For visual generation, discrete autoregressive models often struggle with poor tokenizer reconstruction, difficulties in sampling from large vocabularies, and slow token-by-token generation speeds. We ...

Abstract: This article introduces semantically meaningful causal language modeling (SMCLM), a self-supervised method of training autoregressive models to generate semantically equivalent text. Our ...

Abstract: Autoregressive models are ubiquitous tools for the analysis of time series in many domains such as computational neuroscience and biomedical engineering. In these domains, data is, for ...

ABSTRACT: Geophysics has played a significant and efficient role in studying geological structures over the past decades as the goal of geophysical data acquisition is to investigate underground ...

ABSTRACT: Geophysics has played a significant and efficient role in studying geological structures over the past decades as the goal of geophysical data acquisition is to investigate underground ...