Jiayi Qian

Jiayi Qian (钱家熠)

I'm now a first-year ECE Ph.D. student in Synergy Lab at Georgia Institute of Technology, advised by Prof. Tushar Krishna on Efficient Compositional AI systems and ML Accelerator Design.

Prior to that, I obtained my M.S. degree in Computer Science, also from Georgia Institute of Technology, where I worked closely with Prof. Yingyan (Celine) Lin on efficient ML algorithms. I received my Bachelor's degree in Electronic Engineering from Tsinghua University, advised by Prof. Gang Liu on visual SLAM.

Email / CV / Google Scholar / LinkedIn

Research Interests

I'm interested in efficient machine learning algorithm and system design along with hardware accelerator design. I'm particularly interested in Embodied AI and Neuro-Symbolic AI systems. My publications are listed below.

	Compositional AI Beyond LLMs: System Implications of Neuro-Symbolic-Probabilistic Architectures Zishen Wan, Hanchen Yang, Jiayi Qian, Ritik Raj, Joongun Park, Chenyu Wang, Arijit Raychowdhury, Tushar Krishna ACM Inter Conf on Architectural Support for Programming Languages and Operating Systems (ASPLOS)*, 2026 Paper (To appear)
	Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment Zhenbang Du, Yonggan Fu, Lifu Wang, Jiayi Qian, Xiao Luo, Yingyan (Celine) Lin International Conference on Computer Vision (ICCV)*, 2025 Paper
	Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability Zishen Wan, Jiayi Qian, Yuhang Du, Jason Jabbour, Yilun Du, Yang (Katie) Zhao, Arijit Raychowdhury, Tushar Krishna, Vijay Janapa Reddi IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2025 Paper
	ReCA: Integrated Acceleration for Real-Time and Efficient Cooperative Embodied Autonomous Agents Zishen Wan, Yuhang Du, Mohamed Ibrahim, Jiayi Qian, Jason Jabbour, Yang (Katie) Zhao, Tushar Krishna, Arijit Raychowdhury, Vijay Janapa Reddi ACM Inter Conf on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025 Paper
	AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment Yonggan Fu, Jiayi Qian, Zhongzhi Yu, Junwei Li, Yongan Zhang, Dachuan Shi, Xiangchi Yuan, Roman Yakunin, Yingyan (Celine) Lin The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS)*, 2024 Paper

Teaching Experience

Teaching Assistant — CSE 6140 Algorithms, Georgia Tech, Spring 2024. Instructor: Prof. Xiuwei Zhang.

Design and source code from jonbarron.