To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models

Jiayun L, Wan-cyuan F, Lyuyang W, Xiangteng H, Tanzila R, Purang A, Leonid S

Preprint

[Paper]

Barking Up The Syntactic Tree: Enhancing Emergent Visual Grounding with Syntactic Losses 

Jiayun L, Rayat H, Boyang L, Leonid S 

Preprint

[Paper]

Emergent Open-Vocabulary Semantic Segmentation from Off-the-Shelf Vision-Language Models 

Jiayun L, Siddhesh K, Leonid S, Boyang L

CVPR 2024

[Paper] [Project Page]

A Survey of Computer Vision Technologies in Urban and Controlled-environment Agriculture 

Jiayun L, Boyang L, Cyril L 

ACM Computing Surveys, 2023

[Paper]

Graph neural network for traffic forecasting: A survey 

Weiwei J, Jiayun L  

Expert Systems with Applications, 2022

[Paper]