HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 10 Dec 2025 17:10:29 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6939a985-3bc1" expires: Tue, 30 Dec 2025 08:49:09 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: D587:3157C7:9C1827:AF7AC4:69538FAD accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 08:39:09 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210067-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767083950.742733,VS0,VE222 vary: Accept-Encoding x-fastly-request-id: 53dfd6af25eb3ad42d94d93c3d6aaf4c57acbcfe content-length: 3716

Wenxuan Peng I am a second-year CS PhD student at Cornell University, co-supervised by Prof. Bharath Hariharan and Prof. Hadar Averbuch-Elor. Before that, I obtained my Bachelor’s degree in Computer Science from Nanyang Technological University in Singapore. I've had the opportunity to dive into research at MMLab@NTU, guided by Prof. Ziwei Liu. I was also fortunate to collaborate with Prof. Jean Oh and Prof. Deva Ramanan as a research intern at Carnegie Mellon University. Google Scholar / Email / Github / LinkedIn

Research My research interests lie in the area of generative models, multi-modal vision-language models, and human interactions.

	NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples Baiqi Li*, Zhiqiu Lin*, Wenxuan Peng*, Jean de Dieu Nyandwi*, Zixian Ma, Simran Khanuja, Ranjay Krishna, Graham Neubig, Deva Ramanan (*: equal contribution) NeurIPS D&B, 2024 project page / paper / code
	Personalized Comic Story Generation Wenxuan Peng, Peter Schaldenbrand, Jean Oh, NeurIPS Workshop on Machine Learning for Creativity and Design, 2023 (Spotlight) paper
	Panoptic Video Scene Graph Generation Jingkang Yang*, Wenxuan Peng*, Xiangtai Li, Zujin Guo, Liangyu Chen, Bo Li, Zheng Ma, Kaiyang Zhou, Wayne Zhang, Chen Change Loy, Ziwei Liu, CVPR, 2023 project page / paper / code
	4D Panoptic Scene Graph Generation Jingkang Yang, Jun Cen, Wenxuan Peng, Shuai Liu, Fangzhou Hong, Xiangtai Li, Kaiyang Zhou, Qifeng Chen, Ziwei Liu, NeurIPS, 2023   (Spotlight) paper / code

Education
	Nanyang Technological University (NTU), Singapore B.E. in Computer Science Aug. 2020 - May. 2024
	National University of Singapore (NUS), Singapore SUSEP Exchange Programme Aug. 2021 - Dec. 2021

Experiences
	Carnegie Mellon University Robotics Institute Summer Scholar May.2023 - Jul.2023 Advisor: Prof. Jean Oh
	ByteDance, Singapore Computer Vision Engineer May.2022 - Jul.2022
	MMLab, NTU Undergraduate Researcher Aug.2021 - May.2024 Advisor: Prof. Ziwei Liu

Selected Awards and Honors

[2021-2023] Dean's List (Top 5%), School of Computer Science and Engineering, Nanyang Technological University [2022] NTU President Research Scholar [2019-2024] Science & Engineering Full Scholarship, Ministry of Education, Singapore