☕️I’m Junqi Jing (荆浚淇), a 3rd/4 undergraduate in Software Engineering at Harbin Institute of Technology. My primary research areas are Embodied AI and diffusion models. I am dedicated to exploring the integration of generative AI and embodied intelligence, particularly focusing on diffusion policies and using generative approaches to address data scarcity. Recently, I have been deeply interested in learning from large-scale human video data. If you have any ideas or insights related to this topic, feel free to reach out to me via email. During my undergraduate studies at Harbin Institute of Technology, I was fortunate to join the Institute of Cross-Media Intelligence for research. I am deeply grateful to Prof. Zhaobo Qi, Prof. Weigang Zhang, and Prof. Shuhui Wang for their invaluable guidance. Under their supervision and through close collaboration with my teammates, I contributed to my first top-tier conference paper at ICLR.
I have previously conducted research visits at MiLab, Westlake University, and Nanjing University (Suzhou), where I had the great honor of collaborating with Prof. Donglin Wang and Prof. Kai Zhang.
Currently, I am spending one semester at POSTECH MLV Lab, working in collaboration with Prof. Kwang In Kim.
I am currently seeking a 2025 winter internship.
If you have any ideas or potential collaborations, feel free to contact me at jqjing@stu.hit.edu.cn or xingkong8527@gmail.com.
BE in Software Engineering
Harbin Institute of Technology
I’m thrilled to begin my visit to the Suzhou campus of Nanjing University, where I’ll be joining Prof. Kai Zhang’s lab to explore the application of generative AI and diffusion policies in embodied intelligence.
I’m excited to contribute as a PC member and reviewer for the NeurIPS 2025 Workshop on Embodied World Models for Decision Making, which focuses on world models in embodied AI. The workshop will take place in San Diego, USA.
I will begin a semester-long exchange at POSTECH in South Korea. During the exchange, I’m excited to join MLVlab and collaborate with Professor Kwang In Kim on research in Embodied AI and generative AI.
In this work, we propose a novel modeling method for heterogeneous hybrid objects, based on improvements to the Spring-Gaus physics engine. I contributed to simulation, GNN modeling, experiments, and dataset creation.
We propose a novel Masked Temporal Interpolation Diffusion (MTID) model for procedure planning in instructional videos. The paper is officially accepted at ICLR 2025.
