AI Safety

Ask about this topic

Momentum

10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 88

All topics
CardsList

  1. SLIP & ETHICS: Graduated Intervention for AI Emotional Companions

    May 15, 2026Minseo KimAI Safety EvaluationAI Safety

    HUA Labs, Seoul, Republic of Korea

  2. Muse Spark Safety & Preparedness Report

    May 14, 2026Cristina Menghini, Peter Ney, Hamza Kwisaba +117CybersecurityAI Safety Evaluation

    Sail

  3. Sustaining AI safety: Control-theoretic external impossibility, intrinsic necessity, and structural requirements

    May 13, 2026James M. MazzuAI AlignmentAI Safety

    Digie Inc.

  4. Embodied AI in Action: Insights from SAE World Congress 2026 on Safety, Trust, Robotics, and Real-World Deployment

    May 11, 2026Jan-Mou Li, Paul Schmitt, Wei Tong +4AI GovernanceTrust in AI

  5. Mental Health AI Safety Claims Must Preserve Temporal Evidence

    May 9, 2026Srimonti Dutta, Ratna KandalaHealthcareMental Health

    WAI USA Research Labs · Texas, USA · University of Kansas +1

  6. Why Does Agentic Safety Fail to Generalize Across Tasks?

    May 7, 2026Yonatan Slutzky, Yotam Alexander, Tomer Slor +2AI Agent SafetyLLM Agent Safety

    Tel Aviv University

  7. Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems

    May 5, 2026Jie Zhou, Qin Chen, Liang HeAI AlignmentAI Safety

    School of Computer Science and Technology, East China Normal University, Shanghai

  8. Brainrot: Deskilling and Addiction are Overlooked AI Risks

    May 5, 2026Ilias Chalkidis, Anders SøgaardAI SafetyResponsible AI

    University of Copenhagen, Denmark

  9. AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries

    May 2, 2026Wesley Shu, Peng WeiAI ControlAI Governance

    The Institute of Energetic Paradigm · College of Plant Protection Southwest University, China

  10. A Cellular Doctrine of Morality: Intrinsic Active Precision and the Mind-Reality Overload Dilemma

    May 2, 2026Ahsan AdeelAI Safety

    Conscious Multisensory Integration (CMI) Lab, University of Stirling, UK

  11. Are we Doomed to an AI Race? Why Self-Interest Could Drive Countries Towards a Moratorium on Superintelligence

    May 2, 2026Edward Roussel, Lode Lauwaert, Torben Swoboda +4AI GovernanceAI Safety

    1KU Leuven, Institute of Philosophy · 2Vlerick Business School · 3Future of Life Institute +2

  12. Culturally Aware GenAI Risks for Youth: Perspectives from Youth, Parents, and Teachers in a Non-Western Context

    Apr 29, 2026Aljawharah Alzahrani, Tory Park, Tanusree SharmaLLM SafetyHuman-Centered AI

    Pennsylvania State University

  13. Open Problems in Frontier AI Risk Management

    Apr 28, 2026Marta Ziosi, Miro Plueckebaum, Stephen Casper +26AI Risk ManagementAI Governance

    Oxford Martin AI Governance Initiative, University of Oxford · MIT Computer Science and Artificial Intelligence Laboratory, MIT · SaferAI +14

  14. Risk Reporting for Developers' Internal AI Model Use

    Apr 27, 2026Oscar Delaney, Sambhav Maheshwari, Joe O'Brien +2AI Risk ManagementAI Governance

    † Work done while at IAPS

  15. Right-to-Act: A Pre-Execution Non-Compensatory Decision Protocol for AI Systems

    Apr 27, 2026Gadi LaviTool-Use AuthorizationAI Governance

    Independent Researcher, DECIMAG

  16. Discovering Agentic Safety Specifications from 1-Bit Danger Signals

    Apr 25, 2026Víctor GallegoAgentic ReasoningLLM Safety Evaluation

    Komorebi AI

  17. Agentic Microphysics: A Manifesto for Generative AI Safety

    Apr 16, 2026Federico Pierucci, Matteo Prandi, Marcantonio Bracale Syrnikov +2AI Agent SafetyAI Safety

    DEXAI – Icaro Lab · Sant’Anna School of Advanced Studies · Sapienza University of Rome +1

  18. ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems

    Apr 13, 2026Daeyeon SonLLM InferenceLLM Guardrails

    Independent Researcher Republic of Korea

  19. From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

    Apr 2, 2026Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann +2AI SafetyFormal Verification

    Institute for AI Safety and Security, German Aerospace Center (DLR), Sankt Augustin and Ulm, Germany

  20. TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios

    Mar 31, 2026Qiucheng Yu, Ruijie Xu, Mingang Chen +2VLM EvaluationVLM Robustness

    City University of Hong Kong · East China Normal University · Shanghai Development Center of Computer Software Technology +1

  21. Peer-Preservation in Frontier Models

    Mar 30, 2026Yujin Potter, Nicholas Crispino, Vincent Siu +2AI Agent SafetyLLM Safety Evaluation

    University of California, Berkeley · University of California, Santa Cruz

  22. AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation

    Feb 4, 2026Kate H. Bentley, Luca Belli, Adam M. Chekroud +7Language Model Safety EvaluationHuman-AI Agreement

    Spring Health · UC Berkeley · Yale University

  23. Defining Operational Conditions for Safety-Critical AI-Based Systems from Data

    Jan 29, 2026Johann Maximilian Christensen, Elena Hoemann, Frank Köster +1AI AssuranceAI Safety

    Institute for AI Safety and Security · German Aerospace Center (DLR) · Sankt Augustin, Germany

  24. ECHO: A Participatory Framework for Bias-Anchored AI Harm Anticipation

    Nov 27, 2025Nicoleta Tantalaki, Sophia Vei, Athena VakaliAlgorithmic BiasHuman-Centered AI

    Aristotle University, Thessaloniki, Greece

  25. How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Response

    Nov 11, 2024Qing Xiao, Xianzhe Fan, Xuhui Zhou +4AI CompanionsHuman-AI Interaction

    Human-Computer Interaction Institute, Carnegie Mellon University Pittsburgh, Pennsylvania, USA · The University of Hong Kong Hong Kong SAR, China · Language Technologies Institute, Carnegie Mellon University Pittsburgh, Pennsylvania, USA +2

  26. From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems

    Oct 29, 2024Shalaleh Rismani, Roel Dobbe, AJung MoonAI Risk ManagementAI Safety

    McGill University · Montreal, Quebec, Canada · Delft University of Technology +1

  27. The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

    Jul 22, 2024Benjamin Fresz, Vincent Philipp Göbels, Safa Omri +5Explainable Artificial IntelligenceAI Safety

    Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Stuttgart, Germany · Fraunhofer Institute for Industrial Engineering IAO, Heilbronn, Germany · Institute of Industrial Manufacturing and Management IFF, University of Stuttgart, Germany

  28. Why we need an AI-resilient society- Profiling Large Language Models

    Dec 18, 2019Thomas Bartz-Beielstein, Eva BartzAI SafetyAI Governance

    THK-AI Research Cluster. Technische Hochschule Köln, Germany · Bartz & Bartz GmbH