Nan DUAN (段楠)

Google Scholar | LinkedIn | 京东探索研究院

We are hiring researchers and interns: duannan@jd.com (official) or nanduan.nlp@outlook.com (personal).

Dr. Nan Duan is the Vice President of JD.COM and the Deputy Director of JD Future Academy, where he oversees and leads foundation model research in language, audio, vision, and embodied AI. Prior to this, he served as the Technical Fellow at StepFun and as the Senior Principal Researcher at Microsoft Research Asia. Dr. Duan is an adjunct professor and Ph.D. supervisor at the University of Science and Technology of China, Xi’an Jiaotong University, and Tianjin University. His research spans natural language processing, code intelligence, multimodal foundation models, and AI agents. He has authored over 200 research papers in top-tier conferences and journals, accumulating more than 40,000 citations (h-index 85+) and holds over 20 patents. In 2019, he was named the CCF-NLPCC Distinguished Young Scientist for his contributions to NLP, and in 2023, he was listed among the DeepTech Intelligent Computing Innovators in China for his work on AI foundation models.

段楠博士，现任京东集团副总裁、京东探索研究院副院长，领导语言、语音、视觉和具身智能领域的基础模型研究。此前，他曾任阶跃星辰Technical Fellow和微软亚洲研究院资深首席研究员。段博士是中国科学技术大学、西安交通大学和天津大学的兼职教授及博士生导师。他的研究兴趣包括自然语言处理、代码智能、多模态基础模型和AI智能体等。他在顶级会议和期刊上发表了超过200篇研究论文，累积引用超过40,000次(h-index 85+)，拥有20多项专利。2019年，他因在自然语言处理领域的贡献被评为CCF-NLPCC杰出青年科学家，2023年，他因在人工智能基础模型方面的贡献被列为DeepTech中国智能计算创新人物之一。

Highlight

• JoyAI-Echo-1.5 (Technical Report, 2026), SoTA interactive audio-video world model.
• JoyAI-Echo (Technical Report, 2026), SoTA minute-level multi-shot audio-video generation model.
• JoyAI-Video-Edit (Technical Report, 2026), SoTA real-time streaming video editing model.
• JoyAI-VL-Interaction (Technical Report, 2026), SoTA real-time vision-language interaction model.
• JoyAI-Image-Edit (Technical Report, 2026), a unified image understanding and generation model with spatial intelligence.
• Step-Video-T2V (Technical Report, 2025), SoTA text-to-video model.
• scGPT (Nature Methods, 2024), single-cell Generative Pre-trained Transformer.
• Not All Tokens Are What You Need (NeurIPS, 2024), Best Paper Runner-Up at NeurIPS 2024.
• Visual ChatGPT (Preprint, 2023), pioneer work in AI Agent, obtained 34k+ GitHub stars.
• VL-InterpreT (CVPR, 2022), Best Demo Award at CVPR 2022.
• NUWA(女娲) (ECCV, 2022) & NUWA-Infinity (NeurIPS, 2022), pioneer work in video generation model, reviewed by Bill Gates, cited by OpenAI Sora.
• CodeBERT (EMNLP, 2020) & CodeXGLUE (NeurIPS, 2021), pioneer work in code foundation model, cited by OpenAI Codex.
• Unicoder (EMNLP, 2019) / Unicoder-VL (AAAI, 2020), the 1st multilingual/multimodal pre-trained model deployed in Microsoft Bing for 100+ languages.

Academic Service & Award

• Adjunct Ph.D. Supervisor at Xi’an Jiaotong University (西安交通大学), University of Science and Technology of China (中国科学技术大学), Tianjin University (天津大学).
• Program Committee Chair of NLPCC, 2023.
• Senior Action Editor & Senior Area Chair of ACL Rolling Review (ARR)/NeurIPS/ACL/EMNLP/NAACL/SIGKDD.
• Standing Reviewer of TACL, 2020-present.
• Executive Member of China Society of Image and Graphics (CSIG), 2025-present.
• Executive Member of CCF Technical Committee of NLP, 2018-present.
• Senior Member of IEEE.
• Distinguished Member of CCF.
• AI 2000 Most Influential Scholar Award Honorable Mention in NLP, 2025.
• World’s Top 2% Scientists by Stanford, 2022-present.
• The Intelligent Computing Innovators China (中国智能计算科技创新人物), 2023.
• CCF-NLPCC Distinguished Young Scientist Award (CCF-NLPCC青年科学家奖), 2019.
• NeurIPS Best Paper Runner-Up Award, 2024.
• CVPR Best Demo Award, 2022.