Cite
Notes
Only stored in your browser.
Attribution
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
arXiv 2026
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models
CVPR 2024 1
from 3 papers
Chongyi Wang
Tianyu Yu
Wenshuo Ma
Yuan Yao
Bokai Xu
researcher
Chaojun Xiao
Chi Chen
Fuwei Huang
Guoyang Zeng
Hanyu Liu