Our visual experience in daily life are dominated by dynamic change.

Structural pruning has emerged as a promising solution to reduce the costs of LLMs without requiring post-processing steps.

Such a lack of alignment and uniformity might restrict the transferability and robustness of embeddings. To this end, we devise a new fine-tuning method for robust representation equipping better alignment and uniformity. First, we propose a Geodesic Multi-Modal Mixup that mixes the embeddings of image and text to generate hard negative samples on the hypersphere.