Xin Wen

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

Rethinking Out-of-Distribution Detection in Vision Foundation Models

Granularity Matters in Long-Tail Learning

An Image is Worth $K$ Slots: Data-efficient Scaling of Self-supervised Visual Pre-training

What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights