Qwen2.5-VL Technical Report

Junyang Lin (Justin Lin) is a researcher and open-source maintainer known for the Qwen family of models. His public profiles list interests in LLMs, AI agents, multimodal learning, long-horizon reasoning, world models, and reinforcement learning; multiple March 2026 news reports said he stepped down from the Qwen tech lead role.

Senior algorithm expert at Alibaba Group working on large language models, multimodal large language models, and diffusion models.

Jian Yang is an Associate Professor at Beihang University whose research focuses on code intelligence, large language models, and AI agents. He worked with Alibaba Qwen from 2023 to July 2025.

Research scientist in Tongyi Lab whose public homepage and OpenReview profile describe work on large language models, multimodal learning, and visual grounding. His public profiles also list affiliations with Alibaba Group and East China Normal University.

Research scientist at Alibaba working on multimodal learning and generation; previously a postdoctoral researcher at Carnegie Mellon University.

Jun Tang works on multimodal foundation models, open-source language models, and agent systems. His personal site highlights work on Qwen and Qwen3-VL alongside related multimodal research.

Researcher focused on large language models and multimodal learning, with public profiles linking Keqin Chen to Beihang University and to Qwen vision-language model work.

Qwen researcher and author on the Qwen2-VL and Qwen2.5-VL technical reports, with public profiles linking his work to multimodal and vision-language systems.

Jiahao Liu works on multimodal large language models, reasoning systems, and continual learning. His public profiles connect him to the Qwen2.5-VL technical report and related open research work.

Mingkun Yang works on multimodal large language models, embodied AI, and robotics. His public profile says he is a postdoc at Zhejiang University and a research scientist at Qwen.

Research scientist in Alibaba DAMO Academy's Tongyi Lab working on multimodal learning, vision-language models, and embodied AI; author on the Qwen2-VL and Qwen2.5-VL technical reports.

Zhibo Yang works on multimodal and vision-language systems. Public profiles connect him to the Qwen2.5-VL technical report and to an individual GitHub account that links back to his personal site.

Research scientist on the Qwen team at Alibaba Group, focusing on foundation models and language agents. He received a PhD in computer science from the University of Illinois Urbana-Champaign.

PhD student in CSLT at Tsinghua University working on large language models, multimodal large language models, and speech-language models; publication context connects Jinbo Zhao to the Qwen2.5-VL technical report.

Alibaba senior technology leader and researcher associated with Qwen. Public profiles list him with Alibaba Group, and official Alibaba Cloud coverage identifies him as a chief technology officer leading large-model work.

Researcher on Alibaba's Qwen team focused on large language models and NLP, with public research profiles listing a Nankai University background.

Alibaba researcher working on large language models and multimodal pretraining; public research profiles connect An Yang to Qwen-related work and earlier study at Peking University.

Researcher affiliated with the Qwen team at Alibaba Group on Google Scholar and coauthor of the Qwen and Qwen3 technical reports.

Research scientist in Tongyi Lab whose official profile highlights work on efficient reinforcement learning, generalization, inference-time scaling, and reasoning for large language models.

Independent researcher focused on multimodal learning, document intelligence, and efficient training; coauthor of Qwen2.5-VL and mPLUG-related vision-language systems.

Research scientist in Tongyi Lab and contributor to Qwen2-VL, with public work on multimodal large language models.

Research scientist in Alibaba DAMO Academy's Tongyi Lab working on machine learning, computer vision, and multimodal large language models; author on the Qwen2-VL and Qwen2.5-VL technical reports.

Research scientist in Tongyi Lab and maintainer of Qwen-VL, with public work on vision-language models.

Xuejing Liu is a researcher whose public OpenReview profile includes the Qwen2-VL and Qwen2.5-VL technical report papers.