arXiv Machine Learning
Rethinking Soft Tokens for Parallel Decoding in Diffusion Language Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 4
Supportive Token Revealing for Fast Diffusion Language Model Decoding
arXiv:2606. 04236v1 Announce Type: cross Abstract: Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off.
arXiv AI
Aug 17
CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing
arXiv:2608. 13925v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass.
arXiv Machine Learning
Jun 16
Mean-Field Parallel Decoding for Discrete Diffusion Language Models
arXiv:2606. 15805v1 Announce Type: new Abstract: Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding.
arXiv AI
Jun 3
$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
arXiv:2604. 18995v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction.
arXiv AI
1d ago
Reliable Parallel Decoding in Masked Diffusion Language Models
The paper introduces Reliable Parallel Decoding (RPD) for masked diffusion language models, addressing the unreliability of committing multiple predictions from a single forward pass. Diagnostics reveal that confidence alone is insufficient, as confident end‑sequence predictions can preempt necessary upstream computations, and downstream predictions degrade with upstream uncertainty. RPD selects candidates based on layer‑wise stability and final confidence, committing them under an entropy budget while deferring uncertain predictions, achieving superior throughput and competitive accuracy on LLaDA and Dream benchmarks.
arXiv Computation and Language
Sep 21
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.