Cite
Notes
Only stored in your browser.
Attribution
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
arXiv 2025
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
from 3 papers
Haodong Duan
Kai Chen
Xiangyu Zhao
Bin Fu
Biqing Qi
Botian Shi
Bowen Yang
Bowen Zhou
professor
Changyao Tian
Chengqi Lyu