English(EN) PixSearch: Region-Grounded Retrieval for Knowledgeable Large Multimodal Models

PixSearch 统一了区域锚定的检索，用于多模态模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了 PixSearch，这是一种新颖的端到端大型多模态模型（LMM），旨在改进用于视觉问答的区域锚定检索。与可能传播错误并增加延迟的模块化系统不同，PixSearch 将视觉锚定与检索增强推理相结合。该模型学会触发检索，跨文本、整个图像和区域级数据选择查询，并将目标实体裁剪为视觉查询。与 GroundedSAM-LLaVA 管道相比，这种方法在 CRAG-MM 基准测试上准确率提高了 18.3%，推理延迟降低了 36.4%，尤其在以自我为中心的图像上表现出色。 AI

影响通过整合区域特定的视觉锚定与检索，增强了多模态推理能力，有望提高复杂视觉问答任务的性能。

排序理由详细介绍新模型架构及其在基准测试上性能的研究论文。[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: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新模型架构及其在基准测试上性能的研究论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jeonghwan Kim, Renjie Tao, Sanat Sharma, Jiaqi Wang, Kai Sun, Zhaojiang Lin, Seungwhan Moon, Lambert Mathias, Anuj Kumar, Heng Ji, Xin Luna Dong · 2026-10-15 04:00

PixSearch：面向知识型大型多模态模型的区域接地检索

arXiv:2601.19060v2 Announce Type: replace-cross Abstract: Multimodal Retrieval-Augmented Generation (MM-RAG) augments visual question answering (VQA) with external knowledge, but many systems rely on modular pipelines that separate visual grounding, query construction, and answer…

本文如何被排名

报道来源 [1]

PixSearch：面向知识型大型多模态模型的区域接地检索

相关实体

相关话题