Simplex Diffusion Models Beat Discrete Rivals at Math With 16x Fewer Steps
A new discrete diffusion framework operates directly on the probability simplex, carrying uncertainty between denoising steps and beating masked diffusion on code and math benchmarks.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
A new discrete diffusion framework operates directly on the probability simplex, carrying uncertainty between denoising steps and beating masked diffusion on code and math benchmarks.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
