Search: “safety”

arXiv:2609.13236v1 Announce Type: new Abstract: Humanoid robots are becoming an important part of embodied artificial intelligence, driven by advances in reinforcement learning for locomotion, world m

arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priva

arXiv:2607.28503v3 Announce Type: replace Abstract: In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted

arXiv:2608.06110v1 Announce Type: new Abstract: This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management.

arXiv:2608.05018v1 Announce Type: new Abstract: Short-term load forecasting (STLF) play a vital role in the electric power industry. It serves infrastructure that European and German law designate as

arXiv:2608.02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is f

arXiv:2608.00600v1 Announce Type: new Abstract: Standard multifingered grasp execution architectures plan a collision-free trajectory to a selected grasp pose and track it with a feedback law. Executi

arXiv:2607.24392v1 Announce Type: cross Abstract: Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility. W

arXiv:2604.02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safet

arXiv:2606.22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show t

arXiv:2606.26686v1 Announce Type: new Abstract: In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follo

arXiv:2606.07016v1 Announce Type: cross Abstract: Vulnerable road users (VRUs) account for approximately half of urban traffic deaths globally, with intersections concentrating a disproportionate shar

arXiv:2606.02630v1 Announce Type: cross Abstract: Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke author

arXiv:2606.02443v1 Announce Type: cross Abstract: Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable

arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode colla

arXiv:2605.26159v1 Announce Type: cross Abstract: Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software ser

arXiv:2507.06513v3 Announce Type: replace Abstract: Advances in vision-based sensors and computer vision algorithms have significantly improved the analysis and understanding of traffic scenarios. To

arXiv:2605.14454v1 Announce Type: cross Abstract: As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line

arXiv:2605.14604v1 Announce Type: new Abstract: This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive con

arXiv:2605.08878v1 Announce Type: cross Abstract: Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representa

arXiv:2605.00706v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal

arXiv:2505.24672v2 Announce Type: replace Abstract: Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploit

arXiv:2604.13878v1 Announce Type: new Abstract: Driver drowsiness significantly impairs the ability to accurately judge safe braking distances and is estimated to contribute to 10%-20% of road acciden

arXiv:2604.11174v1 Announce Type: cross Abstract: Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluatio

arXiv:2604.07709v1 Announce Type: cross Abstract: Ask a frontier model how to taper six milligrams of alprazolam (psychiatrist retired, ten days of pills left, abrupt cessation causes seizures) and it

arXiv:2510.05524v2 Announce Type: replace Abstract: We present Knowledge Extraction on OMIn (KEO), a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in s

arXiv:2610.15191v1 Announce Type: new Abstract: Batch risk-based inspection scheduling struggles to detect a critical failure class: food facilities with recent clean inspections that subsequently dev

arXiv:2610.19250v1 Announce Type: new Abstract: Reduced-order models (ROMs) make model predictive control (MPC) of high-dimensional nonlinear systems tractable, but the resulting modeling error can le

arXiv:2610.02300v1 Announce Type: new Abstract: Training-free safeguards for text-to-image generation often rely on a reusable safety signal, such as an unsafe direction or global toxic subspace, appl

arXiv:2609.25755v1 Announce Type: new Abstract: Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-

arXiv:2609.02967v1 Announce Type: cross Abstract: Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and i

arXiv:2608.29241v1 Announce Type: new Abstract: Clinical voice agents are now deployed in routine care, where real patients do not wait their turn: they interrupt. These systems typically use a cascad

arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-

arXiv:2608.02790v1 Announce Type: new Abstract: Vision-language models (VLMs), including medical specialists, are increasingly proposed for medical imaging, yet their stated confidence is rarely evalu

arXiv:2509.02655v3 Announce Type: replace-cross Abstract: Many AI alignment discussions of 'runaway optimisation' focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective

arXiv:2605.11679v2 Announce Type: replace Abstract: In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. S

arXiv:2605.12895v1 Announce Type: cross Abstract: Aggregate accuracy metrics dominate the evaluation of clinical AI decision-support systems but do not detect deployment-phase failures of input reliab

arXiv:2605.07021v1 Announce Type: new Abstract: Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To addr

arXiv:2605.07422v1 Announce Type: cross Abstract: Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding proce

arXiv:2605.01567v1 Announce Type: cross Abstract: Large language model (LLM) coding agents increasingly operate over repositories, terminals, tests, and execution traces across long software-engineeri

arXiv:2604.23095v1 Announce Type: new Abstract: Indoor environments lack the spatial intelligence infrastructure that GPS provides outdoors; first responders arriving at unfamiliar buildings typically

arXiv:2601.03173v2 Announce Type: replace Abstract: Time pressure critically influences risky maneuvers and crash proneness among powered two-wheeler riders, yet its prediction remains underexplored i

arXiv:2601.07177v2 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on imp

arXiv:2608.21869v1 Announce Type: cross Abstract: Text-to-image (T2I) diffusion models offer powerful visual generation, but their controllability creates a critical safety challenge: adversarial prom

arXiv:2608.17823v1 Announce Type: cross Abstract: Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors s

arXiv:2604.15967v1 Announce Type: cross Abstract: Despite the remarkable synthesis capabilities of text-to-image (T2I) models, safeguarding them against content violations remains a persistent challen