🛰️ Daily AI Frontier
‹ back to 2026-08-04

xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

Research Efficiency & Systems

Ranking

Overall 76
Content 80
Popularity 65

Observed public metrics from 1 member.

Representative image for xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

Merged summary

TL;DR - xPress is a lightweight causal refiner that fixes the independence problem in block-diffusion speculative-decoding drafters, raising draft acceptance length ~30% and end-to-end throughput ~1.3x on Qwen3-8B. It matters because it recovers much of the wasted potential of single-pass parallel drafting without reintroducing sequential token-by-token generation.

  • Block-diffusion drafters (e.g. dFlash) emit a whole draft block in one forward pass, but sample each position from its own marginal, so tokens are conditionally independent and often jointly improbable under the target model — causing early rejection during verification.
  • xPress reconciles the entire diffusion block at once via parallel refinement, restoring and propagating causal dependencies across draft positions without an autoregressive loop, preserving the speed advantage of one-pass drafting.
  • Evaluated on Qwen3-8B across seven math, code, and chat benchmarks: acceptance length up ~30% on average (up to +56%), decoding throughput up ~1.3x on average (up to 1.7x) versus the base dFlash drafter.
  • The approach is drafter-side only and lightweight, so gains come without changing the target model or the standard speculative verification procedure.

Sources (1)

xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

arXiv cs.AI Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim, Mudhakar Srivatsa, Raghu K. Ganti, Minjia Zhang, Naigang Wang 2026-08-03 arXiv:2608.02438
Public signals Hugging Face upvotes 1 · Semantic Scholar citations 1 · Semantic Scholar influential citations 0
Providers: Hugging Face · Upvotes 1 OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 1 · Influential citations 0 X · N/A Fetched 2026-09-03 14:33:46.150268 UTC

TL;DR - xPress is a lightweight causal refiner that fixes the independence problem in block-diffusion speculative-decoding drafters, raising draft acceptance length ~30% and end-to-end throughput ~1.3x on Qwen3-8B. It matters because it recovers much of the wasted potential of single-pass parallel drafting without reintroducing sequential token-by-token generation.

  • Block-diffusion drafters (e.g. dFlash) emit a whole draft block in one forward pass, but sample each position from its own marginal, so tokens are conditionally independent and often jointly improbable under the target model — causing early rejection during verification.
  • xPress reconciles the entire diffusion block at once via parallel refinement, restoring and propagating causal dependencies across draft positions without an autoregressive loop, preserving the speed advantage of one-pass drafting.
  • Evaluated on Qwen3-8B across seven math, code, and chat benchmarks: acceptance length up ~30% on average (up to +56%), decoding throughput up ~1.3x on average (up to 1.7x) versus the base dFlash drafter.
  • The approach is drafter-side only and lightweight, so gains come without changing the target model or the standard speculative verification procedure.
item →