English(EN) Oddin: Latent Visual Reasoning in Unified Multimodal Models via Self-Distillation from Image Generation

Oddin框架实现了多模态模型中的潜在视觉推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员推出Oddin，一个旨在增强统一多模态大模型（ULMMs）中潜在视觉推理的新框架。与需要生成中间图像的现有方法不同，Oddin在理解分支中处理紧凑的潜在令牌，仅将生成分支保留用于最终输出。该方法使用具有多个目标的离线自蒸馏进行训练，包括图像生成、文本蒸馏和特殊令牌交叉熵。在七项视觉推理任务上，Oddin的表现优于传统的交错生成基线和闭源视觉语言模型。 AI

影响无需生成中间图像即可实现多模态模型中的复杂视觉推理，可能降低计算开销。

排序理由该集群包含一篇详细介绍多模态模型新框架的研究论文。[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: 9 / 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多模态模型新框架的研究论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jaeyong Ko, Hankyeol Kim, Pilsung Kang · 2026-10-27 04:00

Oddin：通过自生成图像蒸馏实现统一多模态模型中的潜在视觉推理

arXiv:2610.33062v1 Announce Type: cross Abstract: Unified large multimodal models (ULMMs) are able to perform visual reasoning through interleaved text-image generation, but generating explicit intermediate images incurs significant computational overhead. While visual latent rea…

本文如何被排名

报道来源 [1]

Oddin：通过自生成图像蒸馏实现统一多模态模型中的潜在视觉推理

相关实体

相关话题