Tag
This paper introduces Domain Generalizable Dataset Distillation (DGDD), a new problem setting that targets out-of-distribution generalization of distilled datasets, and proposes Spectral Gradient Surgery (SGS) to disentangle class-discriminative and domain-specific information by leveraging cross-domain gradient agreement in the spectral domain.
The paper proposes Slice, a gradient-surgery-based initialization for LoRA adapters in continual learning that reconciles conflicting gradients from current and past tasks to reduce catastrophic forgetting, achieving better stability-plasticity trade-offs.