Junfeng Wu

I am a final-year PhD student at the VLR Group in Huazhong University of Science and Technology under the supervision of Prof. Xiang Bai. My primary research interests lie in the field of Computer Vision, with a focus on visual generation, multimodal large language models, general image and video object perception algorithms. Specifically, I am currently exploring the exciting domains of multi-modal large models (MLLMs) and unified vision understanding and generation tasks.

I also worked as a research intern at the ByteDance AI Lab, from 2021-2024.

I am currently on the job market. Please feel free to reach out if you are interested in my research.

Email / Google Scholar / Github

	UniTok: A Unified Tokenizer for Visual Generation and Understanding Chuofan Ma, Yi Jiang, Junfeng Wu, Jihan Yang, Xin Yu, Zehuan Yuan, Bingyue Peng, Xiaojuan Qi Arxiv, 2025 arXiv / code
	Liquid: Language Models are Scalable and Unified Multi-modal Generators Junfeng Wu, Yi Jiang, Chuofan Ma, Yuliang Liu, Hengshuang Zhao, Zehuan Yuan, Song Bai, Xiang Bai Arxiv, 2024 arXiv / code
	PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects Junyi Li, Junfeng Wu, Weizhi Zhao, Song Bai, Xiang Bai ECCV, 2024 arXiv / code
	General Object Foundation Model for Images and Videos at Scale Junfeng Wu, Yi Jiang, QiHao Liu, Zehuan Yuan, Xiang Bai, Song Bai CVPR, 2024 (Highlight) arXiv / code / video
	InstMove: Instance Motion for Object-centric Video Segmentation QiHao Liu, Junfeng Wu, Yi Jiang, Xiang Bai, Alan Yuille, Song Bai CVPR, 2023 arXiv / code
	In Defense of Online Models for Video Instance Segmentation Junfeng Wu, QiHao Liu, Yi Jiang, Song Bai, Alan Yuille, Xiang Bai ECCV, 2022 (Oral Presentation) arXiv / code / video
	SeqFormer: Sequential Transformer for Video Instance Segmentation Junfeng Wu, Yi Jiang, Song Bai, Wenqing Zhang, Xiang Bai ECCV, 2022 (Oral Presentation) arXiv / code /
	1st Place Solution for YouTubeVOS Challenge 2022: Video Instance Segmentation Junfeng Wu, Xiang Bai, Yi Jiang, Qihao Liu, Zehuan Yuan, Song Bai CVPR, 2022 workshop code

Design and source code from Jon Barron's website.