English(EN)Rethinking the Generation Order of Block Diffusion Language Models
扩散语言模型：效率、鲁棒性和路由创新
作者PulseAugur 编辑部·[8 个来源]·
近期研究探索了扩散语言模型（DLM）的进展，重点是提高其效率和鲁棒性。一篇论文将专家选择路由（Expert-Choice Routing）引入为DLM的优于令牌选择路由（Token-Choice Routing）的替代方案，实现了更好的负载均衡和更快的收敛速度。另一项研究提出了AURORA-LM，一种连续潜在DLM，它将表示构建与分布建模分开，在生成和摘要任务上取得了强劲的性能。进一步的研究考察了像ODB-dLLM这样的加速框架，它使用自适应长度预测和推测解码来加速推理，以及令牌级提前停止（token-level early stopping）以在不牺牲质量的情况下减少扩散步骤。最后，研究还考察了DLM对噪声和对抗性攻击的鲁棒性，强调虽然它们由于其随机性而能抵抗某些攻击，但其整体鲁棒性依赖于权重并且需要架构集成。
AI
arXiv:2608.02602v1 Announce Type: new Abstract: Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation still relies predominantly on discrete tokens. Existing continuous language mod…
arXiv cs.CL
TIER_1English(EN)·Linye Wei, Wenjue Chen, Pingzhi Tang, Xiaotian Guo, Le Ye, Runsheng Wang, Meng Li·
arXiv:2511.21759v2 Announce Type: replace Abstract: Diffusion-based large language models (dLLMs) have recently gained significant attention for their exceptional performance and inherent potential for parallel decoding. Existing frameworks further enhance its inference efficienc…
arXiv:2602.11133v2 Announce Type: replace-cross Abstract: Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step. We introduce a training-fr…
arXiv cs.CL
TIER_1English(EN)·Yaoxuan Dou, Yang Shu·
arXiv:2607.29079v1 Announce Type: new Abstract: Training-free acceleration makes diffusion-based multimodal large language models (dMLLMs) more deployable, but it may silently change generated content. We study this serving-time consistency problem on 300 real images, comparing F…
arXiv:2607.27386v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement. However, their reliability under natural input noise and adversarial att…
arXiv cs.CL
TIER_1English(EN)·Kai Syun Hou, James Kwok·
arXiv:2607.24306v1 Announce Type: new Abstract: Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language mo…
Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language models (BDLMs). We show empirically and analytical…
