1. Bert: Pre-training of deep bidirectional transformers for language understanding;Ming-Wei Chang Kenton;NAACL,2019
2. wav2vec 2.0: A framework for self-supervised learning of speech representations;Baevski;NeurIPS,2020
3. Vision models are more robust and fair when pretrained on uncurated images without supervision;Goyal,2022
4. Using self-supervised learning can improve model robustness and uncertainty;Hendrycks;NeurIPS,2019
5. Towards Learning Universal Audio Representations