Type: cross Abstract: Event cameras have emerged as a high-bandwidth, low-latency sensing modality for safety-critical perception in automated driving systems (ADS), offeri

arXiv:2605.20704v1 Announce Type: cross Abstract: Autonomous AI agents that spawn sub-agent swarms create a safety gap: existing credential revocation mechanisms, OAuth~2.0 introspection, OCSP, and W3

arXiv:2605.20742v1 Announce Type: new Abstract: With the rapid proliferation of electric vehicles, the safety and reliability of lithium-ion batteries have become critical concerns. Effective anomaly

arXiv:2605.20956v1 Announce Type: new Abstract: Conformal triage converts predictive scores into deployment actions that either release a case, flag it for urgent attention, or defer it to human revie

arXiv:2605.21309v1 Announce Type: new Abstract: Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental repre

arXiv:2605.19578v1 Announce Type: cross Abstract: RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing m

Minnesota became the first state to ban prediction markets when Governor Tim Walz signed a public safety bill into law, making operation, promotion, or advertising of platforms like Kalshi and Polymar

arXiv:2605.19744v1 Announce Type: new Abstract: Detecting anomalies in traffic scenes is crucial for ensuring safety in autonomous driving, yet collecting representative anomalous data remains challen

arXiv:2605.19377v1 Announce Type: cross Abstract: As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners increasi

OpenAI discusses methods for establishing content provenance—tracking the origin and history of digital content—to improve transparency and safety in AI systems. The work addresses how verifiable cont

arXiv:2510.03879v3 Announce Type: replace-cross Abstract: Translating C to memory-safe languages, like Rust, prevents critical memory safety vulnerabilities that are prevalent in legacy C software. Ev

Unity AI Gateway Guardrails is a Databricks feature designed to protect AI workloads by implementing safety measures and policy controls within the Unity Catalog framework. The tool enables organizati

arXiv:2605.16375v1 Announce Type: new Abstract: Accurate air quality prediction is essential for public health, environmental monitoring, and industrial safety. However, most existing approaches rely

arXiv:2605.17610v1 Announce Type: cross Abstract: The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deplo

arXiv:2605.16372v1 Announce Type: cross Abstract: Steering or intervening on model representations at inference time to correct predictions is essential for AI interpretability and safety, yet existin

arXiv:2605.15874v1 Announce Type: new Abstract: Industrial Water Treatment Systems (IWTS) are safety critical cyber-physical infrastructures and due to increased connectivity, these systems are expose

arXiv:2605.14413v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection is a critical component for ensuring the reliability of deep neural networks in safety-critical applications. In t

arXiv:2408.16307v3 Announce Type: replace-cross Abstract: Automatic controller tuning is attractive for robotics and mechatronic systems whose dynamics are difficult to model accurately, but direct bl

arXiv:2605.12765v1 Announce Type: new Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning

arXiv:2605.13302v1 Announce Type: new Abstract: This paper extends safety guarantees for multi-task Bayesian optimization with uncertain correlation matrices from intrinsic co-reginalization models to

arXiv:2510.15297v4 Announce Type: replace-cross Abstract: We introduce VERA-MH (Validation of Ethical and Responsible AI in Mental Health), an automated evaluation of the safety of AI chatbots used in