Xiyuan Wei

NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization

Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP

Advancing Interpretability of CLIP Representations with Concept Surrogate Model

Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws

FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources