I am a Ph.D. student in Electrical and Computer Engineering at the University of Arizona, advised by Prof. Huanrui Yang.
My research focuses on efficient and reliable AI, spanning model design, compression, and hardware-aware inference. I study how neural networks can be simplified while preserving their capabilities, how LLM agents can remain effective under perturbations and resource constraints, and how computation and communication shape inference performance on emerging hardware.
Before starting my Ph.D., I completed the EIT Digital dual-degree master’s program in Autonomous Systems at KTH Royal Institute of Technology and EURECOM. I received my bachelor’s degree in Automation from Xi’an Jiaotong University. I have also held internships at TetraMem, Synkrotron, and Siemens.
I am seeking research internship opportunities for Summer 2027, with interests in efficient deep learning, LLM agents, and ML systems. Feel free to contact me at yuxinr@arizona.edu.
Latest News
| 2026.10 | Presented Isobar, our simulation framework for large-scale analog compute-in-memory systems, at the University of Arizona’s Homecoming research showcase. |
|---|---|
| 2026.05 | Our preprint, “From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation,” is now available on arXiv. |
| 2026.05 | Our paper, “FAR: Function-preserving Attention Replacement for IMC-friendly Inference,” was accepted to GLSVLSI 2026. |
| 2025.11 | Passed my Ph.D. qualifying examination at the University of Arizona. |
| 2025.08 | Our paper, “FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference,” was accepted to Findings of EMNLP 2025. |
Selected Publications
- Under review
Scaling Up Analog CIM: A Simulation Framework for Topology-Aware Mapping2026Under review at DAC 2027
