EUVIMED · CrossrefZeitschrift
Proceedings of the AAAI Symposium Series
ISSN 2994-4317 · Association for the Advancement of Artificial Intelligence (AAAI)
Neueste Artikel
When Alignment Erases Disagreement: Preference Collapse and a Four-Valued Alternative for LLMs
Logic for Interactive Consistency: Paraconsistency, Norms, and Accountable Large Language Models
Aligning with Whom in Automated Trading? A Belnap–Dunn Four-Valued Decision Layer for Financial Forecasting Pipelines
The Pluralism Gate: When Should AI Agents Decide Under Irreducible Value Conflict?
Aligning with Whom? A Neutrosophic Paraconsistent Framework for Value Alignment under Irreducible Pluralism
Is the Ladder Measurable? Graded Paraconsistency Tested on Eight Statements and Then on a Bank
Moral Foundations Reward Modeling for Pluriversal LLM Alignment
Monitoring Before Answering: Epistemic Monitoring Improves Knowledge-Limit Recognition in Large Language Models
Grounded Reasoning for Visual Ambiguity Resolution
IMAGINE: Metacognitive Counterfactual Reasoning for Robust Adversary System Analysis
From Metacognitive Monitoring to Control: Resource Allocation in Neuro-Symbolic AI
Model-Based Testability of Dynamical Metacognitive Systems: A Radio-Frequency Case
Adaptive Metacognition in AI: From Monitoring to Learned Control
A Metacognitive Perspective on Anomaly Detection with Vision Foundation Models
Meta-Cognizing Seed AI
From Impasse to Adaptation: An Integrated LLM Supporting Meta-Cognition in a Cognitive Architecture
Metadata for Metacognition: Supporting Self-Regulation Capabilities in Soar
From Bellman to Boltzmann: Towards a Kinetic Theory of Controlled Emergence and Meta-Cognition
A Metacognitive Framework for Test-Time Adaptation: Taxonomy and Research Challenges
Metacognitive Reasoning in Energy Based Models Using Instance Based Learning Theory
Explaining Cognition and Communication in Cognitive Robots
Metacognitive(Metacognitive … (Metacognitive Aesthetics) …)): Implications for Coupled Human – AI Systems
AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes
Uncovering Default Gender Biases in Publicly Accessible LLMs Through Counter-Balancing Cloze-Task (CBCT)
Arguing Residual Risk Acceptance for E2E AI Automated Driving Systems Using Black-Box Risk-Based Testing
Soft-Label Governance for Distributional Safety in Multi-Agent Systems
Measuring Source Fidelity, Exculpatory Recall, and Generative Suspicion in AI-Drafted Police Reports
Uncovering the Security Debt of Machine Unlearning in Agentic Deployment
Auditing Evidence Claims in Federal High-Impact AI Exclusions
An Exploration of Abstention and Calibration in Assurance of Multi-class Classifiers
EUVIMED