59d4e18a60490b9ed9913f3be2b14839-Paper-Conference.pdf
–Neural Information Processing Systems
The remarkable success of the autoregressive paradigm has made significant advancement in Multimodal Large Language Models (MLLMs), with powerful models like Show-o, Transfusion and Emu3 achieving notable progress in unified image phenomenon: understanding the understanding and generation.
Neural Information Processing Systems
Jun-17-2026, 12:22:46 GMT