Search: “safety”

arXiv:2510.04773v2 Announce Type: replace Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiv

arXiv:2606.26071v1 Announce Type: new Abstract: A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But beh

arXiv:2606.24377v1 Announce Type: new Abstract: Compliant joints can embed safety and adaptability into dexterous hands, but achieving large-stroke anthropomorphic motion while maintaining joint-speci

arXiv:2606.21821v1 Announce Type: new Abstract: Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In thi

arXiv:2606.21527v1 Announce Type: cross Abstract: Robust obstacle segmentation is essential for the safety of intelligent robots, where LiDAR-based perception systems play a fundamental role in the ro

arXiv:2606.20752v1 Announce Type: new Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent stu

arXiv:2606.12040v1 Announce Type: new Abstract: The design of reinforced concrete highway barriers is a safety-critical process that requires strict compliance with regulatory provisions such as the A

arXiv:2505.08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety. In this paper we int

arXiv:2606.11507v1 Announce Type: new Abstract: Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajecto

This article from Latent Space discusses Anthropic's Claude Fable 5 model, examining its capabilities in handling creative and mythological content while maintaining safety guardrails, along with cove

Jeremy Howard argues that Anthropic's leadership should recognize that ensuring AI safety and positive outcomes requires collaborative effort across the industry rather than positioning any single org

Gary Marcus critiques Anthropic's rapid shift in positioning Claude from a model deemed too dangerous for public release to one made widely available with safety measures, suggesting this represents i

arXiv:2606.09142v1 Announce Type: cross Abstract: Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexp

arXiv:2606.07970v1 Announce Type: cross Abstract: Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with o

arXiv:2606.09109v1 Announce Type: new Abstract: Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dyna

arXiv:2606.09746v1 Announce Type: cross Abstract: With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing veri

arXiv:2606.08136v1 Announce Type: new Abstract: Model Predictive Control (MPC) is widely used for autonomous-vehicle (AV) motion planning, but its real-time applicability is often limited by the need

arXiv:2606.07620v1 Announce Type: cross Abstract: With the growth of Vision Transformers in safety-critical domains like autonomous systems and medical imaging, ensuring their reliability against soft

arXiv:2606.06133v1 Announce Type: cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produ

arXiv:2606.05647v1 Announce Type: cross Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to cod

arXiv:2601.21288v2 Announce Type: replace-cross Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and

arXiv:2606.04072v1 Announce Type: cross Abstract: Deep learning models are increasingly central to autonomous vehicle (AV) pipelines, yet their integration has traditionally followed a monolithic desi

arXiv:2606.04310v1 Announce Type: new Abstract: Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essenti

Lukas Petersson and Axel Backlund of Andon Labs discuss their work on evaluation methods and benchmarking for AI systems, likely covering approaches to assessing AI capabilities and safety in real-wor

arXiv:2606.04296v1 Announce Type: new Abstract: As autonomous AI agents move from conversational systems to long-horizon software execution, runtime safety layers that decide when to interrupt an agen

arXiv:2606.03695v1 Announce Type: new Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for safety a

Sam Altman argues that US leadership in artificial intelligence requires three concurrent priorities: advancing cutting-edge AI model development, ensuring these models incorporate robust safety measu

Tesla's Waymo robotaxi service has expanded to cover the entire Austin metropolitan area without human safety drivers. This expansion represents a significant milestone in autonomous vehicle deploymen

arXiv:2606.01883v1 Announce Type: cross Abstract: Open-set recognition (OSR) requires a classifier to reject inputs from unseen classes which is essential in safety-critical settings such as medical i

arXiv:2606.02282v1 Announce Type: new Abstract: Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and halluci

arXiv:2606.00059v1 Announce Type: cross Abstract: Informative excitation signals are critical for accurate system identification of mechatronic systems, yet classical system identification (SI) approa

arXiv:2606.00341v1 Announce Type: cross Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safet

arXiv:2507.02983v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) hold significant promise for transforming digital health by enabling automated medical question answering. Howeve

arXiv:2606.00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set. We study a core safety problem in agen

McDonald's paused advertising on 𝕏 (formerly Twitter) in late 2024, likely due to concerns about content moderation and brand safety on the platform following Elon Musk's ownership changes. This move

arXiv:2509.12440v3 Announce Type: replace-cross Abstract: Deploying Large Language Models (LLMs) in medical applications requires fact-checking capabilities to ensure patient safety and regulatory com

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