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...

Opinion | Anthropic’s Chief on A.I.: ‘We Don’t Know if the Models Are Conscious’

[2508.02812] Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms

Abstract page for arXiv paper 2508.02812: Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms

[2507.13920] Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem

Abstract page for arXiv paper 2507.13920: Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Pro...

[2507.12165] Multi-Component VAE with Gaussian Markov Random Field

Abstract page for arXiv paper 2507.12165: Multi-Component VAE with Gaussian Markov Random Field

[2506.21744] Federated Item Response Models: A Gradient-driven Privacy-preserving Framework for Distributed Psychometric Estimation

Abstract page for arXiv paper 2506.21744: Federated Item Response Models: A Gradient-driven Privacy-preserving Framework for Distributed ...

[2506.08125] Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning

Abstract page for arXiv paper 2506.08125: Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement ...

[2506.02371] SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples

Abstract page for arXiv paper 2506.02371: SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples

[2506.01897] MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation

Abstract page for arXiv paper 2506.01897: MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation

[2505.24535] Beyond Linear Steering: Unified Multi-Attribute Control for Language Models

Abstract page for arXiv paper 2505.24535: Beyond Linear Steering: Unified Multi-Attribute Control for Language Models

[2505.21972] LLMs Judging LLMs: A Simplex Perspective

Abstract page for arXiv paper 2505.21972: LLMs Judging LLMs: A Simplex Perspective

[2505.21605] SoSBench: Benchmarking Safety Alignment on Six Scientific Domains

Abstract page for arXiv paper 2505.21605: SoSBench: Benchmarking Safety Alignment on Six Scientific Domains

[2505.14202] MSDformer: Multi-scale Discrete Transformer For Time Series Generation

Abstract page for arXiv paper 2505.14202: MSDformer: Multi-scale Discrete Transformer For Time Series Generation

[2505.13742] Understanding Task Representations in Neural Networks via Bayesian Ablation

Abstract page for arXiv paper 2505.13742: Understanding Task Representations in Neural Networks via Bayesian Ablation

[2505.12530] Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints

Abstract page for arXiv paper 2505.12530: Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints

[2505.12167] FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models

Abstract page for arXiv paper 2505.12167: FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models

[2505.03530] A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders

Abstract page for arXiv paper 2505.03530: A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Aut...

[2503.03206] An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models

Abstract page for arXiv paper 2503.03206: An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models

[2502.15567] Model Privacy: A Unified Framework for Understanding Model Stealing Attacks and Defenses

Abstract page for arXiv paper 2502.15567: Model Privacy: A Unified Framework for Understanding Model Stealing Attacks and Defenses

[2502.07977] RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent

Abstract page for arXiv paper 2502.07977: RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent

[2502.02020] Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustment

Abstract page for arXiv paper 2502.02020: Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustment

[2501.15458] Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies From Simulated Nonparametric Functions

Abstract page for arXiv paper 2501.15458: Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies From ...