Knowledge catalogue
arXiv:2609.20129v1 Announce Type: cross Abstract: Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless,
Reuters: Mistral and other European AI startups accuse US rivals of using safety concerns to entrench their dominance, rejecting Anthropic's calls to pace the frontier — Europe's leading AI company Mi
arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and
Financial Times: Google DeepMind cofounder Shane Legg warns that advancing AI must never run ahead of safety and launches the DeepMind Institute to explore the deployment of AGI — Shane Legg launches
arXiv:2609.16267v1 Announce Type: cross Abstract: Many operational cases are documented more than once, at different workflow stages and for different purposes, yet model evaluations normally select o
arXiv:2609.15289v1 Announce Type: cross Abstract: Artificial intelligence threatens to outrun human understanding and control. New mathematics is needed to design AI that is legible, steerable, and co
When OpenAI CEO Sam Altman, Anthropic CEO Dario Amodei, Google DeepMind cofounder Demis Hassabis, and SpaceX head Elon Musk loosely agreed over the weekend to slow down AI development, skeptics spotte
arXiv:2609.06708v1 Announce Type: cross Abstract: Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, creat
An Anthropic PBC researcher has resigned over concerns that artificial intelligence labs are “gambling with our lives.” Jacob Coxon was part of the company’s AI pretraining team until today. He announ
arXiv:2609.07823v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) show strong progress on vision-language tasks, yet their reliability in safety-critical settings remains undere
arXiv:2609.07857v1 Announce Type: cross Abstract: Robotic ophthalmic surgery offers high precision but introduces a 'sensory gap' by decoupling the surgeon from their instrument, resulting in a loss o
arXiv:2609.04206v1 Announce Type: cross Abstract: Voice AI systems increasingly mediate customer care interactions where caller presentation cues such as accent, affect, fluency, and urgency are avail
arXiv:2608.27239v1 Announce Type: cross Abstract: Adverse drug reactions (ADRs) are a major, largely preventable source of patient harm. In high-income settings, electronic health records store a pati
arXiv:2608.21880v1 Announce Type: new Abstract: Bangla large language model (LLM) safety is difficult to evaluate with English-centric or standard-script benchmarks because Bangla users routinely writ
arXiv:2608.20513v1 Announce Type: cross Abstract: Continuous deployment to large scale production systems creates a tension between release velocity and reliability. Every change is a potential reliab
arXiv:2608.19376v1 Announce Type: cross Abstract: Split-conformal prediction provides marginal coverage under exchangeability and is increasingly used as an abstention layer for zero-shot vision-langu
arXiv:2508.20468v2 Announce Type: replace Abstract: Conspiracy theories erode public trust in science and institutions while resisting debunking by evolving and absorbing counter-evidence. As AI-gener
arXiv:2608.17184v1 Announce Type: new Abstract: Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured na
arXiv:2608.17600v1 Announce Type: new Abstract: Visual cues are increasingly adopted to guide robot learning, but whether Vision-Language-Action (VLA) models can reliably follow authorized cues while
arXiv:2608.17556v1 Announce Type: cross Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Exis
arXiv:2608.16081v1 Announce Type: new Abstract: Open-weight and frontier vision-language models (VLMs) perform well on general image understanding, but their ability to interpret fine-grained hand ges
arXiv:2608.14531v1 Announce Type: new Abstract: Articulated vehicles are the workhorses of freight transportation, and their autonomous navigation is challenging. Their physical characteristics and mo
arXiv:2407.11823v4 Announce Type: replace Abstract: The United States Food and Drug Administration's (FDA's) 510(k) pathway allows manufacturers to gain medical device approval by demonstrating substa
arXiv:2608.12341v1 Announce Type: new Abstract: Cultural taboo safety is essential for deploying large language models (LLMs), as culturally insensitive outputs may cause offense or even social harm.
arXiv:2608.09158v1 Announce Type: cross Abstract: Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs. This diversity includes low-frequency
arXiv:2608.09828v1 Announce Type: cross Abstract: AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent wo
arXiv:2608.06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet m
arXiv:2608.04415v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to detect unsafe content. A common approach is to combine judgments from a panel of models to correct
arXiv:2608.04697v1 Announce Type: new Abstract: Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operatio
arXiv:2608.01291v1 Announce Type: new Abstract: We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syrian, E
arXiv:2608.00068v1 Announce Type: new Abstract: Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only re
arXiv:2607.23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation. Existing f
Open source software is a critical pillar of the global economy. It underpins cloud computing, financial services, manufacturing, telecommunications, government and internet services by making technol
arXiv:2607.21137v1 Announce Type: new Abstract: Independent sidewalk mobility is essential for blind and visually impaired pedestrians (BVIPs), yet smartphone-based assistive navigation requires perce
arXiv:2607.12165v1 Announce Type: new Abstract: Recently, the societal implementation of high-performance image classification models has expanded rapidly. While these models require vast amounts of t
arXiv:2602.05088v4 Announce Type: replace Abstract: Millions of people now use generative AI chatbots for psychological support. Despite their promise, the most pressing question in AI for mental heal
arXiv:2607.02714v1 Announce Type: cross Abstract: There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains an
Chemical accidents involving releases of dangerous chemicals rose 57 percent between 2021 and 2025, from 83 to 131 incidents , with injuries or deaths rising from 60 to 89 over the same period . The E
arXiv:2607.01378v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities across robotic manipulation tasks, yet their real-world depl
arXiv:2607.02510v1 Announce Type: new Abstract: Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs online and raising an alarm when safet
arXiv:2606.30807v1 Announce Type: cross Abstract: Generative models have recently seen rapid adoption in End-to-End (E2E) autonomous driving (AD), with diffusion-based denoising and vocabulary-based r
arXiv:2606.31993v1 Announce Type: new Abstract: While robotic manipulation capabilities have advanced rapidly, physical safety remains a major barrier to deploying household robots: task success is in
arXiv:2606.31114v1 Announce Type: new Abstract: Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are
arXiv:2606.26185v1 Announce Type: new Abstract: LLM-as-judge ('grader') components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream
arXiv:2606.25013v1 Announce Type: cross Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also genera
arXiv:2606.22381v1 Announce Type: cross Abstract: Road traffic accidents remain a critical global crisis, consistently serving as a primary driver of preventable mortality and severe injury. These inc
arXiv:2606.11636v1 Announce Type: new Abstract: Vision-based navigation models, particularly foundation models, generate viable trajectories from RGB observations alone. However, even state-of-the-art
Dean W. Ball / @deanwball: Anthropic secretly limiting Claude's usefulness for LLM development strengthens the argument that Anthropic is using AI safety to justify monopolistic behavior — My last obs
arXiv:2606.07998v1 Announce Type: cross Abstract: Recent advances in generative AI, especially powerful Large Language Models (LLMs) and Large Reasoning Models (LRMs), raise concerns over the interpre
arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde
Apple Inc.’s WWDC 2026 keynote today focused on making its software platform feel more polished, more responsive and more tightly managed across the company’s device ecosystem with refinements to the
arXiv:2606.05463v1 Announce Type: new Abstract: Patient safety event triage, determining whether a clinical event is reportable under jurisdiction-specific policy, is a high-stakes task typically perf
arXiv:2606.01196v1 Announce Type: cross Abstract: Safety alignment learned in high-resource languages transfers poorly to low-resource languages. Models refuse harmful prompts in English but fail to r
arXiv:2605.29629v1 Announce Type: new Abstract: Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not ho
arXiv:2605.29667v1 Announce Type: new Abstract: When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break
arXiv:2605.28097v1 Announce Type: new Abstract: Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo R
arXiv:2605.27948v1 Announce Type: new Abstract: Motorcycles face disproportionately high crash risks compared to cars due to limited protection and heightened sensitivity to surface hazards, yet Advan
arXiv:2605.27333v1 Announce Type: new Abstract: Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary
arXiv:2605.27046v1 Announce Type: new Abstract: Motor thermal management is often overlooked in the context of electrically-actuated robots, particularly legged robots, but motor overheating is a key
arXiv:2605.24270v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of mode