PulseAugur
中
实时 22:48:32

新的SoftMoR技术使Vision Transformers更深入、更高效

研究人员推出了一种名为Soft Mixture-of-Recursions (SoftMoR) 的新方法,通过使Vision Transformers (ViTs) 能够利用所有递归步骤的中间表示来增强它们。这种方法以Soft Recursive Vision Transformer (SR-ViT) 的形式实现,可以在参数增加极少的情况下创建更深入、更强大的ViTs。在ImageNet-1K上的实验表明,将SR-ViT-S的递归深度从一次增加到四次,可以将top-1准确率从79.83%提高到82.48%,同时使用的参数量远少于DeiT-B等大型模型。 AI

影响 这项研究提供了一种参数高效的方法来开发更强大的Vision Transformers,可能对计算机视觉应用产生影响。

排序理由 该集群包含一篇详细介绍改进Vision Transformers新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的SoftMoR技术使Vision Transformers更深入、更高效

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改进Vision Transformers新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
87 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 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 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Sang In Lee, Jihun Park ·

    Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers

    arXiv:2607.00774v1 Announce Type: cross Abstract: Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models. In this work, we leverage recursion to build effectively deeper Transformers w…

  2. arXiv cs.LG TIER_1 English(EN) · Jihun Park ·

    Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers

    Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models. In this work, we leverage recursion to build effectively deeper Transformers with stronger representational capacity. However, i…