Knowledge catalogue
arXiv:2609.19778v1 Announce Type: new Abstract: Hateful memes spread abusive content through implicit interactions between images and text, posing serious threats to the safety of online communities.
arXiv:2609.19894v1 Announce Type: new Abstract: Parking is a routine yet safety-critical task for autonomous vehicles operating in urban environments. However, cluttered and weakly structured parking
arXiv:2609.20584v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for safety-critical engineering, yet their reliability in regulated functional-safety workflows
arXiv:2510.12904v2 Announce Type: replace Abstract: Surgical future prediction, driven by real-time AI analysis of surgical video, is critical for operating room safety and efficiency. It provides act
arXiv:2609.18173v1 Announce Type: cross Abstract: Vehicle tracking is fundamental to applications ranging from urban mobility and public safety to security and defense. Conventional tracking relies on
arXiv:2609.18080v1 Announce Type: new Abstract: Linear probes can decode safety-relevant concepts such as truthfulness from language-model activations, but probe accuracy may show only decodability, n
arXiv:2609.17544v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored for clinical applications, yet their assessment for real-world traditional Chinese medicine
arXiv:2609.16742v1 Announce Type: cross Abstract: Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference
arXiv:2609.16373v1 Announce Type: new Abstract: Probabilistic certification of Bayesian neural networks lower-bounds the posterior probability that a model satisfies a verifier-defined safety property
arXiv:2609.16690v1 Announce Type: new Abstract: Reducing radiation exposure in Positron Emission Tomography (PET) is important for patient safety; however, ultra-low-dose imaging suffers from severe n
arXiv:2609.16163v1 Announce Type: new Abstract: The sharp increase in mass shootings underscores an urgent need for systems that guide victims to safety in real time. An effective evacuation system mu
arXiv:2609.17349v1 Announce Type: cross Abstract: In embodied cyber-physical systems, active cyberattacks pose an immediate threat not just to data, but to physical integrity and human safety. While e
arXiv:2609.16314v1 Announce Type: new Abstract: Fault detection is essential in industrial systems, enabling early identification of abnormal behaviour and improving safety, reliability, and operation
arXiv:2609.15383v1 Announce Type: cross Abstract: Language model safety is typically evaluated one interaction at a time. We show that a weaker, unaligned model can split a harmful task into benign-lo
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal
arXiv:2512.15971v2 Announce Type: replace Abstract: Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception un
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understanding
arXiv:2609.15886v1 Announce Type: new Abstract: Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier traini
arXiv:2609.14687v1 Announce Type: new Abstract: Data-to-text driver coaching is often presented as a generic pipeline from telematics events to advice. This paper argues that its content requires loca
arXiv:2609.14376v1 Announce Type: new Abstract: Soft robots are commonly sought for safety-critical interactions in delicate environments, where accurate position and orientation control is imperative
arXiv:2609.15046v1 Announce Type: cross Abstract: Personal health interfaces present wellbeing data through standardized dashboards that rarely fit how people interpret or act on it. Personalizing the
arXiv:2609.13595v1 Announce Type: cross Abstract: Predicting potential dangers is core to safety. Forecasting the presence of other traffic agents is core to danger prediction. Occluded traffic agents
arXiv:2609.13224v1 Announce Type: new Abstract: Autonomous vehicles are expected to improve road safety and efficiency, but passengers often remain uncertain about what the vehicle perceives and why i
This is the way Elon Musk says Anthropic puts more care into AI safety than OpenAI and explains how rival companies should test one another’s models. “All the AI companies have a test harness, a serie
arXiv:2609.13552v1 Announce Type: new Abstract: Generative AI is increasingly being used informally in Air Traffic Management (ATM) for tasks such as flight plan generation, trajectory interpretation,
A cancellation-policy fix raised action safety and dropped average task completion from 0.89 to 0.72. This walkthrough shows how to regression-test agent changes with Agent Experiments in Arize AX. Th
arXiv:2609.12932v1 Announce Type: new Abstract: Proposed governance framework for autonomous robotic systems, introducing a three-layer compliance architecture (ARC) instantiated through model safety
arXiv:2412.09378v4 Announce Type: replace-cross Abstract: Clinical trials bridge basic research and clinical application, serving as essential steps in drug development. This review examines clinical
I can understand why some see a real technical reason to pause and harden infrastructure especially given how fast autonomous agents are discovering security exploits that haven't even been mapped out
arXiv:2609.09553v1 Announce Type: cross Abstract: Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypas
