regularization term
A penalty added to a loss function to prevent overfitting by constraining model complexity, aiding in generalization to unseen data.
- COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
- Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
- FastJAM: a Fast Joint Alignment Model for Images
- MaxSup: Overcoming Representation Collapse in Label Smoothing
- MaxSup: Overcoming Representation Collapse in Label Smoothing
- Meta-learning how to Share Credit among Macro-Actions
- RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
- RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
- Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
- Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning