Seed1.5-VL Technical Report

Renjie Zheng is a researcher at ByteDance. His public OpenReview profile lists prior research experience at Baidu Research and earlier study at Oregon State University and Tongji University, with public work spanning NLP, language models, and reasoning-related research.

Yuwen Xiong is a Research Scientist at ByteDance Seed in the Bay Area. He received a Ph.D. from the University of Toronto's Machine Learning Group and previously worked at Waabi and Uber ATG.

Feida Zhu is a ByteDance researcher in computer vision. Public sources show prior roles at Tencent Youtu Lab and Nanyang Technological University, and a PhD in Computer Science from The University of Hong Kong.

Public sources identify Can Huang as a ByteDance researcher. OpenReview lists prior research work at Intsig Information Co. Ltd., master's study at Shanghai Jiao Tong University, and undergraduate study at Xi'an Jiaotong University.

Weihao Yu is a researcher in computer vision, multimodal AI, and neural architecture design. Public profiles show PhD and postdoctoral work at the National University of Singapore, a 2025 Research Scientist role at ByteDance Seed, and a 2026 appointment at Peking University Shenzhen Graduate School.

Jian-Hui Duan is an algorithm researcher in the ByteDance Seed LLM team whose public homepage highlights work on pretraining data, training optimization, and distribution-shift mitigation for large language models.

Rui Qian is a researcher at ByteDance Seed. Qian received a Ph.D. from The Chinese University of Hong Kong and a bachelor's degree from Shanghai Jiao Tong University in 2021.

Yujia Qin focuses on LLM/VLM-based agents. The official homepage lists a Ph.D. in Computer Science from Tsinghua University (2020-2024), a B.E. in Electronic Information Science and Technology from Tsinghua University (2016-2020), and Seed at ByteDance starting in July 2024.

Yifan Du is a Ph.D. student at Renmin University of China advised by Wayne Xin Zhao. His public homepage lists research interests in multimodal large language models, visual instruction tuning, long video understanding, and complex visual reasoning, and it lists a VLM post-training internship at ByteDance Seed.

Chenwei Lou is a researcher at ByteDance Seed. Public profiles indicate earlier research experience at Tencent, an MS period at Harbin Institute of Technology, and earlier undergraduate study at Jilin University.

MS student at Peking University's Wangxuan Institute of Computer Technology working on visual reasoning, VLM, OCR, and handwritten mathematical expression recognition.

Chenhui Gou is a PhD student at Monash University in the Vision & Language for Autonomous AI Group. Public profiles list his research in computer vision, visual perception, and reasoning, following earlier master's study at the Australian National University.

Tenglong Ao is a computer science researcher whose public work focuses on character animation, co-speech gesture generation, music-driven dance generation, and multimodal agent behavior. Public sources indicate he received a Ph.D. in computer science from Peking University and a B.S. in electronic engineering from Tsinghua University.

Zilong Huang is a principal researcher at Tencent Singapore whose work focuses on multimodal interaction, multimodal agents, multimodal pretraining, and efficient model architectures. He previously worked at ByteDance and received his Ph.D. and B.E. from Huazhong University of Science and Technology.

Bencheng Liao is a PhD student at the Institute of Artificial Intelligence, Huazhong University of Science and Technology. Public profiles list research interests including autonomous driving, object detection, and visual perception.

Joya Chen is a final-year Ph.D. candidate at Show Lab, National University of Singapore, advised by Mike Zheng Shou. Her research focuses on large multimodal models for video, including data scaling, model architecture, pre-training, post-training, and benchmarking.

Public sources connect Renrui Zhang to multimodal large language models, 3D point cloud analysis, and efficient model adaptation.

Rui Yang is a PhD student at The University of Hong Kong. Public OpenReview and DBLP records link him to research on multimodal large language models, language agents, and vision-language systems, including GPT4Tools, HaploVL, and Visual Spatial Tuning.

Yining Ye (叶奕宁) is a master's student in the THUNLP Lab at Tsinghua University advised by Zhiyuan Liu. Public profiles describe research on LLM/VLM agents, tool learning, and unified language models.

Yurui Ren is a researcher working on image/video synthesis and image enhancement. Public sources identify him as a Ph.D. student at Peking University (2017-2022), advised by Ge Li, with a B.S. from Dalian University of Technology.

Public sources associate Zewei Sun with ByteDance and list Nanjing University education (BS 2013-2017, MS 2017-2020), with research spanning machine translation and later large language model work.

Yufeng Yuan is listed on OpenReview as staff at ByteDance Seed, previously at Tencent AI Lab, with an MS in Computing Science from the University of Alberta.

Public records identify Xuefeng Xiao as a ByteDance-affiliated researcher whose work centers on model compression, optimization, and acceleration; his OpenReview profile also lists M.S. study at South China University of Technology.

Junting Lu is a final-year M.S. student at the Institute for Software Engineering, Peking University. His homepage lists research interests in tool learning, OS agents, and native vision-language agents.

Canonical link

Renjie Zheng

Yuwen Xiong

Feida Zhu

Can Huang

Weihao Yu

Jianhui Duan

Rui Qian

Yujia Qin

Yifan Du

Chenwei Lou

Jianhua Zhu

Chenhui Gou

Tenglong Ao

Zilong Huang

Bencheng Liao

Joya Chen

Renrui Zhang

Rui Yang

Yining Ye

Yurui Ren

Zewei Sun

Yufeng Yuan

Xuefeng Xiao

Junting Lu