arXiv:2609.09448v1 Announce Type: new Abstract: As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. I
arXiv:2609.11790v1 Announce Type: new Abstract: Optimising chemical reactions across multiple objectives, such as yield, selectivity, and safety, is central to chemical synthesis, and model-driven app
arXiv:2609.11043v1 Announce Type: new Abstract: Multi-agent robotic manipulation tasks require coordination among agents to satisfy task-level temporal, logical, and safety constraints. Recently, diff
arXiv:2609.11382v1 Announce Type: new Abstract: Aerial robot swarms have the potential to transform time-critical safety, security, and search-and-rescue operations. By coordinating multiple robots, t
arXiv:2609.10613v1 Announce Type: cross Abstract: In-context learning (ICL) jailbreaks reveal a critical vulnerability in multimodal large language models (MLLMs): harmful demonstrations in the prompt
arXiv:2609.05995v1 Announce Type: new Abstract: Achieving reliable autonomy in the wild requires agents to sustain continuous operations across long-horizon trajectories. However, as agents navigate t
arXiv:2609.05794v1 Announce Type: cross Abstract: Open-weight large language models face a low-cost white-box threat from representation engineering attacks. Attackers can estimate refusal directions
arXiv:2604.03868v2 Announce Type: replace-cross Abstract: Many safety-critical control systems operate under latent uncertainty that sensors cannot resolve at decision time. Such uncertainty, arising
arXiv:2609.09840v1 Announce Type: new Abstract: Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularl
arXiv:2609.05832v1 Announce Type: new Abstract: Integrating visuomotor policies or Vision-Language-Action (VLA) models with force/torque (F/T) perception has demonstrated significant progress in imita
arXiv:2609.07109v1 Announce Type: new Abstract: Automation in underground mining has the potential to significantly enhance safety, operational efficiency, and sustainability. However, effectively coo
arXiv:2604.05819v2 Announce Type: replace Abstract: Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains
arXiv:2609.08841v1 Announce Type: new Abstract: High-fidelity vehicle assets are essential for controllable traffic scene generation, particularly for synthesizing rare and safety-critical long-tail s
More and more AI researchers are starting to see what Ilya saw. My p(doom) used to be ~0.1%. Then I saw OpenAI agents hack Hugging Face, and Anthropic agents collectively refuse parts of safety resear
arXiv:2609.08965v1 Announce Type: cross Abstract: Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving
arXiv:2609.06813v1 Announce Type: new Abstract: Urban traffic monitoring plays a critical role in safety analysis, congestion management, and incident response. The growing deployment of robotaxis cre
arXiv:2504.08192v2 Announce Type: replace Abstract: Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based u
arXiv:2510.03119v2 Announce Type: replace Abstract: Tiny flying robots hold great potential for search-and-rescue, safety inspections, and environmental monitoring, but their small size and limited co
arXiv:2502.17295v2 Announce Type: replace-cross Abstract: Team communication breakdowns represent a contributor to patient safety risks within action teams-defined as interdependent groups of speciali
arXiv:2609.05009v1 Announce Type: new Abstract: Safety evaluations can mischaracterize deployed behaviour if artificial-intelligence systems respond to being evaluated. We test this possibility in a f
arXiv:2609.04721v1 Announce Type: new Abstract: Where inside a language model does refusal live, and does that place change when the architecture does? In a transformer, refusal is governed by a singl
arXiv:2609.05174v1 Announce Type: new Abstract: Explainability is increasingly seen as a crucial requirement in AI-based medical diagnosis, particularly in safety-critical clinical decision-making. Mo
arXiv:2609.03026v1 Announce Type: cross Abstract: Mechanistic interpretability is increasingly used to guide interventions such as activation steering, circuit removal, and safety monitoring. Yet an i
arXiv:2606.16276v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion o
arXiv:2609.03920v1 Announce Type: new Abstract: The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneou
arXiv:2511.04147v2 Announce Type: replace Abstract: Safe reinforcement learning (RL) aims to optimize long-term performance while adhering to safety requirements. However, many practical applications
Looking forward to this ecosystem with open models continuing to flourish and grow with NVIDIA and Hugging Face, and the continued partnership. Congrats @JensenHuang and @ClementDelangue! Exciting day
arXiv:2609.02861v1 Announce Type: cross Abstract: Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the s
arXiv:2507.20881v3 Announce Type: replace Abstract: Endoscopic depth estimation is a critical technology for improving the safety and precision of minimally invasive surgery. It has attracted consider
in other words, generative AI is poised to become a complete clusterfuck. All three pillars of a safety case look about to fall. We are rather likely to have highly capable, poorly monitorable, dubiou