2602.08683
2026-02-27
cs.CV
50%
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
OneVision-Encoder: 编码对齐的稀疏性作为多模态智能的基础原则
Feilong Tang, Xiang An, Yunyao Yan, Yin Xie, Bin Qin, Kaicheng Yang, Yifei Shen, Yuanhan Zhang, Chunyuan Li, Shikun Feng, Changrui Chen, Huajie Tan, Ming Hu, Manyuan Zhang, Bo Li, Ziyong Feng, Ziwei Liu, Zongyuan Ge, Jiankang Deng
机构
*
Glint Lab(Glint实验室)
;
AIM for Health Lab(健康人工智能实验室)
;
MVP Lab(MVP实验室)
专题命中
视觉空间推理
:reasoning(abstract)
AI总结
OneVision-Encoder通过编码对齐的稀疏性原则,实现高效的多模态视觉理解。