Bibliography (6):

1. https://openai.com/index/gpt-4-research/

2. https://openai.com/blog/chatgpt/

3. CLIP: Connecting Text and Images: We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the ‘zero-shot’ capabilities of GPT-2 and GPT-3

4. Visual Instruction Tuning

5. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

6. https://github.com/yunqing-me/AttackVLM