Jiang-Xin Shi

How Does Fine-Tuned Foundation Models Help for Long-Tailed Data

Beyond Re-Training from Scratch: Exploiting the Pre-Trained Classifier for Long-Tailed Learning

Memory-Efficient Fine-Tuning via Low-Rank Activation Compression

X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection

Harnessing Shallow Features in Pre-Trained Models for Out-of-Distribution Detection