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

[2604.03515] Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

Abstract page for arXiv paper 2604.03515: Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

[2604.03480] Large Language Models Align with the Human Brain during Creative Thinking

Abstract page for arXiv paper 2604.03480: Large Language Models Align with the Human Brain during Creative Thinking

[2604.03476] Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition

Abstract page for arXiv paper 2604.03476: Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition

[2604.03473] Evolutionary Search for Automated Design of Uncertainty Quantification Methods

Abstract page for arXiv paper 2604.03473: Evolutionary Search for Automated Design of Uncertainty Quantification Methods

[2604.03472] Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

Abstract page for arXiv paper 2604.03472: Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

[2604.03447] Measuring LLM Trust Allocation Across Conflicting Software Artifacts

Abstract page for arXiv paper 2604.03447: Measuring LLM Trust Allocation Across Conflicting Software Artifacts

[2604.03425] AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems

Abstract page for arXiv paper 2604.03425: AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism...

[2604.03374] CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge

Abstract page for arXiv paper 2604.03374: CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge

[2604.03338] The Ideation Bottleneck: Decomposing the Quality Gap Between AI-Generated and Human Economics Research

Abstract page for arXiv paper 2604.03338: The Ideation Bottleneck: Decomposing the Quality Gap Between AI-Generated and Human Economics R...

[2604.03333] Composer Vector: Style-steering Symbolic Music Generation in a Latent Space

Abstract page for arXiv paper 2604.03333: Composer Vector: Style-steering Symbolic Music Generation in a Latent Space

[2604.03325] Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives

Abstract page for arXiv paper 2604.03325: Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives

[2604.03322] VitaTouch: Property-Aware Vision-Tactile-Language Model for Robotic Quality Inspection in Manufacturing

Abstract page for arXiv paper 2604.03322: VitaTouch: Property-Aware Vision-Tactile-Language Model for Robotic Quality Inspection in Manuf...

[2604.03307] V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators

Abstract page for arXiv paper 2604.03307: V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators

[2604.03303] Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

Abstract page for arXiv paper 2604.03303: Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

[2604.03302] Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models

Abstract page for arXiv paper 2604.03302: Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-moda...

[2604.03300] AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System

Abstract page for arXiv paper 2604.03300: AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System

[2604.03299] MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement

Abstract page for arXiv paper 2604.03299: MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement

[2604.03296] 3D-IDE: 3D Implicit Depth Emergent

Abstract page for arXiv paper 2604.03296: 3D-IDE: 3D Implicit Depth Emergent

[2604.03292] Impact of geophysical fields on Deep Learning-based Lagrangian drift simulations

Abstract page for arXiv paper 2604.03292: Impact of geophysical fields on Deep Learning-based Lagrangian drift simulations

[2604.03295] Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

Abstract page for arXiv paper 2604.03295: Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems