–
Nanyang Technological University
PhD · Expected completion in June 2030
Researcher & PhD Student
PhD Student
NTU
I am currently pursuing my PhD at Nanyang Technological University (NTU), where I work with Wanhua Li and Jianfei Yang. I am also a research intern at Tencent IEG-ARC Lab (now New ARC Lab) through the Qingyun Talent Program, mentored by Yeying Jin. I’m fortunate to work closely with Prof. Ming-Hsuan Yang and Prof. Felix Heide, while also collaborating with Wei Xiong and Enze Xie at NVIDIA.
I am also the Founder of OpenEnvision. OpenEnvision is a joint research hub advancing open vision intelligence through academia-industry collaboration. We work closely with academic partners such as UC San Diego, UIUC, Princeton, NTU, and MMLab, as well as industry collaborators including Nvidia, Adobe, Meta, and ByteDance Seed. We continue to expand our impact through open-source projects and knowledge sharing. If you are interested in collaborating with us, feel free to contact me.
I currently lead the development of WorldFoundry and WorldAtlas. Stay tuned!
My research focuses on vision intelligence in multimodal systems, world models, and Phys AI, with broader interests in Generative AI and Efficient AI. I have published papers at top-tier conferences and serve as a reviewer for leading conferences and journals.
juanxitian1031@gmail.com JTIAN003@e.ntu.edu.sg
–
PhD · Expected completion in June 2030
–
BSc (Honours) in Computer Science & Artificial Intelligence
– Now

Research Intern
–

Research Intern
–

Research Intern
–
Research Intern
Recent updates, achievements, and announcements
I received an internship offer through the Tencent Qingyun Talent Program at Tencent IEG-ARC Lab (now New ARC Lab). My research will focus on Game World Model and Interactive Video Generation.
One paper on multimodal generation was accepted to NeurIPS.
I was invited by Professor Hao Zhao of Tsinghua University to give a talk about OpenEnvision and WorldFoundry.
OpenEnvision/WorldFoundry is now open source. Stars and pull requests are welcome!
One paper on multimodal generation was accepted to the European Conference on Computer Vision (ECCV).
I received the PhD offer from Nanyang Technological University (NTU). My upcoming research will focus on vision intelligence in multimodal systems, world models, and Phys AI.
I'm always happy to connect on research, collaboration, and new ideas in AI, and I'm also glad to chat about academia, career development, and graduate study planning.