Accepted Papers

Poster Session 1 (11:30-12:30)

• Towards Uncertainty Quantification in Generative Model Learning

• The flawed assumption of a data-generating distribution

• AP-OOD: Attention Pooling for Out-of-Distribution Detection

• Gradient-based Learning for Explainable Fuzzy Rule-based Classification

• Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMs

• Rule-Based Dynamic Feature Selection for Explainable Classification with Uncertainty Quantification

• Optimal Conformal Prediction under Epistemic Uncertainty

• On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors

• Exploring the role of action and state uncertainty in imitation learning

• Credal Concept Bottleneck Models: \\ Decomposing Uncertainty for Interpretable Text Classification

• Better Uncertainties Don’t Guarantee Better Decisions

• Efficient Credal Prediction through Decalibration

• Active Inference is a Subtype of Variational Inference

• Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs

• Entropy Is Not Enough: Uncertainty Quantification for LLMs fails under Aleatoric Uncertainty

• Uncertainty-aware diffusion models for probabilistic regression

• Sorting the Past, Not Predicting the Future: Probability, Uncertainty, and Algorithmic Risk in Criminal Justice

• Epistemically Aware Predictive Visuomotor Control

• Bayesian Conformal Prediction as a Decision Risk Problem Using Bayesian Quadrature

• The noise of incomparability: learning incomparability from forced comparisons

• Imprecise Acquisitions in Bayesian Optimization

• Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction

• RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models

• Uncertainty Quantification for Regression Using Proper Scoring Rules

• Effects of priors on epistemic uncertainty in autoregressive active inference

• How Reliable Are Networks? A Bayesian Modeling Approach

• Credal Graph Neural Networks

• Epistemic Error Decomposition for Multi-step Time Series Forecasting: Rethinking Bias–Variance in Recursive and Direct Strategies

• From Bayesian to Generalised Bayesian Experimental Design

Poster Session 2 (14:00-15:00)

• Uncertainty-Aware Multi-Agent Interaction for Reliable VQA

• Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles

• A Three-Way Testing Framework for Quantifying Epistemic Calibration Uncertainty in SBI

• Amortized Implicit Copula Generative Models

• Counterfactual spaces

• Possibilistic Instrumental Variable Regression

• Enhancing Network Robustness using Epistemic Intelligence

• Assessing Expectation Propagation for Mutual Information in Bayesian Optimization

• A Formal Assessment of Uncertainty Measures in Regression

• Evaluating Prediction Uncertainty Estimates from BatchEnsemble

• Spectral Uncertainty Decomposition for Sparse Bayesian Learning

• Maxitive Donsker–Varadhan Formulation for Possibilistic Variational Inference

• Epistemic Error Bounds for Probabilistic Machine Learners

• Evaluating the Impact of Post-Training Quantization on Reliable VQA with Multimodal LLMs

• Not All Credal Sets Are Created Equal: Specialized Approaches for Specialized Uncertainties

• Mixture of Gaussian Processes for Bayesian Active Learning

• Scaling Laws for Uncertainty in Deep Learning

• Robustness and uncertainty: two complementary aspects of the reliability of the predictions of a classifier

• Uncertainty Quantification for Capacities based on Integral Imprecise Probability Metrics

• Latent Energy-Score Training with Geometry-Preserving Decoders for Epistemic UQ in PDE Surrogates

• Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles

• On the Notion that Language Models Reason

• Uncertainty Quantification for Generative Models: Density Estimation Perspective

• So What are Good Imprecise Forecasts?

• Quantifying the Value of Missing Information for Individual Predictions

• Property Elicitation on Imprecise Probabilities

• Epistemic Uncertainty Quantification To Improve Decisions From Black-Box Models

• Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models

• Self-Reflective Code Agents under Epistemic Uncertainty

• Sampling and response noise epistemic uncertainties: from linear regressors to linearized deep networks

• Cumulative Mass Calibration via Conformal Prediction

• Beyond Mamba SSMs: Parallel Kalman Filters as Scalable Primitives for Language Modelling