arXiv 2609.38426 · cs.CV · 2026-09-29
LoopVL: Recurrent Visual Intelligence
Zhe Qian, Ziyang Gong, Zhongxing Xu, Hehan Li, Zhonghua Wang, Hanmeng Liu, Liwei Qian, Xin Pei 等 16 人
Renmin University of China
在最新榜 #13 2026-W40 第 5 名 本站收录于 2026-10-21
一句话要点
LoopVL 把循环 Transformer 扩展到视觉语言模型，在多次循环中反复更新视觉-语言状态。
LoopVL brings looped (recurrent) Transformers to vision-language models, iteratively refining a shared vision-language state.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：多模态
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲560
- VideoJev: System One Model for Video Understanding and Interaction ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models ▲270
- UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement ▲266
- OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction ▲238
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。