1. On the opportunities and risks of foundation models;Bommasani;arXiv preprint arXiv:2108.07258,2021
2. Learning transferable visual models from natural language supervision;Radford,2021
3. Scaling vision transformers to 22 billion parameters;Dehghani,2023
4. OpenAI, “Gpt-4 technical report,” (2024).
5. Segment anything;Kirillov;arXiv preprint arXiv:2304.02643,2023