model retraining
Model retraining is the process of updating a machine learning model to improve its performance as new data becomes available, essential for maintaining relevance in changing environments.
- Curriculum Abductive Learning
- Distillation Robustifies Unlearning
- From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
- GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
- Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning
- Monitoring Risks in Test-Time Adaptation
- On the Coexistence and Ensembling of Watermarks
- Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach
- Reliably detecting model failures in deployment without labels
- Removing Concepts from Text-to-Image Models with Only Negative Samples
- Robust Explanations of Graph Neural Networks via Graph Curvatures
- Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
- Training-Free Efficient Video Generation via Dynamic Token Carving
- Training-Free Safe Denoisers for Safe Use of Diffusion Models