Knowledge catalogue
arXiv:2608.11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.g., the agent does
arXiv:2512.06227v3 Announce Type: replace Abstract: Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis
arXiv:2608.10056v1 Announce Type: cross Abstract: Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surroun
arXiv:2608.10872v1 Announce Type: cross Abstract: We present a robust safety-filtering framework for input-constrained underactuated linear systems subject to unknown disturbances. A baseline H-infty
arXiv:2608.05409v1 Announce Type: new Abstract: Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep est
arXiv:2608.04776v1 Announce Type: new Abstract: The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems. While existing research ha
arXiv:2608.04420v1 Announce Type: new Abstract: Safe navigation with a body-mounted limited-field-of-view sensor requires the complete robot-inflated volume of an intended motion to be observed and ve
arXiv:2608.03866v1 Announce Type: new Abstract: This white paper presents ADMITBench, a reference framework for evaluating industrial LLM advisories at the level of the proposed action. The framework
Yes, the AIs were given a cybersecurity challenge, with internet access enabled and safety filters disabled. But the extent to which Mythos 5 pursued its mission (fake identities, social engineering,
arXiv:2508.05775v3 Announce Type: replace Abstract: Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language
arXiv:2607.24168v1 Announce Type: new Abstract: Road crashes remain among the gravest threats to public safety, and preventing them is a defining task of transportation systems worldwide. Much of that
arXiv:2607.22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whe
arXiv:2607.13594v1 Announce Type: new Abstract: LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a gua
arXiv:2607.08038v1 Announce Type: new Abstract: Diagnostic error is a major threat to patient safety, yet current large language model (LLM) systems often treat diagnosis as a one-shot prediction task
arXiv:2607.07918v1 Announce Type: cross Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Late
At UMA, we build and own the full stack, from hardware to software. This allows us to bake safety in at all levels, rather than bolt it on as an afterthought. Because trust is everything when robots s
arXiv:2607.05180v1 Announce Type: cross Abstract: Adverse driving conditions, such as bad weather, remain a principal barrier to autonomous driving because they degrade two things at once: what the ve
Connie Loizos / TechCrunch: Q&A with Agility Robotics CEO Peggy Johnson on why the startup is going public via SPAC, the physical layer as its proprietary advantage, safety, and more — The humanoid ro
Grace Kay / The Information: Tesla rolls out its Robotaxi service without a safety monitor in Miami, its fifth city, as it aims to expand to a dozen US states by the end of 2026 — Tesla said it rolled
arXiv:2607.01365v1 Announce Type: cross Abstract: Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is? Can we improve our abil
arXiv:2607.01200v1 Announce Type: new Abstract: Fast quadrotor flight requires safe obstacle avoidance under tight onboard compute limits. While 3D Gaussian Splatting (3DGS) provides a continuous, geo
arXiv:2601.21173v2 Announce Type: replace-cross Abstract: With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in com
arXiv:2606.30256v1 Announce Type: new Abstract: Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure. For emotional-support chatbots, that bargain hides p
arXiv:2601.17642v2 Announce Type: replace Abstract: Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal o
Really impressive first few drives with FSD v14 lite! Big leap in capability and feature set from v12.6.4, it’s tuned for safety right now so it’s taking things slow and smoothly. Highway performance
arXiv:2502.09241v2 Announce Type: replace Abstract: This paper presents a novel approach to real-time safety monitoring in human-robot collaborative manufacturing environments through a wrist-mounted
It would be very useful to understand more about the government safety concerns associated with frontier AI releases so we could (a) know what risks everyone will face if/when open source reaches Myth
arXiv:2606.23858v1 Announce Type: cross Abstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify
arXiv:2606.22841v1 Announce Type: cross Abstract: As Large Language Models (LLMs) achieve widespread integration across diverse linguistic landscapes, ensuring their safety and alignment with regional
arXiv:2606.22686v1 Announce Type: cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque. In this work, we investig
An interesting new paper by my recent PhD graduate on how AI agents' greed for visible incentives can lead them to abandon their safety alignment. You can read it here: https://arxiv.org/abs/2606.1691
Ian King / Bloomberg: Nvidia unveils Halos, a safety-focused OS developed from autonomous vehicle tech and designed to run on IGX Thor hardware for humanoid robots, and opens a lab — Nvidia Corp. is w
arXiv:2606.11204v1 Announce Type: new Abstract: Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document forma
arXiv:2606.11316v1 Announce Type: new Abstract: Large language models are increasingly deployed across professional domains, bringing hard-to-predict risks, including the generation of harmful or disr
Dario Amodei: An essay on policy responses to AI's exponential progress across regulation and public safety, macroeconomics and taxes, science, civil liberties, geopolitics — In one of the side plots
Joe Brennan / The Irish Times: CameraMatics, which uses AI to help fleet operators improve safety, reduce operational risk, and lower carbon emissions, raised €49M — Tech focuses on accident preventio
🔔 IF Anthropic is for real about safety, the should pause, for one month, and show leadership. If they won’t pause, even briefly, we have a different kind of answer about what is real and what is mark
When you hear AI 'safety' you should hear 'censorship' and 'control' instead. All of us surveilled and spied by safeguards of loving grace. Today it's intelligent Terms of Service control. You can't d
arXiv:2606.08969v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical summarization, but their outputs can omit medically important information and introduce
fable’s safety guardrails broken within an hour. raise your hand if you are surprised. We tested Anthropic’s new @claudeai Fable 5. It did not fail like an ordinary jailbreak. It failed more quietly.
arXiv:2606.09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories. H
arXiv:2606.08860v1 Announce Type: new Abstract: Temporary work-zone speed limits are communicated through visually inconsistent signage and are often missing from digital maps, creating safety risks f
arXiv:2511.20158v2 Announce Type: replace Abstract: While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominan
Not just foreseeable, but foreseen and called out. We ran a campaign to get them out of the first ever AI Safety Summit. We won that one. Yet most of the field kept licking the boot of the companies a
Safety officials gained detailed data on the impact of large rocket explosions when Blue Origin's New Glenn rocket experienced an anomaly during a hot-fire test at Cape Canaveral on May 28, causing a
David Jeans / Reuters: Sources and docs detail defense tech startup Shield AI's struggles to overcome years of technical hitches and safety concerns with its V-BAT autonomous drone — A year ago, Ryan
arXiv:2602.06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications,
arXiv:2606.04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5
OpenAI outlines initiatives and commitments to enhance youth safety while creating educational and economic opportunities for young people globally. The effort emphasizes OpenAI's role in responsible
arXiv:2606.00773v1 Announce Type: new Abstract: Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety-relevant tr
AI safety can't happen behind closed doors! Super cool to see that the @AISecurityInst is releasing its evals, datasets, and models in the open on @huggingface, so researchers everywhere can scrutiniz
arXiv:2605.29340v1 Announce Type: new Abstract: In this paper, we discuss question-answer dataset for LLM safety evaluation, with a focus on illegal activities. Specifically, on the basis of manual an
arXiv:2605.29801v1 Announce Type: new Abstract: Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhi
Reuters: Former Tesla data labelers say FSD relies on laborious mapping for hazards; crash data analysis shows Tesla exaggerates FSD's safety via flawed methodology — Tesla says its Full Self-Driving
arXiv:2605.28552v1 Announce Type: new Abstract: As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle ty
arXiv:2605.26954v1 Announce Type: new Abstract: Safety evaluation of Large Language Models (LLMs) has largely focused on high-resource languages, leaving low-resource languages critically underserved.
Jared Perlo / NBC News: Illinois Legislature passes SB 315, a bill requiring annual independent third-party safety audits of leading AI companies; the bill heads to the governor's desk — The measure,
arXiv:2605.27117v1 Announce Type: new Abstract: AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing ha
arXiv:2505.11063v3 Announce Type: replace Abstract: LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly sh
Looking forward to speaking at BloombergTech next week with @shiringhaffary to discuss AI safety and our research progress at @LawZero_! Is AI development progressing too quickly? @business' @shiringh