RandAR shows a decoder-only transformer can generate images in arbitrary token orders with quality close to raster order, using position instruction tokens, while unlocking parallel decoding and zero-shot editing.
Medusa: Simple llm inference acceleration framework with multiple decod- ing heads
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
RandAR shows a decoder-only transformer can generate images in arbitrary token orders with quality close to raster order, using position instruction tokens, while unlocking parallel decoding and zero-shot editing.