Knowledge catalogue
If extremely violent criminals are not imprisoned, eventually they will murder innocent people This bodega owner told ABC a year ago that he fears for his safety in NY Last night, he was kiIIed by a s
Are LLMs really more important than fire or electricity? “Honestly, a ton of what we’ve developed in my lifetime amounts to scaling up the delivery of information and entertainment and the frictionles
arXiv:2503.16416v2 Announce Type: replace Abstract: LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environ
arXiv:2604.20166v1 Announce Type: new Abstract: Building trustworthy AI systems for mental health support is a shared priority across stakeholders from multiple disciplines. However, 'trustworthy' rem
arXiv:2604.20728v1 Announce Type: new Abstract: Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified. We study shielding for this setting
arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an im
arXiv:2510.26782v3 Announce Type: replace-cross Abstract: A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical
arXiv:2604.19538v1 Announce Type: new Abstract: Agentic AI, with goal-directed, proactive, and autonomous decision-making capabilities, offers a compelling opportunity to address movement-related risk
arXiv:2604.19301v1 Announce Type: new Abstract: The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-
arXiv:2604.17053v1 Announce Type: new Abstract: Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Resea
arXiv:2604.16358v1 Announce Type: cross Abstract: MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploi
arXiv:2509.10692v3 Announce Type: replace Abstract: This paper presents a motion planning and risk analysis framework for enhancing human-robot collaboration with a Multi-Rotor Aerial Vehicle. The pro
arXiv:2604.15705v1 Announce Type: new Abstract: Reinforcement Fine-Tuning (RFT) has established itself as a critical paradigm for the alignment of Multi-modal Large Language Models (MLLMs) with comple
arXiv:2604.14163v1 Announce Type: new Abstract: Maritime distress communications transmitted over very high frequency (VHF) radio are safety-critical voice messages used to report emergencies at sea.
NHTSA autonomous vehicle crash data has been updated through March 15, 2026, for AVs including Tesla Robotaxi. This includes unsupervised Tesla-driven robotaxis. • Waymo: 58 incidents • Zoox: 3 incide
arXiv:2604.10598v1 Announce Type: new Abstract: Human-in-the-loop (HITL) UAV operation is essential in complex and safety-critical aerial surveying environments, where human operators provide navigati
arXiv:2603.12277v3 Announce Type: replace-cross Abstract: Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: mode
arXiv:2604.10933v1 Announce Type: cross Abstract: Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications.
arXiv:2508.11290v3 Announce Type: replace Abstract: LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful
arXiv:2604.08846v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prom
arXiv:2510.00938v2 Announce Type: replace Abstract: Large reasoning models (LRMs) 'think' by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the abili
arXiv:2604.07039v1 Announce Type: cross Abstract: Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either
arXiv:2604.07457v1 Announce Type: new Abstract: While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global
arXiv:2604.07655v1 Announce Type: cross Abstract: Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yield
arXiv:2604.06571v1 Announce Type: cross Abstract: Missing-person and child-safety investigations rely on heterogeneous case documents, including structured forms, bulletin-style posters, and narrative
arXiv:2604.06502v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration.
Enterprises are rapidly moving AI workloads from experimentation to production on Google Kubernetes Engine (GKE), using its scalability to serve powerful inference endpoints. However, as these models
* **What it likely covers:** This entry likely discusses contemporary concerns regarding the safety and restriction of freedom of speech or civil liberties, drawing a parallel between past discus...
arXiv:2610.21108v1 Announce Type: new Abstract: LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a
arXiv:2610.21189v1 Announce Type: new Abstract: Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free
arXiv:2602.03737v2 Announce Type: replace Abstract: Monitoring bottom-hole variables in petroleum wells is essential for production optimization, safety, and emissions reduction. Permanent Downhole Ga
arXiv:2610.19815v1 Announce Type: new Abstract: Dynamical system (DS)-based learning from demonstration generates flexible robot motions, but existing guarantees rely on certificate generation to obta
arXiv:2610.18948v1 Announce Type: cross Abstract: Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize
arXiv:2610.17544v1 Announce Type: cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted mem
arXiv:2610.19817v1 Announce Type: new Abstract: Human values shape how we expect language models to behave. Dominant alignment approaches treat values as global objectives, although the appropriate va
arXiv:2610.17907v1 Announce Type: cross Abstract: The code generation capabilities of large language models (LLMs) can equally be misused to implement harmful functionality, underscoring the need to u
arXiv:2601.07239v2 Announce Type: replace Abstract: Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As la
arXiv:2610.15359v1 Announce Type: new Abstract: Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified
arXiv:2610.16471v1 Announce Type: new Abstract: Video anomaly detection (VAD) identifies deviations from normal patterns, but such deviations do not necessarily correspond to safety-critical events. W
arXiv:2610.15122v1 Announce Type: new Abstract: Ensuring the safety of autonomous Unmanned Aerial Vehicles (UAVs) operating in underground mines is challenging due to the vast and uncertain Operationa
arXiv:2610.18066v1 Announce Type: new Abstract: Reliable uncertainty evaluation is essential for assessing the trustworthiness of machine learning (ML) predictions, particularly in safety-critical app
arXiv:2610.18842v1 Announce Type: cross Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive S
arXiv:2610.13737v1 Announce Type: cross Abstract: Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure th
arXiv:2610.11586v1 Announce Type: new Abstract: Existing evaluation methods for healthcare LLMs primarily assess factual correctness,safety, and fluency, while providing limited insight into whether g
arXiv:2610.11942v1 Announce Type: new Abstract: A login screen that appears after a tap on Sign in is expected; the same screen after a tap on View order is an attack. For GUI agents, safety is theref
arXiv:2610.11580v1 Announce Type: new Abstract: Accurate trajectory forecasting and well-defined predictive uncertainty are crucial for reliable, safety-critical applications such as autonomous drivin
arXiv:2603.18166v1 Announce Type: cross Abstract: Crowd trajectory prediction plays a crucial role in public safety and management, where it can help prevent disasters such as stampedes. Recent works
arXiv:2610.09941v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are increasingly deployed in safety-critical applications, yet they remain vulnerable to backdoor attacks. Defendin
arXiv:2610.10526v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-languag
arXiv:2610.09034v1 Announce Type: cross Abstract: Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roa
arXiv:2610.08123v1 Announce Type: cross Abstract: End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain diffi
arXiv:2610.07882v1 Announce Type: new Abstract: Off-road navigation exposes a robot to potentially hazardous terrain en route. Although learning-based navigation uses safety supervision to choose whic
arXiv:2610.08331v1 Announce Type: cross Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exi
arXiv:2610.08043v1 Announce Type: new Abstract: Ensuring safety in autonomous driving requires continuous map maintenance supported by reliable quality indicators. In this context, it is crucial to id
arXiv:2610.05749v1 Announce Type: new Abstract: This article introduces an innovative system that integrates landmark identification with deep learning to enhance fall detection accuracy and reliabili
arXiv:2610.03759v1 Announce Type: cross Abstract: Ocean wave forecasting is essential for maritime safety, offshore operations, and coastal resilience, yet remains challenging due to systematic biases
arXiv:2610.02520v1 Announce Type: cross Abstract: We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constrain
arXiv:2610.02378v1 Announce Type: new Abstract: In Recirculating Aquaculture Systems (RAS), precision feeding is critical for minimizing costs and improving fish welfare. However, existing methods lac
Elon was thinking about superintelligence long before anyone in the mainstream even understood where superintelligence was heading He was deeply involved in the conversation around Nick Bostrom’s Supe
arXiv:2610.00568v1 Announce Type: cross Abstract: Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between cap