English(EN) Grounding on Request: Learning Modality Control in Vision-Language Models

新方法增强了视觉-语言模型对冲突模态的控制能力

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

研究人员开发了一种新方法来改进视觉-语言模型（VLM）中的模态控制。该技术称为“按需接地”，侧重于教会模型即使在模态冲突时也能遵循特定的模态（图像或文本）。这是通过反事实干预实现的，反事实干预会根据对所选模态的编辑来测试模型保持或更改答案的能力。研究发现，学习到的模态词和反事实监督增强了控制能力，而轻量级的视觉控制被证明效果出奇地好。 AI

影响提高了视觉-语言模型在信息冲突场景下的可靠性，有可能增强其在需要精确模态遵循的应用中的使用。

排序理由详细介绍视觉-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.CL 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: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍视觉-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: 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.CL TIER_1 English(EN) · Maxime Dassen, Alexander Martin, Andrew Yates, Reno Kriz, William Walden · 2026-10-27 04:00

按需接地：学习视觉语言模型的模态控制

arXiv:2610.33841v1 Announce Type: cross Abstract: When an image and its caption disagree, can a user reliably control which one a vision-language model (VLM) follows? Accuracy alone cannot answer this question, since a model might give the correct answer from parametric knowledge…

本文如何被排名

报道来源 [1]

按需接地：学习视觉语言模型的模态控制

相关实体

相关话题