Search: “safety”

arXiv:2606.09178v1 Announce Type: cross Abstract: Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target l

arXiv:2606.08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfiel

arXiv:2606.07186v1 Announce Type: new Abstract: Software-in-the-loop (SIL) simulation is a cornerstone for the validation of modern automotive safety functions. However, many current frameworks utiliz

arXiv:2606.07437v1 Announce Type: cross Abstract: The ISO 26262 standard defines functional safety for road vehicles through risk assessments based on Severity, Exposure, and Controllability, grounded

arXiv:2606.06875v1 Announce Type: new Abstract: Diffusion transformers (DiTs) equipped with multimodal attention (MM-Attn) have become a dominant paradigm for image generation. However, preventing the

arXiv:2606.05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow

arXiv:2606.06356v1 Announce Type: new Abstract: Multimodal generative models produce fluent outputs but remain unreliable when generation must respect structured, domain-specific, or safety-critical k

arXiv:2606.05185v1 Announce Type: cross Abstract: Mass gathering events are associated with critical safety incidents caused by insufficient crowd monitoring and inadequate emergency response coordina

arXiv:2606.04656v1 Announce Type: cross Abstract: Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for saf

arXiv:2606.04158v1 Announce Type: new Abstract: Multi-agent Next-Best-View (NBV) selection for safe path planning in uncertain and unknown environments requires informative, safety-aware, and efficien

arXiv:2606.03804v1 Announce Type: new Abstract: Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their envir

arXiv:2502.09755v4 Announce Type: replace-cross Abstract: Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation

arXiv:2606.01605v1 Announce Type: new Abstract: We propose an online monocular perception-to-control framework that embeds semantic risk into the distance field used by Control Barrier Function (CBF)-

arXiv:2601.18783v2 Announce Type: replace-cross Abstract: Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A

arXiv:2606.00297v1 Announce Type: cross Abstract: Control barrier functions (CBFs) provide real-time safety guarantees through pointwise conditions on the state. However, synthesizing a valid CBF is d

arXiv:2506.11083v3 Announce Type: replace Abstract: We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate

arXiv:2606.00090v1 Announce Type: cross Abstract: Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential a

arXiv:2602.02557v2 Announce Type: replace-cross Abstract: Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignmen

arXiv:2602.07253v2 Announce Type: replace Abstract: Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability. While existin

arXiv:2512.11944v2 Announce Type: replace-cross Abstract: Motion planning for autonomous driving (AD) faces a critical trade-off. While traditional rule-based pipelines offer verifiable safety and int

arXiv:2605.27671v1 Announce Type: cross Abstract: Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect

arXiv:2605.27758v1 Announce Type: cross Abstract: Automotive crashworthiness optimization remains a safety-critical challenge, requiring the management of large-scale nonlinear structural deformations

arXiv:2605.27157v1 Announce Type: new Abstract: Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robust

arXiv:2605.24860v1 Announce Type: cross Abstract: Advanced driver assistance systems (ADAS) play an important role in modern automotive intelligence, significantly enhancing vehicle safety and stabili

arXiv:2602.00491v2 Announce Type: replace Abstract: Public health reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it r

arXiv:2602.13241v2 Announce Type: replace-cross Abstract: Emergency call-takers form the first operational link in public safety response, handling over 240 million calls annually while facing a susta

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