prediction quality
Prediction quality assesses the accuracy and reliability of predictions made by an AI model. It typically involves a combination of metrics (e.g., precision, recall, F1 score) to evaluate how well a model performs its intended task.
- Anytime-valid, Bayes-assisted, Prediction-Powered Inference
- Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
- Learning-Augmented Streaming Algorithms for Correlation Clustering
- Test Time Scaling for Neural Processes
- Transformers for Mixed-type Event Sequences
- UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection