2D-RoPE for image models is easier in the complex representation, says arohan

_arohan_ · x · 2026-09-05

Replying to @thomasahle, arohan suggests generalizing RoPE (rotary position embeddings): image models can use a generalized form like 2D-RoPE, which is easier to implement in the complex representation. A brief technical take with no further details or experiments.

Original post →

More from Research

Research channel →