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 and 8 more
Renmin University of China
In latest · #13 2026-W40 #5 Added on 2026-10-21
One-line takeaway
LoopVL brings looped (recurrent) Transformers to vision-language models, iteratively refining a shared vision-language state.
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。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Multimodal
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.