Target-conditioned diffusion drafters predict candidate tokens in parallel, yet each new block must wait for updated target-model hidden states. This forces drafting and verification to run sequentially, limiting speedup even though each block is generated in one pass. We introduce D3D, a standalone diffusion drafter that removes this inter-round dependency. D3D combines blockwise denoising with auxiliary autoregressive supervision to achieve long accepted prefixes without target hidden states. This independence lets D3D draft successor blocks during verification in one packed pass, enabling asynchronous speculative decoding. We progressively prune layers according to their effect on acceptance length to reduce the cost of packed drafting. Removing five of 36 layers retains over 99\% of mean acceptance length across three benchmarks with Qwen3-8B as the target. Across seven benchmarks, D3D averages 5.00$\times$ and 5.71$\times$ decoding speedup with Qwen3-8B and Qwen3-32B targets, compared with 4.03$\times$ and 3.67$\times$ for DFlash. On GSM8K with Qwen3-32B, speedup reaches 7.48$\times$. Code is publicly available at https://github.com/fudan-generative-vision/D3D.
Discrete diffusion models with parallel decoding are often distilled using token-wise KL objectives. Although token-wise KL exactly matches the corresponding product-form block distributions, its probability-space optimization geometry and teacher-only candidate truncation may provide insufficient supervision under aggressive few-step distillation. Concrete Score Matching (CSM) provides an alternative within-position objective by aligning relative logit geometry, but its complete pairwise form incurs \mathcal{O}(|\mathcal{V}|^2) complexity. We propose Bidirectional Centered Score Matching (BCSM), an efficient within-position distillation objective that constructs an \mathcal{O}(K) bidirectional active set, reduces pairwise comparisons to \mathcal{O}(K^2), and factorizes them into an \mathcal{O}(K) objective. We further introduce cross-timestep transition alignment. Experiments demonstrate strong quality--efficiency trade-offs, including up to 6\times NFE reduction with a 16.9\% relative HumanEval gain and a 15.1\% relative MMMU gain at single-step inference.
We present T^\star, a simple TraceRL-based curriculum for progressive block-size scaling in masked diffusion language models (MDMs).Starting from an AR-initialized small-block MDM, T^\star gradually increases the block size while re-optimizing the denoising policy at each stage, enabling higher-parallelism decoding with limited degradation on math reasoning benchmarks. Across two SDAR scales and three benchmarks, T^\star consistently outperforms direct large-block TraceRL and is substantially more stable during training. Our schedule analysis suggests that the learned policy does not simply revert to a strictly left-to-right order; instead, it retains block-size-specific non-monotone updates while improving accuracy.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表