bias
Systematic errors in predictions or decisions made by AI systems often resulting from biased training data or model assumptions. Understanding and mitigating bias is crucial for developing fair and equitable AI solutions.
- A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal Inference
- Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
- Efficient Randomized Experiments Using Foundation Models
- Improved Algorithms for Fair Matroid Submodular Maximization
- MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
- Prediction-Powered Semi-Supervised Learning with Online Power Tuning
- Ridge Boosting is Both Robust and Efficient