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 and 4 more
Qwen
In latest · #102 Added on 2026-10-21
One-line takeaway
VisionWeave lets MLLMs learn end-to-end where and how finely to spend visual tokens, adapting to image content.
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。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Multimodal
- 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
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.