Carview!

CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 accept-ranges: bytes age: 1 cache-control: public,max-age=0,must-revalidate cache-status: "Netlify Edge"; fwd=miss content-encoding: gzip content-type: text/html; charset=UTF-8 date: Mon, 29 Dec 2025 11:16:58 GMT etag: "6349a22c554574e3f05e2f230c16ad14-ssl-df" server: Netlify strict-transport-security: max-age=31536000 vary: Accept-Encoding x-nf-request-id: 01KDMX6PX3QX4478KG6FY05WBY Wenqi Wang

Wenqi Wang (王文琦)

Hello! I am a Ph.D. student in Computer Science at Boston University, where I am fortunate to be advised by Prof. Boqing Gong.

I completed my Bachelor's degree in Computer Science and Technology at Tsinghua University. My research focuses on computer vision, with a particular interest in vision-language foundation models and their applications in understanding and generating multimodal content.

Email / CV / Google Scholar / Twitter / Github

Research

BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
Shengao Wang*, Wenqi Wang*, Zecheng Wang*, Max Whitton*,
Michael Wakeham, Arjun Chandra, Joey Huang, Pengyue Zhu,
Helen Chen, David Li, Jeffrey Li, Shawn L. Li, Andrew Zagula, Amy Zhao, Andrew Zhu, Sayaka Nakamura, Yuki Yamamoto, Jerry Jun Yokono, Aaron Mueller, Bryan A. Plummer, Kate Saenko, Venkatesh Saligrama, Boqing Gong
*Equal Contribution, ArXiv, 2025
project page(TBD) / code(TBD) / arXiv

BabyVLM-V2 is an infant-inspired vision-language framework with a longitudinal pretraining corpus and a cognitive benchmark, showing that compact models trained from scratch can achieve competitive performance.

SITE: towards Spatial Intelligence Thorough Evaluation
Wenqi Wang, Reuben Tan, Pengyue Zhu, Jianwei Yang, Zhengyuan Yang, Lijuan Wang, Andrey Kolobov, Jianfeng Gao, Boqing Gong
ICCV, 2025
project page / code / arXiv

We curate a benchmark combining a bottom-up survey and a top-down strategy drawing upon three classification systems in cognitive science, including 31 computer vision datasets and 8000+ evaluation samples.

Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstruction
Yizhi Wang, Wallace Lira, Wenqi Wang, Ali Mahdavi-Amiri, Hao (Richard) Zhang,
CVPR, 2024
project page / arXiv / code / video

Our single-view 3D reconstruction method, Slice3D, predicts multi-slice images to reveal occluded parts without changing the camera (in contrast to multi-view synthesis), and then lifts the slices into a 3D model.

Education

	Boston University, Boston, MA Ph.D. in Computer Science, 2024 - Present Advisor: Prof. Boqing Gong
	Tsinghua University, Beijing, China B.Eng. in Computer Science and Technology, 2020 - 2024

Miscellanea

I enjoy photography in my spare time. Check out my gallery!
I have served as reviewer for various conferences and journals including CVPR, ICCV.

Clone from source code.

Original Source | Taken Source