Jiancheng Lv

V-Zero achieves fine-grained visual reasoning without any annotated answer labels, outperforming traditional methods in both speed and accuracy.

Unified vision-language perception in MLLMs is not just an evolution; it’s a critical leap toward achieving artificial general intelligence.

STORM recovers up to 63.3% accuracy in visual state space models by enforcing spatial awareness in token reduction, transforming how we approach model efficiency.

scGTN not only captures the complex intercellular relationships in single-cell RNA sequencing data but also achieves superior clustering performance compared to traditional methods.