Junran Peng

University of Science and Technology Beijing

Papers

Total Citations

H-Index

About

Junran Peng is a rising star in the field of generative artificial intelligence, with a primary focus on human motion generation and diffusion-based modeling. His most influential work, "StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework" (2024), addresses critical challenges in the rapidly evolving domain of diffusion models for human motion synthesis. Peng’s research systematically investigates the design of network architectures and training strategies—areas where prior work often relied on disparate, unexamined approaches. By clarifying the effects of each component, his contributions enable more robust and efficient motion generation, a key requirement for applications in animation, robotics, and virtual reality. With 19 citations in just its first year, this paper signals strong early impact and recognition within the AI community. Peng’s work stands out for its methodological rigor and practical orientation, offering a foundational framework that helps researchers and practitioners build more reliable motion generation systems. As diffusion models continue to reshape generative AI, Junran Peng’s contributions are poised to influence both academic research and real-world deployment in human-centric computing.