1. ViViT: A Video Vision Transformer
2. Visual prompting: Modifying pixel space to adapt pre-trained models;Bahng,2022
3. Beit: Bert pre-training of image transformers;Bao
4. Coresets via bilevel optimization for continual learning and streaming;Borsos;Advances in Neural Information Processing Systems,2020
5. Language models are few-shot learners;Brown;NeurIPS,2020