Flatness-aware minimization for domain generalization
Abstract Domain generalization (DG) seeks to learn robust models that generalize well
under unknown distribution shifts. As a critical aspect of DG, optimizer selection has not …
under unknown distribution shifts. As a critical aspect of DG, optimizer selection has not …
Disentangled Prompt Representation for Domain Generalization
Abstract Domain Generalization (DG) aims to develop a versatile model capable of
performing well on unseen target domains. Recent advancements in pre-trained Visual …
performing well on unseen target domains. Recent advancements in pre-trained Visual …
Rethinking the evaluation protocol of domain generalization
Abstract Domain generalization aims to solve the challenge of Out-of-Distribution (OOD)
generalization by leveraging common knowledge learned from multiple training domains to …
generalization by leveraging common knowledge learned from multiple training domains to …
Your mixture-of-experts llm is secretly an embedding model for free
While large language models (LLMs) excel on generation tasks, their decoder-only
architecture often limits their potential as embedding models if no further representation …
architecture often limits their potential as embedding models if no further representation …
Dawin: Training-free dynamic weight interpolation for robust adaptation
Adapting a pre-trained foundation model on downstream tasks should ensure robustness
against distribution shifts without the need to retrain the whole model. Although existing …
against distribution shifts without the need to retrain the whole model. Although existing …