Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
ICLROral2026
TL;DR
We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image generation relies on next-patch prediction, a memory-bound process that leads to high latency.
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
image generation efficient memory