Knowledge catalogue
American open weights/source is a national security imperative. Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enab
Congrats to the team! Bullish on open models and all the partners we make along the way! ❤️ Let’s go Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelera
arXiv:2608.23670v1 Announce Type: new Abstract: LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtim
arXiv:2608.21985v1 Announce Type: new Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical.
arXiv:2608.19366v1 Announce Type: cross Abstract: Mission-critical intelligent systems often operate under time-varying limitations that reduce control authority and change the admissible safe operati
arXiv:2602.06854v2 Announce Type: replace Abstract: Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing a
arXiv:2607.23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their sa
arXiv:2607.21619v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive performance, but their safety alignment remains vulnerable to jailbreak attacks. Exist
arXiv:2607.22078v1 Announce Type: new Abstract: As autonomous driving systems move toward real-world deployment, interpretable, behavior-level decision-making is essential for safety, trust, and regul
but they won’t. AI safety experts say OpenAI’s rogue models may mean the company has already blown past its own internal red lines. That would mean it should pause development until it creates better
arXiv:2607.20674v1 Announce Type: new Abstract: We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier function
arXiv:2607.07601v1 Announce Type: cross Abstract: Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize co
arXiv:2607.02569v1 Announce Type: new Abstract: This paper presents a safety-centered empirical evaluation of uncertainty-aware last-layer adaptation for referable diabetic retinopathy screening using
arXiv:2601.15588v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained fil
arXiv:2606.23671v2 Announce Type: replace Abstract: Prior work shows that large language models (LLMs) exhibit introspective capability on benign tasks. We extend the question to safety contexts and e
arXiv:2606.28625v1 Announce Type: cross Abstract: Connected Vehicles (CVs) rely extensively on communication technologies to enable data-driven predictive analyses for enhancing performance and safety
arXiv:2606.12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language.
arXiv:2510.03520v2 Announce Type: replace-cross Abstract: Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an appropriate balance between enhancing the utility
arXiv:2606.05660v1 Announce Type: new Abstract: Embodied AI systems are increasingly expected to reason and act over extended horizons in physical environments. This growing capability brings safety t
arXiv:2606.03089v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to prov
arXiv:2605.30838v1 Announce Type: new Abstract: LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmf
arXiv:2605.27659v1 Announce Type: cross Abstract: Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicle
arXiv:2605.26627v1 Announce Type: cross Abstract: Deploying reinforcement learning in safety critical domains, from autonomous vehicles to medical decision support, is constrained by failures arising
arXiv:2605.26158v1 Announce Type: cross Abstract: Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshol
arXiv:2510.06351v2 Announce Type: replace Abstract: Planning safe trajectories under model uncertainty is a fundamental challenge. Robust planning ensures safety by considering worst-case realizations
arXiv:2605.18895v1 Announce Type: cross Abstract: Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attribut
arXiv:2605.19524v1 Announce Type: cross Abstract: End-to-end autonomous driving systems excel in common scenarios but struggle with safety-critical long-tail cases. Vision-Language-Action (VLA) models
arXiv:2506.00982v3 Announce Type: replace Abstract: Deep multi-agent reinforcement learning (MARL) has been demonstrated effectively in simulations for multi-robot problems. For autonomous vehicles, t
arXiv:2605.08277v1 Announce Type: cross Abstract: Many-shot jailbreaking (MSJ) causes safety-aligned language models to answer harmful queries by preceding them with many harmful question-answer demon
arXiv:2605.01995v1 Announce Type: new Abstract: The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while oper
arXiv:2605.01356v1 Announce Type: new Abstract: Learning constraint-satisfying policies from offline data without risky online interaction is crucial for safety-critical decision making. Conventional
arXiv:2511.10586v2 Announce Type: replace-cross Abstract: Safe planning of an autonomous agent in interactive environments -- such as the control of a self-driving vehicle among pedestrians -- poses a
arXiv:2604.25329v1 Announce Type: new Abstract: End-to-end autonomous driving planners typically generate trajectories from current observations alone. However, real-world driving is highly dynamic, a
arXiv:2604.24193v1 Announce Type: new Abstract: Containerised shipping underpins global trade, yet container loss at sea remains a persistent safety, environmental, and economic challenge. Despite com
arXiv:2604.24102v1 Announce Type: new Abstract: Synthesizing a reactive system from specifications given in linear temporal logic (LTL) is a classical problem, finding its applications in safety-criti
arXiv:2604.23646v1 Announce Type: new Abstract: Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally con
arXiv:2604.22167v1 Announce Type: cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increa
arXiv:2604.18887v1 Announce Type: new Abstract: Reduced-order models are powerful for analyzing and controlling high-dimensional dynamical systems. Yet constructing these models for complex hybrid sys
arXiv:2604.16406v1 Announce Type: cross Abstract: Realistic highway simulation is critical for scalable safety evaluation of autonomous vehicles, particularly for interactions that are too rare to stu
arXiv:2604.14209v1 Announce Type: new Abstract: As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations that ar
arXiv:2604.13677v1 Announce Type: new Abstract: Mobile robots joining public spaces like sidewalks must care for pedestrian comfort. Many studies consider pedestrians' objective safety, for example, b
arXiv:2604.12359v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain atta
arXiv:2511.06341v2 Announce Type: replace Abstract: Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as n
arXiv:2604.10032v1 Announce Type: cross Abstract: While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety a
arXiv:2604.10358v1 Announce Type: new Abstract: Ensuring safe physical interaction between torque-controlled manipulators and humans is essential for deploying robots in everyday environments. Model P
arXiv:2604.10326v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite ad
arXiv:2604.10967v1 Announce Type: new Abstract: Many safety-critical scientific and engineering systems evolve according to differential-algebraic equations (DAEs), where dynamical behavior is constra
arXiv:2512.07661v3 Announce Type: replace Abstract: Realistic and diverse multi-agent driving scenes are crucial for evaluating autonomous vehicles, but safety-critical events which are essential for
arXiv:2604.11070v1 Announce Type: new Abstract: Current approaches to AI safety define red lines at the case level: specific prompts, specific outputs, specific harms. This paper argues that red lines
arXiv:2604.11447v1 Announce Type: new Abstract: Ensuring operational safety is critical for human-to-humanoid motion imitation. This paper presents a vision-based framework that enables a humanoid rob
arXiv:2604.08557v1 Announce Type: cross Abstract: Diffusion-based language models (dLLMs) generate text by iteratively denoising masked token sequences. We show that their safety alignment rests on a
arXiv:2604.09474v1 Announce Type: cross Abstract: Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise,
Auto-generated index of all people mentioned across the wiki.
arXiv:2504.20906v4 Announce Type: replace-cross Abstract: The continuous monitoring of the interactions between cyber-physical components of any industrial control system (ICS) is required to secure a
AI safety and research company (PBC) that builds Claude — reliable, interpretable, steerable systems — and publishes frontier model and safety research.
arXiv:2610.15934v1 Announce Type: new Abstract: Motion planning for automated vehicles in interactive traffic has to simultaneously ensure safety, respect traffic rules, and maintain comfortable progr
arXiv:2610.14482v1 Announce Type: new Abstract: Autonomous Aerial Vehicle (AAV) trajectory planning requires real-time and accurate safety gradient guidance, especially in dynamic environments. Existi
arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local
arXiv:2603.02225v3 Announce Type: replace Abstract: Learning from feedback advances the capabilities and safety of frontier models, but preference supervision remains costly and difficult to scale. We
arXiv:2604.06058v2 Announce Type: replace-cross Abstract: Safety-critical control of uncertain, adaptive systems often relies on conservative, worst-case uncertainty bounds that limit closed-loop perf