Joshua Ainslie3 papers on this site (2020–2023)GQA: Training Generalized Multi-Query Transformer Models from Multi-Head CheckpointsJoshua Ainslie, James Lee-Thorp, Michiel de Jong, et al.2023LongT5: Efficient Text-To-Text Transformer for Long SequencesMandy Guo, Joshua Ainslie, David Uthus, et al.2022Big Bird: Transformers for Longer SequencesManzil Zaheer, Guru Guruganesh, Avinava Dubey, et al.2020