Search: “safety”

arXiv:2605.23304v1 Announce Type: new Abstract: Hazard, as an abstract concept, is typically defined through cognitive-level logical reasoning rather than concrete examples. In contrast, existing haza

arXiv:2605.21811v1 Announce Type: new Abstract: Robotic dexterous manipulation requires continuously reconciling objectives and constraints defined on heterogeneous geometric spaces: a robot controlle

arXiv:2605.21257v1 Announce Type: new Abstract: Planning through crowded environments under uncertain obstacle motions remains difficult, as stochastic interactions often induce overly conservative be

arXiv:2605.19321v1 Announce Type: cross Abstract: Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards.

arXiv:2510.13727v2 Announce Type: replace Abstract: Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-g

arXiv:2605.19457v1 Announce Type: new Abstract: Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approa

arXiv:2605.20108v1 Announce Type: cross Abstract: While conventional (k=1) discrete-time barrier certificate conditions impose strict safety constraints by requiring the function to be non-increasing

arXiv:2602.20042v2 Announce Type: replace Abstract: General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. T

arXiv:2605.18549v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not alwa

arXiv:2605.17128v1 Announce Type: cross Abstract: Jailbreak attacks on large models have drawn growing attention due to their close ties to societal safety. This work identifies a practical yet unexpl

arXiv:2602.19532v2 Announce Type: replace Abstract: Real-world tasks involve nuanced combinations of goal and safety specifications. In high dimensions, the challenge is exacerbated: formal automata b

arXiv:2605.14194v1 Announce Type: new Abstract: Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implic

arXiv:2605.14087v1 Announce Type: new Abstract: Large Language Models (LLMs), when trained on web-scale corpora, inherently absorb toxic patterns from their training data. This leads to ``toxic degene

arXiv:2605.12719v1 Announce Type: cross Abstract: The continual assurance of safety and performance of automated driving systems (ADSs) poses significant challenges. ADSs operate in complex, dynamic,

arXiv:2605.12917v1 Announce Type: new Abstract: Deep learning models for medical imaging often exhibit overconfidence, creating safety risks in ambiguous diagnostic scenarios. While Conformal Predicti

arXiv:2605.13755v1 Announce Type: new Abstract: In recent years, autonomous driving has significantly in creased the demand for high-quality data to train 2D and 3D perception models for safety-critic

arXiv:2605.13801v1 Announce Type: cross Abstract: As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of th

arXiv:2605.13125v1 Announce Type: new Abstract: In automated driving, crash mitigation is crucial to ensure passenger safety. Accurate avoidance requires precise knowledge of the object's position and

arXiv:2605.13329v1 Announce Type: cross Abstract: How large language models internally represent high-level behaviors is a core interpretability question with direct relevance to AI safety: it determi

arXiv:2605.11972v1 Announce Type: new Abstract: Collisions at non-line-of-sight (NLOS) intersections remain a major safety concern because drivers have limited visibility of approaching traffic. V2X b

arXiv:2411.16769v3 Announce Type: replace-cross Abstract: Understanding the capabilities of text-to-image (T2I) models in harmful content generation is essential to safety and compliance. However, hum

arXiv:2512.20865v2 Announce Type: replace Abstract: The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that

arXiv:2603.02719v2 Announce Type: replace Abstract: As artificial intelligence systems move toward clinical deployment, ensuring reliable prediction behavior is fundamental for safety-critical decisio

arXiv:2605.10721v1 Announce Type: cross Abstract: Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate

arXiv:2605.10624v1 Announce Type: new Abstract: Model Predictive Control (MPC) is widely used to operate safety-critical infrastructure by predicting future trajectories and optimizing control actions

arXiv:2602.00877v2 Announce Type: replace Abstract: Low speed does not always guarantee safety in off-road driving. For instance, crossing a ditch may be risky at a low speed due to the risk of gettin

arXiv:2605.09376v1 Announce Type: new Abstract: Trajectory optimization for autonomous vehicles usually relies on the kinematic bicycle model because of its computational simplicity. However, when the

arXiv:2501.03544v5 Announce Type: replace-cross Abstract: Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, the

Sam Altman made statements under oath in May 2023 regarding AI safety and OpenAI's practices, but Gary Marcus critiqued these statements as incomplete or misleading, suggesting Altman failed to fully

arXiv:2605.07324v1 Announce Type: cross Abstract: Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior w

Good summary of today, @katiemiller, but then again it is getting hard to track of the total number of ex-board members who have called Altman a liar 🤷‍♂️ Also hard to keep track how many OpenAI safet

arXiv:2508.14994v3 Announce Type: replace-cross Abstract: In hazardous and remote environments, robotic systems perform critical tasks demanding improved safety and efficiency. Among these, quadruped

arXiv:2605.02921v1 Announce Type: cross Abstract: As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improv

arXiv:2601.07885v2 Announce Type: replace-cross Abstract: Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs)

arXiv:2605.00868v1 Announce Type: cross Abstract: We present a Safe Active Learning (SAL) framework for autonomous reliability characterization of rectifying Ga_2O_3-based devices under coupled therma

arXiv:2602.07249v2 Announce Type: replace-cross Abstract: Autonomous Vehicles (AVs), especially vision-based AVs, are rapidly being deployed without human operators. As AVs operate in safety-critical

arXiv:2605.01113v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can g

arXiv:2605.01432v1 Announce Type: new Abstract: Autonomous landing in cluttered or unstructured environments remains a safety-critical challenge for unmanned aerial vehicles (UAVs), particularly under

arXiv:2508.11696v3 Announce Type: replace Abstract: A deep learning real-time smoking detection system for CCTV surveillance of fire exit areas is proposed due to critical safety requirements. The dat

arXiv:2602.03265v2 Announce Type: replace Abstract: Large Language Models (LLMs) have seen widespread adoption across multiple domains, creating an urgent need for robust safety alignment mechanisms.

arXiv:2412.16720v2 Announce Type: replace Abstract: The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provi

arXiv:2604.25887v1 Announce Type: new Abstract: Current pedestrian crossing signals operate on fixed timing without adjustment to pedestrian behavior, which can leave vulnerable road users (VRUs) such

arXiv:2504.06176v3 Announce Type: replace-cross Abstract: Foundation Models, which leverage large neural networks pre-trained on unlabelled data before fine-tuning for specific tasks, are increasingly

arXiv:2604.24572v1 Announce Type: new Abstract: The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM), maintained by the Observational Health Data Sciences and Informatics (OHDSI

arXiv:2604.24384v1 Announce Type: new Abstract: Automated vehicles (AVs) are commonly programmed to yield unconditionally to pedestrians in the interest of safety. However, this design choice can give

arXiv:2604.23875v1 Announce Type: cross Abstract: Noisy labels are a pervasive challenge in medical image classification, where annotation errors arise from inter-observer variability and diagnostic a