MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design ICLAD 2026 Zesong Jiang, Yuqi Sun, Qing Zhong, Mahathi Krishna, Deepak Patil, Cheng Tan, Jeff Zhang Automates CGRA hardware/software co-design through four collaborative stages: design generation, error correction, best-design selection, and evaluation with feedback. Evaluation reports 25.9% lower power, 20.0% higher performance, and 5× faster design-space search, with final designs validated through a complete 7 nm ASIC flow. Paper

CAPO: Certification-Guided Agentic Workflow for Physical Design Parameter Optimization GLSVLSI 2026 Zesong Jiang, Qihang Wu, Bing-yue Wu, Jeff Zhang Formulates physical-design optimization as certified trajectory control, combining structured flow-state abstraction, bottleneck-aware planning, and transition certification to reject harmful actions and support recovery across coupled design stages. Paper

IICPilot: An Intelligent Integrated Circuit Backend Design Framework Using Open EDA Preprint 2024 Zesong Jiang, Qing Zhang, Cheng Liu, Long Cheng, Huawei Li, Xiaowei Li Automates backend-design script generation, EDA-tool execution, parameter exploration, container resource allocation, and exception handling through specialized agents and a unified interface for OpenROAD and iEDA. Paper

Break the Cold Barrier: An In-Depth Study on FPGA Performance and Design Optimization at Cryogenic Temperature Integrated Circuits and Systems 2024 Zesong Jiang, Muhan Zhang, Qingyun Liu, Runze Liu Characterizes FPGA behavior at cryogenic temperature and uses CryoFPGA-Pilot to explore a 500-point architecture space for low-delay and low-power designs. Paper

SigDLA: A Deep Learning Accelerator Extension for Signal Processing Preprint 2024 Fangfa Fu, Wenyu Zhang, Zesong Jiang, Zhiyu Zhu, Guoyu Li, Bing Yang, Cheng Liu, Liyi Xiao, Jinxiang Wang, Huawei Li, et al. Extends a conventional deep-learning accelerator with programmable data shuffling and a reconfigurable compute array, converting irregular signal-processing patterns into regular operations while preserving deep-learning support. Paper

A Low-Field Magnetic Resonance Signal Transmission and Reception Processing Platform ICICSP 2024 Zesong Jiang, Muhan Zhang, Qing Zhang, Yuchong Xie Implements low-field MRI transmission and reception on an FPGA: direct digital synthesis generates adjustable RF pulses, while digital downconversion and CIC/FIR filters recover baseband signals. Paper

A Biodegradable Piezoelectric Scaffold Promotes Spinal Cord Injury Nerve Regeneration Nano Energy 2024 Jinjing Zhang, Qiong Wang, Xiaoyi Tang, Mingyang Chai, Nuo Liu, Zesong Jiang, Xingjiang Li, Ping Chen Develops a biodegradable PLLA/KNN@PDA piezoelectric scaffold that provides structural guidance and sustained electrical stimulation, promoting neural growth and functional recovery in a rat spinal-cord injury model. Paper