Maxim Panov

Assistant Professor@Mohamed bin Zayed University of Artificial Intelligence·阿联酋·OpenReview

研究方向

predictive uncertainty quantification · conformal prediction · topic models · social network analysis · graph embeddings · Bayesian methods · Gaussian processes regression

Maxim Panov

Modeling the Density of Pixel-level Self-supervised Embeddings for Unsupervised Pathology Segmentation in Medical CT

Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads

Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search

Neural Optimal Transport Meets Multivariate Conformal Prediction

Uncertainty Quantification for Regression Using Proper Scoring Rules

Multidimensional Uncertainty Quantification via Optimal Transport

CoCoA: A Minimum Bayes Risk Framework Bridging Confidence and Consistency for Uncertainty Quantification in LLMs

From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation

Probabilistic Conformal Prediction with Approximate Conditional Validity

Screener: Self-supervised Pathology Segmentation Model for 3D Medical Images

Rectifying Conformity Scores for Better Conditional Coverage

Screener: Learning Conditional Distribution of Dense Self-supervised Representations for Unsupervised Pathology Segmentation in 3D Medical Images