Machine Learning

AI training rolled out for Kilifi teachers, learners

Education in Kilifi County has received a major boost following the rollout of an Artificial Intelligence (AI) training initiative target...

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

[2604.04190] Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

Abstract page for arXiv paper 2604.04190: Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verifica...

[2604.04182] Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty

Abstract page for arXiv paper 2604.04182: Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty

[2604.04171] A Model of Understanding in Deep Learning Systems

Abstract page for arXiv paper 2604.04171: A Model of Understanding in Deep Learning Systems

[2604.04157] Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents

Abstract page for arXiv paper 2604.04157: Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents

[2604.04145] Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting

Abstract page for arXiv paper 2604.04145: Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting

[2604.04131] Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents

Abstract page for arXiv paper 2604.04131: Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents

[2604.04106] InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories

Abstract page for arXiv paper 2604.04106: InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories

[2604.03976] Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

Abstract page for arXiv paper 2604.03976: Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

[2604.03898] LLM-Agent-based Social Simulation for Attitude Diffusion

Abstract page for arXiv paper 2604.03898: LLM-Agent-based Social Simulation for Attitude Diffusion

[2604.03888] PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage

Abstract page for arXiv paper 2604.03888: PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Laten...

[2604.03893] FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

Abstract page for arXiv paper 2604.03893: FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

[2604.03820] Affording Process Auditability with QualAnalyzer: An Atomistic LLM Analysis Tool for Qualitative Research

Abstract page for arXiv paper 2604.03820: Affording Process Auditability with QualAnalyzer: An Atomistic LLM Analysis Tool for Qualitativ...

[2604.03742] Structured Multi-Criteria Evaluation of Large Language Models with Fuzzy Analytic Hierarchy Process and DualJudge

Abstract page for arXiv paper 2604.03742: Structured Multi-Criteria Evaluation of Large Language Models with Fuzzy Analytic Hierarchy Pro...

[2604.03675] PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training

Abstract page for arXiv paper 2604.03675: PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training

[2604.03660] TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables

Abstract page for arXiv paper 2604.03660: TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical...

[2604.03656] Beyond Retrieval: Modeling Confidence Decay and Deterministic Agentic Platforms in Generative Engine Optimization

Abstract page for arXiv paper 2604.03656: Beyond Retrieval: Modeling Confidence Decay and Deterministic Agentic Platforms in Generative E...

[2604.03631] Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors

Abstract page for arXiv paper 2604.03631: Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning ...

[2604.03630] A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction

Abstract page for arXiv paper 2604.03630: A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery...

[2604.03589] Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark

Abstract page for arXiv paper 2604.03589: Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on t...

[2604.03571] Selective Forgetting for Large Reasoning Models

Abstract page for arXiv paper 2604.03571: Selective Forgetting for Large Reasoning Models