新方法用局部不确定性修复，让块并行推测解码更快更稳，AI推理加速值得关注。
arXiv:2608.00531v1 Announce Type: new Abstract: Speculative decoding mitigates the latency of sequential generation in autoregressive Large Language M…
提出DeLS-Spec方法，解耦长短上下文实现并行投机解码，大幅提升大模型推理效率。
arXiv:2607.07409v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in paral…
无需训练即可加速扩散大模型，动态缓存与自适应并行解码双管齐下，推理性能再升级。
arXiv:2606.26120v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, exce…
扩散语言模型借助残差上下文实现并行多token解码，突破自回归限制，大幅提升文本生成效率
arXiv:2601.22954v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely au…
揭秘掩码扩散语言模型并行解码的脆弱性，提出关注度折扣自适应采样器提升效率与安全。
arXiv:2606.10829v1 Announce Type: cross Abstract: Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoisi…
扩散LLM迎来并行解码新突破，依赖感知注意力机制让加速生成更高效，ICML 2026接收
arXiv:2603.12996v2 Announce Type: replace Abstract: Parallel decoding for Diffusion LLMs (dLLMs) is difficult because each denoising step provides onl…
时空并行解码+置信外推，大幅提升扩散语言模型推理效率，架构创新值得深挖。
arXiv:2605.30753v1 Announce Type: new Abstract: Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising…
提出轨迹自蒸馏方法，让扩散语言模型用少步就能快速并行生成文本，突破推理速度瓶颈。
arXiv:2602.12262v3 Announce Type: replace-cross Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the …
新型扩散语言模型并行解码方法DMax，通过自精炼机制减少误差累积，实现高并行度高质量生成。
arXiv:2604.08302v3 Announce Type: replace-cross Abstract: We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigate…