1. Flamingo: a visual language model for few-shot learning;Alayrac;NeurIPS,2022
2. VQA: Visual Question Answering
3. Openflamingo: An open-source framework for training large autoregressive vision-language models;Awadalla,2023
4. (ab) using images and sounds for indirect instruction injection in multi-modal llms;Bagdasaryan,2023
5. Are aligned neural networks adversarially aligned?;Carlini,2023