Machine Learning

My Intrusion Detection ML Model Failed in Real Lab Testing [D]

I’m building a small ML-based cyber attack detection project using a self-created lab environment. Setup includes: GNS3 simulated network...

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

[2603.28651] Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

Abstract page for arXiv paper 2603.28651: Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

[2603.28643] The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle

Abstract page for arXiv paper 2603.28643: The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AI...

[2603.28618] Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

Abstract page for arXiv paper 2603.28618: Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

[2603.28590] MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

Abstract page for arXiv paper 2603.28590: MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language M...

[2603.28558] T-Norm Operators for EU AI Act Compliance Classification: An Empirical Comparison of Lukasiewicz, Product, and Gödel Semantics in a Neuro-Symbolic Reasoning System

Abstract page for arXiv paper 2603.28558: T-Norm Operators for EU AI Act Compliance Classification: An Empirical Comparison of Lukasiewic...

[2603.28444] Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG

Abstract page for arXiv paper 2603.28444: Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG

[2603.28386] COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

Abstract page for arXiv paper 2603.28386: COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments v...

[2603.28361] Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science

Abstract page for arXiv paper 2603.28361: Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science

[2603.28360] CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems

Abstract page for arXiv paper 2603.28360: CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems

[2603.28295] Evaluating LLMs for Answering Student Questions in Introductory Programming Courses

Abstract page for arXiv paper 2603.28295: Evaluating LLMs for Answering Student Questions in Introductory Programming Courses

[2603.28248] Reasoning as Energy Minimization over Structured Latent Trajectories

Abstract page for arXiv paper 2603.28248: Reasoning as Energy Minimization over Structured Latent Trajectories

[2603.28197] EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

Abstract page for arXiv paper 2603.28197: EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling

[2603.28183] PReD: An LLM-based Foundation Multimodal Model for Electromagnetic Perception, Recognition, and Decision

Abstract page for arXiv paper 2603.28183: PReD: An LLM-based Foundation Multimodal Model for Electromagnetic Perception, Recognition, and...

[2603.28135] CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning

Abstract page for arXiv paper 2603.28135: CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning

[2603.28062] SLOW: Strategic Logical-inference Open Workspace for Cognitive Adaptation in AI Tutoring

Abstract page for arXiv paper 2603.28062: SLOW: Strategic Logical-inference Open Workspace for Cognitive Adaptation in AI Tutoring

[2603.28052] Meta-Harness: End-to-End Optimization of Model Harnesses

Abstract page for arXiv paper 2603.28052: Meta-Harness: End-to-End Optimization of Model Harnesses

[2603.28026] When Choices Become Priors: Contrastive Decoding for Scientific Figure Multiple-Choice QA

Abstract page for arXiv paper 2603.28026: When Choices Become Priors: Contrastive Decoding for Scientific Figure Multiple-Choice QA

[2603.28015] What an Autonomous Agent Discovers About Molecular Transformer Design: Does It Transfer?

Abstract page for arXiv paper 2603.28015: What an Autonomous Agent Discovers About Molecular Transformer Design: Does It Transfer?

[2603.28010] HeteroHub: An Applicable Data Management Framework for Heterogeneous Multi-Embodied Agent System

Abstract page for arXiv paper 2603.28010: HeteroHub: An Applicable Data Management Framework for Heterogeneous Multi-Embodied Agent System

[2603.27977] SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

Abstract page for arXiv paper 2603.27977: SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology