arXiv 2610.07987 · cs.CV · 2026-10-06
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu 等 12 人
Qwen
在最新榜 #102 本站收录于 2026-10-21
一句话要点
VisionWeave 让多模态模型端到端学会按内容分配视觉 token 粒度，细节处多给、简单处少给。
VisionWeave lets MLLMs learn end-to-end where and how finely to spend visual tokens, adapting to image content.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：多模态
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲560
- LoopVL: Recurrent Visual Intelligence ▲417
- 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
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。