Cite
Notes
Only stored in your browser.
Attribution
Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
arXiv 2026
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
arXiv 2024
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
arXiv 2023
from 3 papers
Qing Li
Xiaojian Ma
Baobao Chang
Bingxuan Lin
Diyun Xiang
Dong Wang
Donghao Wang
Fei Ma
Feng Qiu
Futeng Liu