← Search

Chengwei Zhu

2 accepted papers

2024

Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation

ICML 2024poster

Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses challenges due to the significant modality discrepancy and scar…

Cited by 4SourcePDFScholar
2024

Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments

NeurIPS 2024poster

Enabling deep models to generalize in non-stationary environments is vital for real-world machine learning, as data distributions are often found to continually change. Recently, evolving domain generalization (EDG) has emerged to tackle the domain generalization in a time-varying system, where the…

Cited by 0SourcePDFScholar