The paper introduces asynchronous flow map language models (aFMLMs), a new one‑step parallel language modeling approach that incorporates token prediction order via learned or prescribed asynchronous flows. These flows define a token‑wise time schedule controlling denoising progress, and the authors prove that such flows yield valid flow maps and develop distillation methods. Experiments on Sudoku solving and code generation for GSM8K math word problems show that aFMLMs achieve state‑of‑the‑art performance in one‑step generation.
arXiv:2606. 27617v1 Announce Type: cross Abstract: Masked Diffusion Models (MDMs) promise fast, parallel language generation, but their reverse transition factorises across token positions -- an approximation that breaks down in the few-step sampling regime where parallel generation ought to provide the greatest efficiency gains.
arXiv:2610.28559v1 Announce Type: cross Abstract: Continuous flow language models offer a path to parallel generation with tools for control and acceleration unavailable to discrete diffusion, yet ef...
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: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...
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: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.
PlaidQ is a 0.7B continuous diffusion language model designed for code generation. By distilling its iterative refinement trajectory into only a few denoising steps—or even a single step—PlaidQ achieves competitive performance with discrete diffusion models while dramatically reducing inference time. The study demonstrates that continuous diffusion can be effectively compressed, enabling efficient and accurate code generation with minimal computational overhead.
Diffusion language models accelerate generation by decoding multiple masked positions per forward pass. However, accuracy is known to drop when parallel decoding trajectories deviate from their sequen...
SpecCTMC is a training‑free speculative sampler for masked diffusion language models that reduces the sequential bottleneck of exact continuous‑time sampling. It updates tokens successively using previously computed predictions, evaluates intermediate states in parallel, and applies an exact acceptance‑and‑correction step, thereby preserving the joint distribution of event times, generation order, and token values. Experiments on LLaDA‑8B‑Instruct and Dream‑v0‑Instruct‑7B show 1.73‑4.38× fewer sequential model evaluations while maintaining the reference sampling distribution.
arXiv:2606. 00722v1 Announce Type: cross Abstract: Controlling language model outputs is essential for ensuring structural validity, reliability, and downstream usability, and diffusion language models are no exception.
arXiv:2601. 22954v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel.
arXiv:2610.33811v1 Announce Type: new Abstract: Continuous-state flow and diffusion models offer a promising approach to fast, parallel language generation, but matching the generation quality of aut...