Yana Wei

Ph.D. Student @ Johns Hopkins University

ywei66 [at] jh.edu

Greetings! Welcome to my homepage!

I am a first year Ph.D. student in Computer Science at VIU Lab, Johns Hopkins University, advised by Prof. Vishal Patel. I earned my Bachelor's degree in Software Engineering at Shandong University in 2021, followed by a M.S. degree of Computer Science at ShanghaiTech University in 2024, supervised by Prof. Xuming He.

My research interests broadly include computer vision, natural language processing and embodied agents, with a focus on vision-languge understanding. I'm excited about creating AI agents that can understand human needs across various modalities.

Recent highlights

🎉🎉[July, 2024] Our paper Merlin: Empowering Multimodal LLMs with Foresight Minds has been accepted to ECCV 2024.
🎉🎉[December, 2023] We present Merlin, the first end-to-end multimodal large language model that supports video-level visual localization (including tracking, video recognition, video registration, etc.) and future reasoning.
🎉🎉[July, 2023] Our paper Grounded Image Text Matching with Mismatched Relation Reasoning has been accepted to ICCV 2023.

Selected publications

Merlin: Empowering Multimodal LLMs with Foresight Minds

En Yu*, Liang Zhao*, Yana Wei, Jinrong Yang, Dongming Wu, Lingyu Kong, Haoran Wei, Tiancai Wang, Zheng Ge, Xiangyu Zhang, Wenbing Tao

ECCV 2024

[Project Page] [Paper]
Grounded Image Text Matching with Mismatched Relation Reasoning

Yu Wu*, Yana Wei*, Haozhe Wang, Yongfei Liu, Sibei Yang, Xuming He

ICCV 2023

[Project Page] [Paper] [Suppl] [Code] [Video]

Awards

Third Prize, 11th National College Student Mathematics Competition, 2019
First Prize, 17th Shandong Province College Student Software Design Competition, 2019
First Prize, 2019 National College Student Mathematical Modeling Competition, 2019
Second Prize, 7th "Teddy Cup" National Data Mining Challenge, 2019

Ph.D. Student @ Johns Hopkins University

Recent highlights

Selected publications

Merlin: Empowering Multimodal LLMs with Foresight Minds

Grounded Image Text Matching with Mismatched Relation Reasoning

Awards

Singing Videos