Machine Learning

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

Improving AI models’ ability to explain their predictions

New technique makes AI models leaner and faster while they’re still learning

[2604.03291] RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models

Abstract page for arXiv paper 2604.03291: RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models

[2604.03289] Toward Artificial Intelligence Enabled Earth System Coupling

Abstract page for arXiv paper 2604.03289: Toward Artificial Intelligence Enabled Earth System Coupling

[2604.03272] Artificial Intelligence and Systemic Risk: A Unified Model of Performative Prediction, Algorithmic Herding, and Cognitive Dependency in Financial Markets

Abstract page for arXiv paper 2604.03272: Artificial Intelligence and Systemic Risk: A Unified Model of Performative Prediction, Algorith...

[2604.03267] A reconfigurable smart camera implementation for jet flames characterization based on an optimized segmentation model

Abstract page for arXiv paper 2604.03267: A reconfigurable smart camera implementation for jet flames characterization based on an optimi...

[2604.03263] LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

Abstract page for arXiv paper 2604.03263: LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling

[2604.03260] Why Attend to Everything? Focus is the Key

Abstract page for arXiv paper 2604.03260: Why Attend to Everything? Focus is the Key

[2604.03258] SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

Abstract page for arXiv paper 2604.03258: SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model C...

[2604.03257] Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation

Abstract page for arXiv paper 2604.03257: Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation

[2604.03254] Is your AI Model Accurate Enough? The Difficult Choices Behind Rigorous AI Development and the EU AI Act

Abstract page for arXiv paper 2604.03254: Is your AI Model Accurate Enough? The Difficult Choices Behind Rigorous AI Development and the ...

[2604.03249] BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI Models

Abstract page for arXiv paper 2604.03249: BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI Models

[2604.03247] Classifying Problem and Solution Framing in Congressional Social Media

Abstract page for arXiv paper 2604.03247: Classifying Problem and Solution Framing in Congressional Social Media

[2604.03246] Personalized AI Practice Replicates Learning Rate Regularity at Scale

Abstract page for arXiv paper 2604.03246: Personalized AI Practice Replicates Learning Rate Regularity at Scale

[2604.03245] FVRuleLearner: Operator-Level Reasoning Tree (OP-Tree)-Based Rules Learning for Formal Verification

Abstract page for arXiv paper 2604.03245: FVRuleLearner: Operator-Level Reasoning Tree (OP-Tree)-Based Rules Learning for Formal Verifica...

[2604.03237] The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance

Abstract page for arXiv paper 2604.03237: The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance

[2311.12882] LLMs-Healthcare : Current Applications and Challenges of Large Language Models in various Medical Specialties

Abstract page for arXiv paper 2311.12882: LLMs-Healthcare : Current Applications and Challenges of Large Language Models in various Medic...

[2604.04878] Learning, Potential, and Retention: An Approach for Evaluating Adaptive AI-Enabled Medical Devices

Abstract page for arXiv paper 2604.04878: Learning, Potential, and Retention: An Approach for Evaluating Adaptive AI-Enabled Medical Devices

[2604.04876] Incompleteness of AI Safety Verification via Kolmogorov Complexity

Abstract page for arXiv paper 2604.04876: Incompleteness of AI Safety Verification via Kolmogorov Complexity

[2604.04853] MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

Abstract page for arXiv paper 2604.04853: MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

[2604.04749] AI Trust OS -- A Continuous Governance Framework for Autonomous AI Observability and Zero-Trust Compliance in Enterprise Environments

Abstract page for arXiv paper 2604.04749: AI Trust OS -- A Continuous Governance Framework for Autonomous AI Observability and Zero-Trust...

[2604.04651] Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents

Abstract page for arXiv paper 2604.04651: Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents