The paper introduces dSpark, a schedule distillation framework that learns when to commit tokens in diffusion large language models to accelerate generation. By constructing unmasking schedules that prioritize revealing tokens which make other positions easier to predict, dSpark reduces uncertainty earlier in decoding. Experiments on mathematical reasoning and code generation tasks show significant speedups—10.12× on LLaDA‑8B‑Instruct and 5.12× on Dream‑7B‑Instruct—while preserving superior task performance.
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:2609.15177v1 Announce Type: new Abstract: Diffusion language models (dLLMs) promise fast inference by generating multiple tokens in parallel, but suffer severe performance degradation when para...
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.
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.
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:2608.22646v1 Announce Type: new Abstract: Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation...
arXiv:2609. 04010v1 Announce Type: new Abstract: Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation.
arXiv:2610.36901v1 Announce Type: cross Abstract: We propose HiLo-RD (High-to-Low Budget Representation Distillation) to improve masked diffusion language models (MDLMs) under a limited generation bu...
TeCoP is a training‑free decoder that accelerates diffusion large language model (dLLM) decoding by decoupling prediction readiness from context utility. It uses tentative context pipelining and draft‑and‑verify to reuse stable but uncommitted predictions as provisional cross‑block context, with commitment based on confidence and stability checks. Across four dLLMs on GSM8K, Minerva MATH, and MBPP, TeCoP cuts forward evaluations by up to 87% and boosts throughput up to 7.5‑fold without KV caching and 11.77‑fold with caching, outperforming Fast‑dLLM and DSB while maintaining accuracy within one percentage point.
arXiv:2508. 10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm.
arXiv:2601. 07568v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation.
The paper introduces DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores intra-block dependencies in speculative decoding by evaluating multiple candidate tokens for contextual compatibility across adjacent draft positions. DCOCO maintains parallel drafting while enabling contextually informed token selection at low additional cost. Across multiple verifier backbones and benchmarks, DCOCO achieves the highest average throughput, delivering speedups of up to 6.6× over vanilla decoding and outperforming competing methods by 6–23% under concurrent serving loads.