model uncertainty
Model uncertainty refers to the uncertainty in the predictions made by an AI model due to various factors such as lack of data, choice of model architecture, or inherent variability in the environment. Understanding this uncertainty is crucial for developing robust AI systems that can reliably perform in diverse settings.
- Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
- Balanced Active Inference
- BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
- Distributionally Robust Performative Optimization
- Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
- ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
- Exploring and Exploiting Model Uncertainty in Bayesian Optimization
- Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project
- VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models