Cite
Notes
Only stored in your browser.
Attribution
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
arXiv 2026
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
arXiv 2025
from 3 papers
Bin Qin
Bo Li
Chunyuan Li
Huajie Tan
Jiankang Deng
Kaicheng Yang
Xiang An
Yin Xie
Ziwei Liu
Ziyong Feng