Instruction tuning large language models (LLMs) using machine-generated instruction-
following data has been shown to improve zero-shot capabilities on new tasks, but the idea …

We launch EVA-02, a next-generation Transformer-based visual representation pre-trained
to reconstruct strong and robust language-aligned vision features via masked image …

Contrastive pre-training of image-text foundation models such as CLIP demonstrated
excellent zero-shot performance and improved robustness on a wide range of downstream …

Deep neural network (DNN) classifiers are potent instruments that can be used in various
security-sensitive applications. Nonetheless, they are vulnerable to certain attacks that …

Training large transformer models from scratch for a target task requires lots of data and is
computationally demanding. The usual practice of transfer learning overcomes this …

Knowledge Distillation (KD) has proven effective for compressing large teacher models into
smaller student models. While it is well known that student models can achieve similar …

Transfer-based adversarial attacks raise a severe threat to real-world deep learning systems
since they do not require access to target models. Adversarial training (AT), which is …

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer
ability. The high generality and usability of these visual models is achieved via a web-scale …