LLaDA (Speculative decoding): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 2 beat it on benchmarks — #46 of 151 most-superseded. Sub-problem: cluster led by SSD. Newer alternatives in the same sub-problem include FeF-DLLM, DualDiffusion, Principled Coarse-Graining (PCG).

Speculative decoding

LLaDA

Large Language Diffusion Models

Superseded baseline#46 of 151 most-superseded · first seen Feb 14, 2025

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 2 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating LLaDA. Values are copied from the source paper's tables — verify against the cited paper.

DualDiffusion beats LLaDA
75.4 vs 298.3
Time (s) · [no_condition]
DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models
FeF-DLLM (step=4) beats LLaDA
36.56 vs 26.60
Acc. · [MATH]
Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding
FeF-DLLM (step=2) beats LLaDA
36.40 vs 26.60
Acc. · [MATH]
Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.