No article text was recorded for this version.
situational safety awareness
Version 1 of 150 papers78 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challenges
- Blog: SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents
- Blog: HomeSafeBench: A Benchmark for Embodied Vision-Language Models in Free-Exploration Home Safety Inspection
- Blog: Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization
- Blog: Towards quantitative modeling of task confirmations in human-robot dialog
- Blog: AIR: Improving Agent Safety through Incident Response
- Blog: Safety Guardrails for LLM-Enabled Robots
- Blog: Is Your Multimodal Language Model Oversensitive to Safe Queries?
- Blog: Multimodal Situational Safety
- Blog: Jailbreaking LLM-Controlled Robots
- Blog: System Safety Monitoring of Learned Components Using Temporal Metric Forecasting
- Blog: EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
- Blog: Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
- Blog: Semantically Guided Scene Generation via Contextual Reasoning and Algebraic Measures
- Blog: HowLLMDecision Agents Fail in the Wild: AReproducible Failure-Cell Framework
- Blog: Visionary Co-Driver: Enhancing Driver Perception of Potential Risks with LLM and HUD
- Blog: Multimodal Situational Safety
- Blog: Potential Fields as Scene Affordance for Behavior Change-Based Visual Risk Object Identification
- Blog: Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation
- Blog: Task-Aware Risk Estimation of Perception Failures for Autonomous Vehicles
- Blog: CrowdRadar: a mobile crowdsensing framework for urban traffic green travel safety risk assessment
- Blog: Towards Computational Foreseeability
- Blog: Anticipatory Thinking Challenges in Open Worlds: Risk Management
- Blog: Egocentric human-object interaction in industrial scenarios: a case study
- Blog: Detecting and Mitigating System-Level Anomalies of Vision-Based Controllers
- Blog: Future Outdoor Safety Monitoring: Integrating Human Activity Recognition with the Internet of Physical–Virtual Things
- Blog: Discovering Agentic Safety Specifications from 1-Bit Danger Signals
- Blog: DriveSOTIF: Advancing Perception SOTIF Through Multimodal Large Language Models
- Blog: Risk Assessment for Nonlinear Cyber-Physical Systems under Stealth Attacks
- Blog: Gemini Robotics: Bringing AI into the Physical World
- Blog: Steering Multimodal Large Language Models Decoding for Context-Aware Safety
- Blog: Mitigating Covertly Unsafe Text within Natural Language Systems
- Blog: ML-driven Malware that Targets AV Safety
- Blog: Teaching Robots to "Get It Right"
- Blog: Safety Aware Task Planning via Large Language Models in Robotics
- Blog: The Concept of Criticality in AI Safety
- Blog: From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents
- Blog: Auxiliary tasks to improve trip hazard affordance detection on construction sites
- Blog: SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents
- Blog: RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
- Blog: Generating Robot Constitutions & Benchmarks for Semantic Safety
- Blog: Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
- Blog: SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
- Blog: Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making
- Blog: Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguards
- Blog: Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological Rewards
- Blog: WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
- Blog: Being safe around the robot
- Blog: Semantic-Metric Bayesian Risk Fields: Learning Robot Safety from Human Videos with a VLM Prior
- Blog: CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
History & citation
Current · Permanent link
- This direction split from Situational Safety for Embodied and Agentic AI (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_situational_safety_awareness_496f676e,
title = {situational safety awareness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/situational-safety-awareness/rdr_496f676e4a984f6dbd245fa5f986e472},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_situational_safety_awareness_496f676e_v1,
title = {situational safety awareness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/situational-safety-awareness/rdr_496f676e4a984f6dbd245fa5f986e472/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}