Newshot
Papers Still developing Event #01M7J491JGV369FBVH269XTFCY

See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models

Event overview(model summary, not the source's own text)

arXiv 于 2611.17754v1 发布论文《See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models》,指出策略梯度方法虽被广泛用于让大语言模型输出对齐人类偏好,但其对数似然计算代价高昂。该论文提出一种面向掩码扩散语言模型的方差缩减后训练方法,主张每个块只采样一次。同一批次中另有 ReMaRL(2611.22576v1)研究冻结扩散语言模型中的解掩与重掩顺序对最终答案准确率的影响,以及 OpenGNS(2611.24331v1)发布跨视觉、语言与扩散模型的梯度噪声规模开放数据集。三者均为 arXiv 新公告摘要,正文细节尚未公开。

This summary was distilled by a model from the 3 reports below; it is not the source text. Treat the reports themselves as the facts.

How this story unfolded

Left: what it concluded — the key points the model distilled from the reports below, each one listing the reports it rests on. Right: what happened — ordered by time, each with a short summary so you can follow the thread without clicking through. The numbered links work both ways: tap a source under a point to jump to that report, tap the cited-by chip on a report to jump back to the point.

Key points5 items Model summary · ordered by when the evidence was published

  1. Point 01 11/16, 13:00

    arXiv 2611.17754v1 发布新论文,主题是掩码扩散语言模型的方差缩减后训练方法

  2. Point 02 11/16, 13:00

    该论文指出策略梯度方法被广泛用于对齐大语言模型输出与人类偏好,但对数似然计算存在代价问题

  3. Point 03 11/18, 13:00

    ReMaRL(arXiv 2611.22576v1)关注冻结扩散语言模型中 token 解掩顺序对最终答案准确率的影响

  4. Point 04 11/19, 13:00

    OpenGNS(arXiv 2611.24331v1)发布覆盖视觉、语言与扩散模型的梯度噪声规模开放数据集

  5. Point 05 11/19, 13:00

    OpenGNS 所依据的 GNS 指标衡量随机梯度下降中梯度的信噪比

ReportsBy publish time · newer further down

  1. November 16, 2026 · Mon
  2. Start

    See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models

    Original summary arXiv:2611.17754v1 Announce Type: new Abstract: Policy gradient methods are widely used to align large language model outputs with human preferences, but the log-likelihoods they r

    arXiv cs.CL Original ↗
    Cited by Point 01 Point 02 Cited
  3. November 18, 2026 · Wed
  4. +2d 0h

    ReMaRL: Learning to Unmask and Remask in Frozen Diffusion Language Models

    Original summary arXiv:2611.22576v1 Announce Type: new Abstract: Masked diffusion language models generate tokens in parallel, and the order in which tokens are unmasked affects final-answer accura

    arXiv cs.LG Original ↗
    Cited by Point 03 Cited
  5. November 19, 2026 · Thu
  6. +3d 0h

    OpenGNS: An Open Dataset of the Gradient Noise Scale across Vision, Language, and Diffusion Models

    Original summary arXiv:2611.24331v1 Announce Type: new Abstract: The Gradient Noise Scale (GNS) metric measures the signal-to-noise ratio of gradients in stochastic gradient descent and, as shown b

    arXiv cs.LG Original ↗
    Cited by Point 04 Point 05 Cited
  7. Still developing · later reports will keep extending this axis

Related reading

RISA: Recoverable Sparse Attention for Block-Diffusion Language Models
arXiv:2611.22191v1 Announce Type: new Abstract: Block-wise diffusion language models (DLMs) refine multiple tokens in pa
arXiv cs.CL 11/18/2026 Full text here
77pts