consistency
In AI, consistency refers to the alignment between model predictions and the underlying data or ground truth, ensuring that similar inputs yield similar outputs across different contexts.
- Availability-aware Sensor Fusion via Unified Canonical Space
- Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification
- CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
- Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations
- Entropy Rectifying Guidance for Diffusion and Flow Models
- Kernel von Mises Formula of the Influence Function
- LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models
- Learning-Augmented Online Bidding in Stochastic Settings
- Low-Rank Graphon Learning for Networks
- Network two-sample test for block models
- Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
- Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
- Statistical Analysis of an Adversarial Bayesian Weak Supervision Method
- Transferring Causal Effects using Proxies
- Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts