Search: “safety”

arXiv:2607.00326v1 Announce Type: new Abstract: Safe multi-arm motion planning is a challenging problem in robotics due to its high dimensionality, coupled configuration space, and complex collision c

AI systems that are accessible or even better open-source are safer for a simple reason: more people can inspect them, test them, stress them, and report what breaks or harms to keep the builders acco

arXiv:2606.31614v1 Announce Type: cross Abstract: Engineering specifications such as interlocks, alarm rationalization tables, and cause-and-effect (C&E) matrices remain central to process control and

arXiv:2606.31339v1 Announce Type: new Abstract: Agentic artificial intelligence is increasingly used to decompose industrial tasks, propose robot actions, and adapt execution plans in dynamic cyber-ph

Being at the launch of Cybercab two years ago was magic. A decade from now there will be millions of these things rolling around the world. The war over autonomous vehicles is on, as everyone in San F

arXiv:2606.28360v1 Announce Type: cross Abstract: University students often struggle to navigate complex academic policies, leading to advising bottlenecks and delayed access to critical information.

arXiv:2405.10703v4 Announce Type: replace Abstract: Safe control in unknown environments is a key challenge in mobile robotics. Control Barrier Functions (CBFs) provide a principled framework for guar

arXiv:2606.29372v1 Announce Type: new Abstract: Massive robot swarms can explore unknown environments quickly, but adding robots eventually stops helping. Doorways and dense traffic create congestion,

arXiv:2606.27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We invest

arXiv:2510.26518v2 Announce Type: replace Abstract: Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, veri

arXiv:2606.27123v1 Announce Type: cross Abstract: Closed-loop traffic simulation remains challenging because it must generate interactive multi-agent behaviors that are scene-consistent and controllab

arXiv:2606.27147v1 Announce Type: cross Abstract: Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predic

arXiv:2606.26017v1 Announce Type: new Abstract: In autonomous driving, diffusion-based planners have emerged as a promising paradigm for robust motion planning in dense and interactive traffic, as the

arXiv:2606.25651v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in healthcare settings, accurate error detection and correction in generated or existing text

arXiv:2606.23699v1 Announce Type: new Abstract: Instrumented bicycle studies have produced direct field evidence on vehicle passing behavior, but extracting overtaking events from continuous rear-faci

arXiv:2606.24231v1 Announce Type: new Abstract: Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are con

arXiv:2603.19957v2 Announce Type: replace-cross Abstract: Pathology reports are structured, multi-granular documents encoding diagnostic conclusions, histological grades, and ancillary test results ac

arXiv:2606.24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs). The dataset is designed to be di

arXiv:2606.23531v1 Announce Type: new Abstract: Endoscopic retrograde cholangiopancreatography (ERCP) demands precise endoscopic navigation and stable biliary cannulation within a narrow monocular fie

arXiv:2606.15980v2 Announce Type: replace Abstract: Activation monitors -- lightweight probes trained on a language model's internal representations -- are an increasingly common layer in deployment s

arXiv:2606.23131v1 Announce Type: new Abstract: Background: Laparoscopic camera navigation (LCN) is a critical skill, yet its current assessment typically relies on manual rating systems which are tim

arXiv:2503.03579v2 Announce Type: replace-cross Abstract: Spoken instructions in robot-to-human handovers may specify either an object ('the cup') or an intended use ('pour water'); in both cases, suc

arXiv:2606.20764v1 Announce Type: new Abstract: Reliable spatial decision automation, such as autonomous driving and maritime surveillance, critically depends on robust visual perception. However, rea

arXiv:2606.20636v1 Announce Type: cross Abstract: Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during

arXiv:2606.12142v1 Announce Type: cross Abstract: Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, mos

arXiv:2606.11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile

arXiv:2606.12306v1 Announce Type: new Abstract: Safe ground navigation in large, threat-augmented environments requires aerial support that actively reduces the risks that a ground vehicle faces along

arXiv:2606.11109v1 Announce Type: new Abstract: Falls are one of the leading causes of injury and hospitalization among elderly individuals, making reliable fall awareness an essential capability for

Why are AI research restrictions treated differently from every other safeguard? @theemozilla and @karan4d, co-founders of Nous Research: 'On the bio stuff... just saying no to the user and being hone

arXiv:2606.09414v1 Announce Type: cross Abstract: This report examines practical challenges in operationalising JSP 936 Part 1 for AI assurance in UK Defence. Using a structured interpretive review of

arXiv:2606.09122v1 Announce Type: cross Abstract: Cloud network infrastructure at hyperscale presents unique operational challenges where traditional human-driven incident response cannot keep pace wi

arXiv:2606.08875v1 Announce Type: new Abstract: Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics

arXiv:2606.08090v1 Announce Type: cross Abstract: Evaluating a natural-language yes/no predicate over a document corpus under an accuracy target - the semantic filter - is a cornerstone of LLM-based d

arXiv:2604.04251v2 Announce Type: replace Abstract: Intelligent tutoring systems increasingly rely on reinforcement learning to personalise instruction, yet optimising for observable engagement signal

arXiv:2606.09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such

arXiv:2606.08021v1 Announce Type: cross Abstract: As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: propose

arXiv:2606.06893v1 Announce Type: new Abstract: Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write. This paper

arXiv:2606.05748v1 Announce Type: cross Abstract: Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to supp

arXiv:2606.04185v1 Announce Type: new Abstract: Safe navigation in dynamic and uncertain environments often relies on accurate estimation of, or assumptions about, the true underlying uncertainty. How

arXiv:2606.04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, enviro

arXiv:2603.03205v2 Announce Type: replace Abstract: Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon ac

arXiv:2509.14760v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications

arXiv:2606.04248v1 Announce Type: new Abstract: Decentralized rigid formation flocking requires a swarm of autonomous agents to maintain a predetermined geometric configuration while moving, relying s

arXiv:2606.03296v1 Announce Type: new Abstract: Complex, dynamic, and interactive driving environments pose significant challenges for autonomous driving, primarily due to the pervasive uncertainty of

arXiv:2606.03601v1 Announce Type: cross Abstract: While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rej

arXiv:2509.20623v2 Announce Type: replace Abstract: Reinforcement learning has enabled significant progress in complex domains such as coordinating and navigating multiple quadrotors. However, even we