uncertainty quantification
This process involves assessing and representing the uncertainty in AI model predictions. It is crucial for applications where decision-making relies heavily on the confidence of predictions, helping to create more robust and trustworthy systems.
- Accelerating Feature Conformal Prediction via Taylor Approximation
- Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- Ask a Strong LLM Judge when Your Reward Model is Uncertain
- Asymmetric Duos: Sidekicks Improve Uncertainty
- Asymptotic theory of SGD with a general learning-rate
- Bayesian Concept Bottleneck Models with LLM Priors
- Bernstein–von Mises for Adaptively Collected Data
- Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation
- C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
- Class conditional conformal prediction for multiple inputs by p-value aggregation
- CoCoA: A Minimum Bayes Risk Framework Bridging Confidence and Consistency for Uncertainty Quantification in LLMs
- Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation
- Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
- Conformal Prediction for Causal Effects of Continuous Treatments
- Conformal Prediction for Time-series Forecasting with Change Points
- Contextual Thompson Sampling via Generation of Missing Data
- Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
- Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
- Exploring the Noise Robustness of Online Conformal Prediction
- Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient Descent
- Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
- Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation
- Image Super-Resolution with Guarantees via Conformalized Generative Models
- Infinite Neural Operators: Gaussian processes on functions
- Integral Imprecise Probability Metrics
- Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models
- Knowledge Distillation of Uncertainty using Deep Latent Factor Model
- Light-Weight Diffusion Multiplier and Uncertainty Quantification for Fourier Neural Operators
- Martingale Posterior Neural Networks for Fast Sequential Decision Making
- Neurosymbolic Diffusion Models
- Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shift with Unlabeled Data
- Online Locally Differentially Private Conformal Prediction via Binary Inquiries
- Personalized Federated Conformal Prediction with Localization
- Position: Biology is the Challenge Physics-Informed ML Needs to Evolve
- Preference-Based Dynamic Ranking Structure Recognition
- ProDAG: Projected Variational Inference for Directed Acyclic Graphs
- Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference
- Regression Trees Know Calculus
- Rethinking Approximate Gaussian Inference in Classification
- STACI: Spatio-Temporal Aleatoric Conformal Inference
- Solving and Learning Partial Differential Equations with Variational Q-Exponential Processes
- Statistical Inference for Gradient Boosting Regression
- Thompson Sampling in Function Spaces via Neural Operators
- Topology-Aware Conformal Prediction for Stream Networks
- Torch-Uncertainty: Deep Learning Uncertainty Quantification
- Transductive Conformal Inference for Full Ranking
- Transformers for Mixed-type Event Sequences
- Uncertainty Estimation by Flexible Evidential Deep Learning
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
- Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference
- Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
- Valid Selection among Conformal Sets
- Variational Polya Tree
- Vicinal Label Supervision for Reliable Aleatoric and Epistemic Uncertainty Estimation
- When and how can inexact generative models still sample from the data manifold?