data imbalance
A condition where certain classes of data are underrepresented, which can skew the learning process of a model, often leading to biased predictions.
- CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
- DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
- Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
- SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation
- Synthetic Series-Symbol Data Generation for Time Series Foundation Models