Search: “safety”

arXiv:2607.26654v1 Announce Type: new Abstract: Post-training alignment is often shallow, eroding under fine-tuning. Whether midtraining interventions, cleanly isolated from post-training, can produce

arXiv:2607.27085v1 Announce Type: new Abstract: This paper presents the North Carolina Transitional Autonomous Vehicle Lane-Changing (NC-tALC) dataset and uses it to characterize mandatory lane-changi

arXiv:2607.27145v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitorin

arXiv:2607.26389v1 Announce Type: new Abstract: Fine-tuning a language model on data containing a narrow flaw, such as insecure code or incorrect mathematical answers, can cause broad misalignment thr

arXiv:2607.24829v1 Announce Type: cross Abstract: AI-based medication recommendation systems have attracted substantial attention due to their potential to enhance patient safety and therapeutic outco

arXiv:2607.24900v1 Announce Type: new Abstract: Language model alignment aims to make model behavior reliably reflect desirable properties such as helpfulness, safety, and instruction following. Curre

arXiv:2607.25138v1 Announce Type: new Abstract: Safety inflation can cause nearby obstacles to overlap, violating the disjoint-obstacle assumptions used by many modulation-based reactive planners. We

arXiv:2607.26042v1 Announce Type: new Abstract: We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing devi

arXiv:2607.22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and per

arXiv:2607.23388v1 Announce Type: cross Abstract: As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustnes

arXiv:2607.22959v1 Announce Type: cross Abstract: AI-generated video is increasingly used across marketing, product storytelling, and creative workflows, yet automated; high-precision quality control

arXiv:2607.23979v1 Announce Type: new Abstract: Visual tire recognition serves as a core supporting technique for vehicle safety monitoring, autonomous driving perception and automated automotive main

arXiv:2607.23991v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements. However,

Nvidia on Monday said it is joining forces with Microsoft, SpaceX, IBM, and other tech companies to build and share open-source AI security tools. The new Open Secure AI Alliance said open tools are r

arXiv:2607.11346v3 Announce Type: replace Abstract: Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP const

arXiv:2602.13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT

arXiv:2607.16619v2 Announce Type: replace Abstract: Safe and socially compliant navigation in open human-robot environments requires robots to reason about heterogeneous participants with different dy

arXiv:2511.05865v3 Announce Type: replace-cross Abstract: Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised signifi

arXiv:2507.05458v2 Announce Type: replace Abstract: For effective real-world deployment, robots should adapt to human preferences, such as balancing distance, time, and safety in delivery routing. Act

arXiv:2607.19899v1 Announce Type: cross Abstract: Disagreement-triggered escalation can create a structural blind spot in multi-agent arbitration: as base learners improve, they tend to converge, weak

arXiv:2607.20277v1 Announce Type: new Abstract: Machine learning models achieve high predictive accuracy in regression tasks, but their deployment in safety-critical and regulated domains requires int

arXiv:2607.19061v2 Announce Type: replace-cross Abstract: Hateful optical illusions expose a serious gap in current multimodal safety systems. On original-view hateful illusions, previous work shows t

arXiv:2607.19351v1 Announce Type: new Abstract: LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions throu

arXiv:2607.20046v1 Announce Type: cross Abstract: With the widespread deployment of deep neural networks (DNNs) in safety-critical domains, reducing the cost of model validation under limited testing

arXiv:2607.20082v1 Announce Type: new Abstract: Language models are increasingly asked to self-report, informing safety evaluations, public understanding, and model-welfare debates. Yet their reports

It's essential that defenders have the same capabilities as attackers. This is a preview of the future where our ham-fisted safeguards and the doomsday and safety drumbeat make us decidely less safe.

And now from the Chinese government side. This would be a good time for cooperation between the US and China to establish common testing/acceptance standards for new models, so at least the safety cer

arXiv:2607.13806v1 Announce Type: new Abstract: European safety regulation now permits a large share of automated-driving homologation evidence to be produced virtually, provided a validated physical-

arXiv:2607.13655v1 Announce Type: new Abstract: Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in saf

arXiv:2607.11957v1 Announce Type: new Abstract: Maintenance of critical infrastructures, such as railways and power plants, is essential for ensuring operational safety and reliability. However, the d

arXiv:2607.12785v1 Announce Type: new Abstract: Robot-assisted minimally invasive surgery (MIS) critically depends on reliable endoscopic perception for navigation and safety. However, conventional en

arXiv:2607.12662v1 Announce Type: new Abstract: The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical

arXiv:2607.12423v1 Announce Type: new Abstract: Multi-Robot Motion Planning in continuous environments, where robots must generate dynamically feasible, collision-free trajectories, is challenging due

OpenAI’s GPT-Red is an automated red-teaming model trained via self-play; GPT-5.6 Sol shows 6× fewer hard prompt-injection failures.

arXiv:2607.11899v1 Announce Type: cross Abstract: High-altitude Clear Air Turbulence (CAT) poses significant risks to aviation safety due to its unpredictability and challenges in detection. This stud

arXiv:2607.11983v1 Announce Type: cross Abstract: A specialist tolerates blind spots that a generalist does not. Usually this is treated as a cost to be minimized. We treat it as a design variable: a

arXiv:2511.03075v2 Announce Type: replace Abstract: The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, esp

arXiv:2607.02300v2 Announce Type: replace Abstract: In the automotive domain, in-car scene understanding (ISU) enables the detection of safety-critical events, such as driver distraction, and supports

arXiv:2606.16567v2 Announce Type: replace Abstract: Neural ordinary differential equations (neural ODE) gained attention in safety critical settings such as continuous-time controllers for cyber-physi

arXiv:2607.08054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly trusted to draft the artifacts of safety analysis such as, losses, hazards, Unsafe Control Actions (UCAs

arXiv:2607.07538v1 Announce Type: new Abstract: Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics on the loss landscape, and a natural safety question is to

arXiv:2607.06950v1 Announce Type: cross Abstract: Sampling-based model predictive control methods handle nonlinear dynamics and complex cost landscapes through Monte Carlo rollouts, yet typically empl

arXiv:2607.07252v1 Announce Type: new Abstract: Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems

arXiv:2601.17216v3 Announce Type: replace-cross Abstract: Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventiona

arXiv:2607.07196v1 Announce Type: cross Abstract: Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world,

arXiv:2607.05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Rea