Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models

Excerpt

arXiv:2608.11742v2 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a ripple effect in dLLM decoding: proactively committin