English(EN) Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models

新的Cord解码策略提升了dLLM在推理和代码任务上的性能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-31 04:00

研究人员开发了Cord，一种用于掩码扩散语言模型（dLLMs）的新解码策略，通过智能地决定何时以及如何揭示掩码标记来提高生成质量。与使用统一揭示规则的标准方法不同，Cord学会根据置信度、生成方向、与上下文的接近程度以及填空需求来调整其策略。这种方法在推理、编码和约束满足等各种基准测试中显著提高了任务成功率，同时增加了最少的计算开销。 AI

影响这项研究可能带来更强大、更高效的语言模型，用于推理和代码生成等复杂任务。

排序理由该集群包含一篇详细介绍语言模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍语言模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 3 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Chengwei Zhou, Zhaoyan Jia, Massoud Pedram, Gourav Datta · 2026-10-31 04:00

Cord: 掩码扩散语言模型的置信度锚定订单残差解码

arXiv:2610.39372v1 Announce Type: cross Abstract: The decoding order of masked diffusion language models (dLLMs) can substantially affect generation quality, yet common decoders typically apply the same reveal rule throughout generation. Confidence provides a strong default, but …

本文如何被排名

报道来源 [1]

Cord: 掩码扩散语言模型的置信度锚定订单残差解码

相关实体

相关话题