PulseAugur
中
实时 15:49:30
English(EN) Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

新研究探索扩散模型优化和控制技术 · 已追踪 4 个来源

作者 PulseAugur 编辑部 · [6 个来源] ·

研究人员正在探索扩散模型的先进方法，重点是优化采样过程和控制分布。一篇论文介绍了“优化你的采样”（OYS），这是一种贝叶斯优化技术，可调整文本到图像和修复任务的采样时间步长，从而在降低推理成本的同时显著提高质量。另一项研究提出了一个用于推理时分布控制的均场框架，为引导扩散模型走向期望分布提供了理论保证，可应用于蛋白质构象等任务。第三篇论文全面介绍了通用状态空间中的扩散模型，统一了连续和离散域，重点关注理论基础和训练原则。最后，第四篇论文解决了参数不确定性下的扩散控制问题，提出了一种分布鲁棒的贝叶斯控制公式，以减轻错误指定并改进策略评估。 AI

影响 扩散模型采样和控制的进步可能带来更高效、更多功能的生成式 AI 应用。

排序理由 该集群包含多篇关于扩散模型的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →

新研究探索扩散模型优化和控制技术 · 已追踪 4 个来源

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
Research
该集群包含多篇关于扩散模型的学术论文。
Source corroboration
6 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, other
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
54 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+2 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [6]

  1. arXiv cs.LG TIER_1 English(EN) · Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth ·

    嵌套序列蒙特卡洛的离散扩散推理时控制

    arXiv:2608.20123v1 Announce Type: cross Abstract: We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without retraining. Prior work in this domain has focused on particle-bas…

  2. arXiv cs.LG TIER_1 English(EN) · Travis Zhang, Christian Belardi, Justin Lovelace, Jin Peng Zhou, Saebyeol Shin, Carla P. Gomes, Kilian Q. Weinberger ·

    优化您的采样：基于贝叶斯优化的调优扩散采样

    arXiv:2608.18040v1 Announce Type: new Abstract: Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparatively little …

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    用于扩散模型推理时分布控制的均场框架

    Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are typically defined on individual samples, for many applications it is desirable to steer according to d…

  4. arXiv cs.CV TIER_1 English(EN) · Libo Chen, Souvik Ghosh, Teo Deveney, Chris Budd, Vinay P. Namboodiri ·

    基于评分的扩散模型中条件约束的插件式解释

    arXiv:2608.19504v1 Announce Type: new Abstract: We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an unconditional joint score network and enforces conditioning at inference via a pl…

  5. arXiv stat.ML TIER_1 English(EN) · Vincent Pauline, Tobias H\"oppe, Kirill Neklyudov, Alexander Tong, Stefan Bauer, Andrea Dittadi ·

    通用状态空间中的扩散模型基础：自包含式导论

    arXiv:2512.05092v2 Announce Type: replace Abstract: Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom clarify their connection to discrete-state analogues. This article is a self-containe…

  6. arXiv stat.ML TIER_1 English(EN) · Jose Blanchet, Jiayi Cheng, Yuewei Ling, Hao Liu, Yang Liu ·

    分布鲁棒贝叶斯扩散控制中的对偶与策略评估

    arXiv:2506.19294v4 Announce Type: replace-cross Abstract: We study diffusion control problems under parameter uncertainty. Controllers based on plug-in estimation can be brittle due to potential distribution shifts. Bayesian control with a prior on the parameters offers a formula…

相关实体

相关话题