Search: “safety”

arXiv:2510.16492v4 Announce Type: replace Abstract: As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While

arXiv:2606.25442v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. Ho

arXiv:2505.11494v3 Announce Type: replace Abstract: Robot learning has produced remarkably effective ``black-box'' controllers for complex tasks such as dynamic locomotion on humanoids. Yet ensuring d

arXiv:2606.06037v2 Announce Type: cross Abstract: Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evaluated on m

arXiv:2606.07678v1 Announce Type: cross Abstract: Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets. Existing data se

arXiv:2606.07193v1 Announce Type: new Abstract: Reinforcement learning (RL) policies enable dynamic legged locomotion but lack mechanisms to avoid violations of safety constraints that are absent duri

arXiv:2603.25670v3 Announce Type: replace Abstract: Safety monitoring is essential for Cyber-Physical Systems (CPSs). However, unsafe events are rare in real-world CPS operations, creating an extreme

arXiv:2606.03793v1 Announce Type: new Abstract: Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial

arXiv:2606.03648v1 Announce Type: cross Abstract: Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety. Previ

arXiv:2606.00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmfu

arXiv:2606.00369v1 Announce Type: cross Abstract: Safe global deployment of AI models requires alignment with human values that vary across cultures. Yet rater pools in safety evaluation datasets rema

arXiv:2606.00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moder

arXiv:2605.31381v1 Announce Type: new Abstract: We evaluate the consistency of automated judges in conducting a multi-dimensional safety evaluation in a reference-free setup. Our results indicate that

arXiv:2508.11011v2 Announce Type: replace Abstract: Construction safety inspections typically involve a human inspector identifying safety concerns on-site. With the rise of powerful Vision Language M

arXiv:2605.28338v1 Announce Type: new Abstract: Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance

arXiv:2605.27690v1 Announce Type: new Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long be

arXiv:2605.27932v1 Announce Type: cross Abstract: Think-with-image reasoning is emerging as a new inference paradigm for large vision-language models, but its safety implications remain poorly underst

arXiv:2605.26947v1 Announce Type: new Abstract: Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt datase

arXiv:2509.13608v2 Announce Type: replace Abstract: As Large Multimodal Models (LMMs) become integral to daily digital life, understanding their safety architectures is a critical problem for AI Align

arXiv:2605.20994v1 Announce Type: new Abstract: Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a stand

arXiv:2505.17352v2 Announce Type: replace Abstract: Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignmen

arXiv:2605.16282v1 Announce Type: cross Abstract: The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a prolifera

arXiv:2602.07892v2 Announce Type: replace-cross Abstract: Safety post-training can improve the harmfulness and policy compliance of Large Language Models (LLMs), but it may also reduce general utility

arXiv:2605.08513v1 Announce Type: cross Abstract: Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expr

arXiv:2503.06223v5 Announce Type: replace Abstract: Large Vision-Language Models (VLMs) are increasingly deployed in open-ended environments, where ensuring reliable safety under multimodal inputs is

arXiv:2605.04366v1 Announce Type: cross Abstract: Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation off

arXiv:2604.04409v2 Announce Type: replace Abstract: Multi-robot systems (MRS) are essential for large-scale applications such as disaster response, material transport, and warehouse logistics, yet ens

arXiv:2605.01913v1 Announce Type: cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable t

arXiv:2604.26577v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this

arXiv:2603.02259v2 Announce Type: replace-cross Abstract: Multi-agent systems provide mature methodologies for role decomposition, coordination, and normative governance, capabilities that remain esse

arXiv:2604.23445v1 Announce Type: cross Abstract: Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigo

arXiv:2506.17299v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their v

arXiv:2505.13527v3 Announce Type: replace-cross Abstract: Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to j

arXiv:2604.20799v1 Announce Type: new Abstract: This paper presents a framework for mapping unknown scalar fields using a sensor-equipped autonomous robot operating in unsafe environments. The unsafe

arXiv:2604.20193v1 Announce Type: new Abstract: Ensuring functional safety in human-robot interaction is challenging because AI perception is inherently probabilistic, whereas industrial standards req

arXiv:2510.08240v2 Announce Type: replace Abstract: Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing

arXiv:2405.13068v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Cu

arXiv:2604.16916v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respo

arXiv:2604.14032v1 Announce Type: cross Abstract: Reinforcement learning has shown promise for automating power-grid operation tasks such as topology control and congestion management. However, its de

arXiv:2604.02821v2 Announce Type: replace Abstract: This paper presents a learning-based approach for all-pairs motion planning, where the initial and goal states are allowed to be arbitrary points in

arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to pra

arXiv:2610.10625v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated use of shared parameters across

arXiv:2610.11766v1 Announce Type: cross Abstract: Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcom

arXiv:2610.09517v1 Announce Type: new Abstract: Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describing d

arXiv:2610.05571v1 Announce Type: cross Abstract: In safety-critical domains such as autonomous driving, systems must be evaluated across a large number of environment conditions, often represented as

arXiv:2610.05756v1 Announce Type: new Abstract: In the rapidly evolving field of construction management, worker safety remains a top priority. This paper introduces an innovative vision-based system