CONF Pannatier_ECMLPKDD_2024/IDIAP s-GPTs: A New Approach to Autoregressive Models. Pannatier, Arnaud Courdier, Evann Fleuret, Francois Autoregressive models Permutations Rejection Sampling transformers EXTERNAL http://publications.idiap.ch/attachments/papers/2024/Pannatier_ECMLPKDD_2024.pdf PUBLIC European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2024 Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this assumption and show that by simply adding a positional encoding for the output, this order can be modulated on-the-fly per-sample which offers key advantageous properties. It allows for the sampling of and conditioning on arbitrary subsets of tokens, and it also allows sampling in one shot multiple tokens dynamically according to a rejection strategy, leading to a sub-linear number of model evaluations. We evaluate our method across various domains, including language modeling, path-solving, and aircraft vertical rate prediction, decreasing the number of steps required for generation by an order of magnitude.