uncertainty modeling
The practice of quantifying and representing uncertainty in machine learning models, which can involve techniques like probabilistic models or Bayesian inference to express confidence or risk associated with predictions.
- CURV: Coherent Uncertainty-Aware Reasoning in Vision-Language Models for X-Ray Report Generation
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
- Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation
- Learning from Interval Targets
- Neurosymbolic Diffusion Models
- What do you know? Bayesian knowledge inference for navigating agents