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...

Accelerating science with AI and simulations

MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...

Improving AI models’ ability to explain their predictions

[2603.24780] Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback

Abstract page for arXiv paper 2603.24780: Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback

[2603.25480] Retraining as Approximate Bayesian Inference

Abstract page for arXiv paper 2603.25480: Retraining as Approximate Bayesian Inference

[2603.24753] Light Cones For Vision: Simple Causal Priors For Visual Hierarchy

Abstract page for arXiv paper 2603.24753: Light Cones For Vision: Simple Causal Priors For Visual Hierarchy

[2603.25450] Cross-Model Disagreement as a Label-Free Correctness Signal

Abstract page for arXiv paper 2603.25450: Cross-Model Disagreement as a Label-Free Correctness Signal

[2603.24744] Contrastive Learning Boosts Deterministic and Generative Models for Weather Data

Abstract page for arXiv paper 2603.24744: Contrastive Learning Boosts Deterministic and Generative Models for Weather Data

[2603.25412] Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

Abstract page for arXiv paper 2603.25412: Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

[2603.25379] Does Structured Intent Representation Generalize? A Cross-Language, Cross-Model Empirical Study of 5W3H Prompting

Abstract page for arXiv paper 2603.25379: Does Structured Intent Representation Generalize? A Cross-Language, Cross-Model Empirical Study...

[2603.24709] Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards

Abstract page for arXiv paper 2603.24709: Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated R...

[2603.25356] 4OPS: Structural Difficulty Modeling in Integer Arithmetic Puzzles

Abstract page for arXiv paper 2603.25356: 4OPS: Structural Difficulty Modeling in Integer Arithmetic Puzzles

[2603.24695] Amplified Patch-Level Differential Privacy for Free via Random Cropping

Abstract page for arXiv paper 2603.24695: Amplified Patch-Level Differential Privacy for Free via Random Cropping

[2603.25334] Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks

Abstract page for arXiv paper 2603.25334: Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous ...

[2603.24648] Energy-Efficient Hierarchical Federated Anomaly Detection for the Internet of Underwater Things via Selective Cooperative Aggregation

Abstract page for arXiv paper 2603.24648: Energy-Efficient Hierarchical Federated Anomaly Detection for the Internet of Underwater Things...

[2603.24641] Learning Mesh-Free Discrete Differential Operators with Self-Supervised Graph Neural Networks

Abstract page for arXiv paper 2603.24641: Learning Mesh-Free Discrete Differential Operators with Self-Supervised Graph Neural Networks

[2603.25328] Macroscopic Characteristics of Mixed Traffic Flow with Deep Reinforcement Learning Based Automated and Human-Driven Vehicles

Abstract page for arXiv paper 2603.25328: Macroscopic Characteristics of Mixed Traffic Flow with Deep Reinforcement Learning Based Automa...

[2603.24647] Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch

Abstract page for arXiv paper 2603.24647: Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch

[2603.25326] Evaluating Language Models for Harmful Manipulation

Abstract page for arXiv paper 2603.25326: Evaluating Language Models for Harmful Manipulation

[2603.24644] Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Columns under Transient Operating Conditions

Abstract page for arXiv paper 2603.24644: Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Col...

[2603.24639] Experiential Reflective Learning for Self-Improving LLM Agents

Abstract page for arXiv paper 2603.24639: Experiential Reflective Learning for Self-Improving LLM Agents

[2603.25284] SliderQuant: Accurate Post-Training Quantization for LLMs

Abstract page for arXiv paper 2603.25284: SliderQuant: Accurate Post-Training Quantization for LLMs

[2603.25283] A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion

Abstract page for arXiv paper 2603.25283: A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion