Knowledge catalogue
arXiv:2605.10293v1 Announce Type: cross Abstract: In offline reinforcement learning (RL), we learn policies from fixed datasets without environment interaction. The major challenges are to provide gua
arXiv:2605.09772v1 Announce Type: cross Abstract: This paper proposes a safe data-driven control framework for nonlinear systems with partially known dynamics. The method ensures stability and constra
arXiv:2605.10715v1 Announce Type: new Abstract: Landslide monitoring and simulation play an important role in urban safety assessment and disaster prevention. Existing landslide simulation pipelines t
arXiv:2605.10579v1 Announce Type: new Abstract: Training AI agents to proactively assist humans in daily activities, from routine household tasks to urgent safety situations, requires large-scale visu
arXiv:2603.25074v2 Announce Type: replace Abstract: Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Ne
arXiv:2605.07032v1 Announce Type: cross Abstract: The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening. Adversa
arXiv:2605.07837v1 Announce Type: cross Abstract: Decision Trees (DTs) are widely used in safety-critical domains such as medical diagnosis, valued for their interpretability and effectiveness on tabu
arXiv:2512.05439v2 Announce Type: replace Abstract: As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model
arXiv:2605.07883v1 Announce Type: new Abstract: Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often l
arXiv:2605.07690v1 Announce Type: new Abstract: Time-series anomaly detection is critical for ensuring safety in high-stakes applications, where robustness is a fundamental requirement rather than a m
arXiv:2605.07062v1 Announce Type: cross Abstract: AI agents are assuming active roles in Continuous Integration and Continuous Deployment (CI/CD) workflows, yet the research community lacks a shared v
arXiv:2605.06696v1 Announce Type: new Abstract: Collections of interacting AI agents can form coalitions, creating emergent group-level organization that is critical for AI safety and alignment. Howev
arXiv:2605.07925v1 Announce Type: new Abstract: Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and em
arXiv:2605.07835v1 Announce Type: new Abstract: Multi-robot systems in automated warehouses must manage continuous streams of pickup-and-delivery tasks while ensuring efficiency and safety. Prior work
arXiv:2509.26272v3 Announce Type: replace Abstract: The rapid rise of synthetic media has made deepfake detection a critical challenge for online safety and trust. Progress remains constrained by the
This post likely discusses the proliferation of AI bots and chatbot applications while arguing that despite their abundance, many demonstrate reasonable safety practices or alignment with human values
arXiv:2605.04327v1 Announce Type: new Abstract: We propose an architecture for integrating high-level, human-provided safety rules and operator-aligned semantic preferences into autonomous robot navig
Gary Marcus posted on X (formerly Twitter) requesting that Bloomberg update outdated information, likely regarding AI safety, regulation, or related technological topics that Marcus frequently discuss
arXiv:2605.04295v1 Announce Type: new Abstract: LLMs' overconfidence, particularly when hallucinating, poses a significant challenge for the deployment of the models in safety-critical settings and ma
arXiv:2605.03409v1 Announce Type: new Abstract: We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that c
arXiv:2506.04680v2 Announce Type: replace Abstract: During the development of wearable exoskeletons, evaluations involving human subjects pose inherent safety risks. Therefore, systematic testing is o
arXiv:2604.06132v2 Announce Type: replace Abstract: Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing
arXiv:2605.02488v1 Announce Type: new Abstract: Several applications demand the timely detection of critical situations, such as threats to safety and transparency, over high-velocity streams of symbo
arXiv:2605.02983v1 Announce Type: new Abstract: Self-adaptive robots operate in dynamic, unpredictable environments where unaddressed uncertainties can lead to safety violations and operational failur
arXiv:2605.03135v1 Announce Type: new Abstract: Standard classification treats all errors equally, but in content moderation, medical screening, and safety-critical applications, mistakes on clear-cut
arXiv:2605.02908v1 Announce Type: new Abstract: Understanding how textual embeddings contribute to memorization in text-to-image diffusion models is crucial for both interpretability and safety. This
Mira Murati, OpenAI's former CTO, has testified under oath that CEO Sam Altman lied to her about the safety standards for a new AI model. In a video deposition shown during the ongoing Musk v. Altman
Mira Murati’s testimony is gripping – and what it makes absolutely clear is how utterly wrong most of Twitter was about why Sam was fired. – It had nothing per se to do with AI safety - It had nothing
arXiv:2605.01710v1 Announce Type: new Abstract: AI products often route requests through version aliases, service tiers, tool choices, regional endpoints, fallback rules, or safety handling before res
arXiv:2605.02946v1 Announce Type: new Abstract: Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly
arXiv:2509.20102v2 Announce Type: cross Abstract: Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems. However, existing methods are often
arXiv:2605.01222v1 Announce Type: new Abstract: Signal Temporal Logic (STL) offers verifiable task specifications and is crucial for safety-critical control. Yet STL planning remains challenging: exac
arXiv:2605.01888v1 Announce Type: new Abstract: Accurate 3D object detection is essential for ensuring the safety of autonomous vehicles. Cooperative perception, which leverages vehicle-to-everything
arXiv:2605.00055v1 Announce Type: cross Abstract: We report a safety incident in a deployed multi-agent research system in which a primary AI agent installed 107 unauthorized software components, over
arXiv:2605.01451v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly being integrated into high-stakes public safety systems, including emergency call triage and dispatch decision
arXiv:2605.00248v1 Announce Type: new Abstract: A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with c
arXiv:2601.04376v3 Announce Type: replace Abstract: Reliable stress recognition is critical in applications such as medical monitoring and safety-critical systems, including real-world driving. While
arXiv:2410.08491v2 Announce Type: replace Abstract: Automated vehicles promise to enhance transportation safety and efficiency. However, ensuring their reliability in real-world conditions remains cha
arXiv:2605.02580v1 Announce Type: new Abstract: Recognizing unknown objects is crucial for safety-critical applications such as autonomous driving and robotics. Open-Set Panoptic Segmentation (OPS) ai
arXiv:2509.21173v5 Announce Type: replace Abstract: Vision-Language Models (VLMs) such as CLIP have revolutionized zero-shot classification and safety-critical tasks, including Out-of-Distribution (OO
arXiv:2605.02716v1 Announce Type: new Abstract: Autonomous driving technology has rapidly evolved over the past decade, offering significant improvements in transportation efficiency, safety, and cost
arXiv:2602.07784v3 Announce Type: replace Abstract: Camera-based adaptive traffic signal control is inherently partially observable: detections can be missed, vehicle speeds and distances can be noisy
arXiv:2605.00059v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) finds extensive application in autonomous drone navigation within complex, high-risk environments. However, its practi
arXiv:2605.00436v1 Announce Type: new Abstract: Concerns with the safety and reliability of applying large-language models (LLMs) in unpredictable real-world applications motivate this study, which ex
arXiv:2605.00553v1 Announce Type: new Abstract: Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effec
arXiv:2605.00364v1 Announce Type: new Abstract: Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existin
arXiv:2604.27019v1 Announce Type: cross Abstract: Safety-aligned language models must refuse harmful requests without collapsing into broad over-refusal, but the training-time mechanisms behind this t
arXiv:2505.22798v3 Announce Type: replace-cross Abstract: The growing reliance on artificial intelligence in safety- and security-critical applications is raising concerns about the robustness of neur
This post references an interview featuring Elon Musk and Sam Altman discussing AI safety, existential risks, and the future of humanity, with an unconventional or humorous element involving goblins.
arXiv:2506.22500v2 Announce Type: replace-cross Abstract: Automated identification of surgical safety risks is critical for improving patient outcomes; however, Multimodal Large Language Models (MLLMs
arXiv:2604.27168v1 Announce Type: new Abstract: We present the Field of Safe Motion (FSM), a quantitative safety model for determining whether a driver maintains a collision-free escape route, or 'out
arXiv:2604.25963v1 Announce Type: new Abstract: Vehicle platooning has attracted increasing attention as a promising approach to improve traffic efficiency, energy consumption, and roadway safety thro
arXiv:2604.25965v1 Announce Type: cross Abstract: Deep learning models are widely deployed in safety-critical domains, but remain vulnerable to adversarial attacks. In this paper, we study the adversa
arXiv:2506.13116v2 Announce Type: replace-cross Abstract: Crime hotspot prediction is critical for ensuring urban safety and effective law enforcement, it remains challenging due to complex spatial de
arXiv:2504.13529v4 Announce Type: replace Abstract: Existing black-box portfolio management systems are prevalent in the financial industry due to commercial and safety constraints, though their perfo
arXiv:2506.16742v3 Announce Type: replace Abstract: To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information
arXiv:2604.25203v1 Announce Type: new Abstract: Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs
arXiv:2512.20677v4 Announce Type: replace-cross Abstract: The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically eval
arXiv:2602.11075v2 Announce Type: replace Abstract: Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic
Scary that he doesn’t know this. Elon Musk just said on the witness stand that he doesn't know what a 'safety card' is with regard to AI development... 'Why would it be a card?' He also says he doesn'