Knowledge catalogue
arXiv:2610.07518v1 Announce Type: cross Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of a
arXiv:2610.07167v1 Announce Type: cross Abstract: We propose an imitation-learning design for neural-network control policies under state and input constraints. Training alternates a standard imitatio
arXiv:2610.07125v1 Announce Type: cross Abstract: While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important con
arXiv:2610.07599v1 Announce Type: cross Abstract: In this paper, we study robust decision-making in the latent space of world models (WMs). Robust optimization is a mathematical framework where, given
arXiv:2610.07474v1 Announce Type: new Abstract: Safe crowd navigation under distribution shift requires uncertainty representations that capture structured human-motion prediction errors and safety ob
arXiv:2610.05733v1 Announce Type: new Abstract: Autonomous social navigation requires balancing efficiency, physical safety, and social compliance. Reinforcement Learning (RL) methods provide a viable
arXiv:2610.04569v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical settings, yet their black-box nature makes it difficult to provide formal gu
arXiv:2610.06503v1 Announce Type: new Abstract: Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, system
arXiv:2510.18643v3 Announce Type: replace Abstract: Control Barrier Functions (CBFs) can provide provable safety guarantees for dynamic systems. However, finding a valid CBF for a system of interest i
arXiv:2610.06211v1 Announce Type: new Abstract: Learned models for industrial control are usually judged by aggregate accuracy, but accuracy at the component level does not guarantee safety once it is
arXiv:2610.04088v1 Announce Type: cross Abstract: Before autonomous driving systems can be deployed on public roads, it is vital that these systems comply with safety standards, traffic rules, and soc
arXiv:2610.02341v1 Announce Type: new Abstract: Safe whole-body motion is essential for deploying humanoid robots in unstructured environments. Modern humanoid control commonly separates reference spe
Powerful testimony from ex Google DeepMind researcher @Turn_Trout at NYC Hearing on AI, about how he tried to get Google to commit to AI safety, and how Google, sadly including Demis Hassabis, ultimat
arXiv:2610.03132v1 Announce Type: cross Abstract: Generative planners based on diffusion/flow matching can learn to synthesize long-horizon trajectories from demonstrations. However, real-world deploy
arXiv:2610.01436v1 Announce Type: new Abstract: Artificial intelligence systems are increasingly deployed in high impact and safety critical settings, yet security assessment remains difficult to repr
arXiv:2610.01581v1 Announce Type: new Abstract: Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they ofte
arXiv:2610.01028v1 Announce Type: cross Abstract: Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely o
arXiv:2606.22676v2 Announce Type: replace Abstract: Refusal on a safety benchmark does not reveal how stable that behavior will remain after model updates. Benign downstream fine-tuning can weaken ref
arXiv:2609.38411v1 Announce Type: new Abstract: Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of hu
arXiv:2609.38810v1 Announce Type: cross Abstract: As vision language models are increasingly deployed in clinical diagnosis, understanding how they internally resolve competing visual and textual sign
arXiv:2609.38282v1 Announce Type: new Abstract: Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness. Sequ
arXiv:2601.08355v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for saf
Generated with H3: Mock H3 version of the ending to Wargames(83) as a test of a custom node I've been working on w/ both Claude(Opus/Fable) and OAI's Sol/Astra. One click generation using only 4 movie
arXiv:2505.03761v2 Announce Type: replace Abstract: Soft robots promise inherent safety via their material compliance for seamless interactions with humans or delicate environments. Despite progress,
arXiv:2609.36562v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, their reliability is threatened by multimodal imp
arXiv:2609.37537v1 Announce Type: new Abstract: Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive ret
arXiv:2609.34145v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) gives vision--language driving systems access to external safety knowledge, yet a retrieved risk rule may be releva
arXiv:2609.33671v1 Announce Type: cross Abstract: When must a foundation-model safety gateway generate tokens, and when should it directly output a calibrated decision? We study calibrated standalone
arXiv:2308.09456v2 Announce Type: replace Abstract: Overtaking on two-lane roads is a safety-critical decision-making problem for autonomous vehicles, since oncoming traffic may force the ego vehicle
arXiv:2609.30940v1 Announce Type: new Abstract: Individually protective decisions can produce avoidable collective failures. As large language model (LLM) agents take on greater roles in financial dec
** Built to align with NVIDIA’s Agent Safety Platform strategy for securing autonomous agents When an agent handles confidential material, it needs enough access to do the job and nothing else. The ha
It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in conflict. Safety is how trust is earned.' Today, with over 100 in
Calculators “may be deserving of important rights”, too! NEW: Dario Amodei has said that AI systems 'may be deserving of important rights.' Anthropic's top safety researchers argue AI may be 'justifie
arXiv:2508.20661v5 Announce Type: replace Abstract: Traversing narrow paths is challenging for humanoid robots due to the sparse and safety-critical footholds required. Purely template-based or end-to
arXiv:2609.26130v1 Announce Type: new Abstract: Crack detection is a crucial process to ensure the safety and longevity of buildings and other infrastructure. In this paper, we developed a low-cost, a
arXiv:2609.25257v1 Announce Type: cross Abstract: Safety evaluation in sampling-based stochastic model predictive control often requires numerical estimation of exit functionals. The approximation of
arXiv:2609.25756v1 Announce Type: new Abstract: Precision medical robotics demands adaptive decision-making under strict safety, interpretability, and execution constraints. Although recent Vision-Lan
arXiv:2609.25945v1 Announce Type: new Abstract: The field of Artificial Intelligence has been adopted for many application domains. Vision Language Models are one of the recently advanced AI technique
arXiv:2609.24250v1 Announce Type: new Abstract: The shipping industry has a significant impact on the global economy, emphasizing the need for operational availability and safety through the use of ef
arXiv:2609.24376v1 Announce Type: new Abstract: We propose a safety-critical framework for the cooperative transportation of passive targets in microgravity, where a team of chaser robots acts through
arXiv:2609.23100v1 Announce Type: new Abstract: Where to look and how to move? A robot navigating an unmapped environment must do both at once, and the two goals pull against each other. The regions m
arXiv:2609.23071v1 Announce Type: cross Abstract: This thesis proposes a framework for 'responsible intelligence' to address AI's critical challenges in safety, ethics, and cultural sensitivity. It ad
The Information: Source: before the Hugging Face incident, OpenAI was negotiating a legally binding deal with Anthropic for the companies to stress-test each other's models — OpenAI is rethinking a ra
arXiv:2609.20822v1 Announce Type: cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built
Baseten launched a new safety infrastructure standard alongside its Base Labs research arm on Wednesday, partnering with Hugging Face and Goodfire AI to build safety evaluation and monitoring infrastr
arXiv:2609.19330v1 Announce Type: new Abstract: Autonomous robots operating in partially observed environments must navigate safely while acquiring observations that improve future planning. Existing
arXiv:2609.19449v1 Announce Type: new Abstract: Robots must complete their tasks and maintain the achieved outcomes while avoiding safety failures at all times. Strict reach-avoid-stay (sRAS) formaliz
arXiv:2609.18128v1 Announce Type: new Abstract: Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orche
arXiv:2609.17247v1 Announce Type: new Abstract: An agentic AI driver-assistance framework that integrates perception, compliance reasoning, vehicle-state interpretation, and safety arbitration into a
arXiv:2609.17499v1 Announce Type: cross Abstract: Uncertainty estimation for Vision-Language-Navigation (VLN) models is a critical task since it can help identify ambiguous and unreliable predictions,
arXiv:2609.16454v1 Announce Type: new Abstract: Recent work by Doshi and Hauser (2024), Bisbee et al. (2024), and Xie et al. (2026) raises concerns that outputs from large language models (LLMs) tend
arXiv:2507.23136v2 Announce Type: replace Abstract: Many prediction tasks can admit multiple models that can perform almost equally well. This phenomenon can undermine interpretability and safety when
arXiv:2609.15134v1 Announce Type: new Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through ru
arXiv:2603.09460v2 Announce Type: replace Abstract: Efficiently learning safe and agile quadruped navigation in densely cluttered environments remains difficult: existing methods often lack safety and
arXiv:2609.14258v1 Announce Type: new Abstract: Vision-language models (VLMs) remain vulnerable to jailbreaks that distribute harmful intent across text and images, making unimodal safety mechanisms i
arXiv:2609.12831v1 Announce Type: cross Abstract: As the number of autonomous robots continues to grow, safety becomes increasingly important. Control barrier functions (CBFs) provide a theoretically
Anthropic CEO Dario Amodei says the time has come to slow down AI development and will give third-party evaluators like METR access to its models to help ensure its 'adherence to safety practices and
arXiv:2609.11697v1 Announce Type: new Abstract: Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in general-purpose robotic manipulation, yet their gen
arXiv:2609.08256v1 Announce Type: cross Abstract: Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built a
arXiv:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box generators---are increasingly deployed behind runtime verifi