Pix2Seq is this ingenious way of formulating the object detection task as a language modeling one: https://t.co/p3FpbpdR1z (@tingchenai et al.) Ting, I wonder how did you come up with such an elegant setting? What were the initial thoughts? @ariG23498, thanks for the suggestion

New work with @ariG23498 on implementing Masked Autoencoders for self-supervised pretraining of images. Thanks to @endernewton for the helpful discussions.