real datasets
Real datasets are collections of data derived from actual observations rather than simulated or synthetic sources. They are critical for training models that generalize well to real-world applications.
- $\text{G}^2\text{M}$: A Generalized Gaussian Mirror Method to Boost Feature Selection Power
- Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization
- FraPPE: Fast and Efficient Preference-Based Pure Exploration
- Inferring stochastic dynamics with growth from cross-sectional data
- Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling
- Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics
- Online Two-Stage Submodular Maximization
- Prediction-Powered Semi-Supervised Learning with Online Power Tuning
- Spectral Analysis of Representational Similarity with Limited Neurons