epistemic uncertainty
Uncertainty in AI predictions that arises from lack of knowledge about the underlying model or data, often addressed through Bayesian methods.
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- Credal Prediction based on Relative Likelihood
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
- Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- Epistemic Uncertainty for Generated Image Detection
- Integral Imprecise Probability Metrics
- MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
- On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
- PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
- Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
- Rethinking Approximate Gaussian Inference in Classification
- SOMBRL: Scalable and Optimistic Model-Based RL
- TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning
- Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation
- Towards Robust Uncertainty Calibration for Composed Image Retrieval
- Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data
- Variational Uncertainty Decomposition for In-Context Learning
- Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation