Cover Image

Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Berger, Julia, Frauenknecht, Bernd, Trimpe, Sebastian, Leibe, Bastian
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
by: Eisele, Artur, et al.
Published: (2026)

Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
by: Frauenknecht, Bernd, et al.
Published: (2024)

On Rollouts in Model-Based Reinforcement Learning
by: Frauenknecht, Bernd, et al.
Published: (2025)

Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics
by: Frauenknecht, Bernd, et al.
Published: (2026)

Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors
by: Cramer, Emma, et al.
Published: (2024)

Learning Hybrid Dynamics Models With Simulator-Informed Latent States
by: Ensinger, Katharina, et al.
Published: (2023)

Epistemic Wrapping for Uncertainty Quantification
by: Sultana, Maryam, et al.
Published: (2025)

Label-wise Aleatoric and Epistemic Uncertainty Quantification
by: Sale, Yusuf, et al.
Published: (2024)

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
by: Bakman, Yavuz, et al.
Published: (2025)

HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model
by: Van Katwyk, Peter, et al.
Published: (2025)

Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
by: Zepf, Kilian, et al.
Published: (2023)

Epistemic Uncertainty Quantification For Pre-trained Neural Network
by: Wang, Hanjing, et al.
Published: (2024)

Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching
by: Ju, Li, et al.
Published: (2026)

BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
by: Brunzema, Paul, et al.
Published: (2026)

MPX: Mixed Precision Training for JAX
by: Gräfe, Alexander, et al.
Published: (2025)

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
by: Song, Haoze, et al.
Published: (2026)

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence
by: Wang, Tianyang, et al.
Published: (2025)

Quantification via Gaussian Latent Space Representations
by: Pérez-Mon, Olaya, et al.
Published: (2025)

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models
by: Li, Mingda, et al.
Published: (2025)

Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs
by: Valdettaro, Filippo, et al.
Published: (2024)

Accurate and Efficient Hybrid-Ensemble Atmospheric Data Assimilation in Latent Space with Uncertainty Quantification
by: Fan, Hang, et al.
Published: (2026)

Activation-Space Uncertainty Quantification for Pretrained Networks
by: Bergna, Richard, et al.
Published: (2026)

Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices
by: Gräfe, Alexander, et al.
Published: (2026)

Learning Surrogate LPV State-Space Models with Uncertainty Quantification
by: Olucha, E. Javier, et al.
Published: (2026)

Quantifying Epistemic Uncertainty in Diffusion Models
by: Gupta, Aditi, et al.
Published: (2026)

Rethinking Aleatoric and Epistemic Uncertainty
by: Smith, Freddie Bickford, et al.
Published: (2024)

The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification
by: Mücke, Nikolaj T., et al.
Published: (2024)

Post-Hoc Split-Point Self-Consistency Verification for Efficient, Unified Quantification of Aleatoric and Epistemic Uncertainty in Deep Learning
by: Zhao, Zhizhong, et al.
Published: (2025)

Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
by: Wang, Xiaoyu, et al.
Published: (2026)

Exact Inference for Continuous-Time Gaussian Process Dynamics
by: Ensinger, Katharina, et al.
Published: (2023)

Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
by: Subhasish, Devdutt, et al.
Published: (2026)

CHEQ-ing the Box: Safe Variable Impedance Learning for Robotic Polishing
by: Cramer, Emma, et al.
Published: (2025)

Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models
by: Neumeier, Marion, et al.
Published: (2024)

Metric Space Magnitude for Evaluating the Diversity of Latent Representations
by: Limbeck, Katharina, et al.
Published: (2023)

(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models
by: Kirsch, Andreas
Published: (2024)

On the Consistency of Kernel Methods with Dependent Observations
by: Massiani, Pierre-François, et al.
Published: (2024)

A Novel Framework for Uncertainty Quantification via Proper Scores for Classification and Beyond
by: Gruber, Sebastian G.
Published: (2025)

Safety in safe Bayesian optimization and its ramifications for control
by: Fiedler, Christian, et al.
Published: (2025)

Robust Node Affinities via Jaccard-Biased Random Walks and Rank Aggregation
by: Pfeifer, Bastian, et al.
Published: (2026)

Quantifying Epistemic Predictive Uncertainty in Conformal Prediction
by: Chau, Siu Lun, et al.
Published: (2026)