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: Learned lossless image compression has been a popular topic in recent research. While outperforming many traditional compression techniques in terms of compression ratio, the high time and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results