Publications

Author key underline: Students advised; *: communication authors; ^: co-first author.

2025

• SmoothE: Differentiable E-Graph Extraction
  Yaohui Cai, Kaixin Yang, Chenhui Deng, Cunxi Yu, Zhiru Zhang
  Architectural Support for Programming Languages and Operating Systems (ASPLOS'25)
  GitHub
  

• Digitized Phase Change Material Heterostack for Diffractive Optical Neural Network
  Ruiyang Chen, Cunxi Yu, Weilu Gao
  Advanced Photonics Research (2025)
  

• Optical Neural Engine for Solving Scientific Partial Differential Equations
  Yingheng Tang, Ruiyang Chen, Minhan Lou, Jichao Fan, Cunxi Yu, Andy Nonaka, Zhi Yao, Weilu Gao
  pre-print
  

2024

• MapTune: Advancing ASIC Technology Mapping via Reinforcement Learning Guided Library Tuning
  Mingju Liu, Daniel Robinson, Yingjie Li, Cunxi Yu
  IEEE/ACM International Conference On Computer Aided Design (ICCAD'24)
  GitHub
  
  

• Differentiable Combinatorial Scheduling at Scale
  Mingju Liu^, Yingjie Li^, Jiaqi Yin, Zhiru Zhang, Cunxi Yu
  International Conference on Machine Learning (ICML'24)
  
  GitHub

• Linear Algebra Approach to Verification of Modular (2^n−1) Multipliers
  Jiteshri Dasari, Cunxi Yu, Maciej Ciesielski
  2024 IFIP/IEEE 32nd International Conference on Very Large Scale Integration (VLSI-SoC)
  

• E-Syn: E-Graph Rewriting with Technology-Aware Cost Functions for Logic Synthesis
  Chen Chen, Guangyu Hu, Dongsheng Zuo, Cunxi Yu, Yuzhe Ma and Hongce Zhang
  Design Automation Conference (DAC'24) GitHub

• Less is More: Hop-wise Graph Attention for Scalable and Generalizable Learning on Circuits
  Chenhui Deng, Zichao Yue, Cunxi Yu, Gokce Sarar, Ryan Carey, Rajeev Jain and Zhiru Zhang
  Design Automation Conference (DAC'24) GitHub

• FPGA EDA: Design Principles and Implementation
  Kaihui Tu , Xifan Tang , Cunxi Yu, Lana Josipović , Zhufei Chu
  Springer (Book), 2024

• BoolGebra: Attributed Graph-learning for Boolean Algebraic Manipulation
  Yingjie Li, Anthony Agnesina, Yanqing Zhang, Mark Ren, Cunxi Yu
  IEEE Design, Automation and Test in Europe Conference (DATE'24)
  

• DAG-aware Synthesis Orchestration
  Yingjie Li, Mingju Liu, Alan Mishchenko, Mark Ren, Cunxi Yu
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)
  orchestrate@ABC

2023

• Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling
  Jiaqi Yin, Cunxi Yu
  ACM/IEEE International Conference on Computer-Aided Design (ICCAD'23)
  

• Verilog-to-PyG -- A Framework for Graph Learning and Augmentation on RTL Designs
  Yingjie Li, Mingju Liu, Alan Mishchenko, Cunxi Yu
  ACM/IEEE International Conference on Computer-Aided Design (ICCAD'23)
  Verilog-to-PyG

• AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP
  Zhuoping Yang, Jinming Zhuang, Jiaqi Yin, Cunxi Yu, Alex Jones and Peipei Zhou
  ACM/IEEE International Conference on Computer-Aided Design (ICCAD'23)
  GitHub

• LightRidge: An End-to-end Agile Design Framework for Diffractive Optical Neural Networks
  Yingjie Li, Ruiyang Chen, Minhan Lou, Berardi Sensale-Rodriguez, Weilu Gao, Cunxi Yu
  ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'24)
  LightRidge
  
  

• RubikONNs: Multi-task Learning with Rubik's Diffractive Optical Neural Networks
  Yingjie Li, Weilu Gao*, Cunxi Yu*
  32nd International Joint Conference on Artificial Intelligence (IJCAI'23) (15%)
  Github (LightRidge)

• Invited: Equality Saturation for Datapath Synthesis: A Pathway to Pareto Optimality
  Ecenur Ustun, Cunxi Yu, and Zhiru Zhang
  Design Automation Conference (DAC'23) (Invited Perspective Paper)

• RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs
  Jiaqi Yin, Yingjie Li, Daniel Robinson, Cunxi Yu
  Design Automation Conference (DAC'23) (23%)
  GitHub

• Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networks
  Nan Wu, Yingjie Li, Steve Dai, Cong (Callie) Hao, Cunxi Yu*, Yuan Xie
  Design Automation Conference (DAC'23) (23%) (Best Paper Award, 2/1157)
  GitHub
  Slides

• Physics-aware Roughness Optimization for Diffractive Optical Neural Networks
  Yingjie Li^, Shanglin Zhou^, Minhan Lou, Weilu Gao, Cunxi Yu, Caiwen Ding
  Design Automation Conference (DAC'23) (23%)
  Github: will be released with LightRidge

• Tutorial: A Journey to Optical Computing: From Physics Fundamentals to Hardware-Software Co-Design, Automation, and Application
  Jiaqi Gu, Chenghao Feng, Hanqing Zhu, Ray T. Chen, Ulf Schlichtmann, Zhengqi Gao, Duane Boning, Yingjie Li, Cunxi Yu
  Design Automation Conference (DAC'23)
  Slides

• Tutorial: Reinforcing Circuit and Layout Synthesis
  Shubham Rai, Cunxi Yu, Huigang Liao, Keren Zhu
  Design Automation Conference (DAC'23)
  

• Book chapter: Machine Learning for Agile FPGA Design
  Debjit Pal, Chenhui Deng, Ecenur Ustun, Cunxi Yu, Zhiru Zhang
  Springer (Book: Machine Learning Applications in Electronic Design Automation, Haoxing Ren, Jiang Hu.)

• Effects of Interlayer Reflection and Interpixel Interaction in Diffractive Optical Neural Networks
  Minhan Lou, Yingjie Li, Cunxi Yu, Berardi Sensale-Rodriguez, Weilu Gao*
  Optics Letter. Jan 2023.

2022

• Device-system Co-design of Photonic Neuromorphic Processor using Reinforcement Learning
  Yingheng Tang, Princess Tara Zamani, Ruiyang Chen, Jianzhu Ma, Minghao Qi, Cunxi Yu*, Weilu Gao*
  Laser & Photonics Reviews. Oct 2022. (IF:13.2)

• FlowTune: End-to-end Automatic Logic Optimization Exploration via Domain-specific Multi-armed Bandi
  Walter Lau Neto, Yingjie Li, Pierre-Emmanuel Gaillardon, Cunxi Yu
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD'22)
  GitHub

• Physics-aware Complex-valued Adversarial Machine Learning in Reconfigurable Diffractive All-optical Neural Network
  Ruiyang Chen^, Yingjie Li^, Minhan Lou, Jichao Fan, Yingheng Tang, Berardi Sensale-Rodriguez, Cunxi Yu*, Weilu Gao*
  Laser & Photonics Reviews. Vol 16, July 2022 (IF:13.2).
  

• Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks
  Yingjie Li, Ruiyang Chen, Weilu Gao and Cunxi Yu.
  IEEE/ACM International Conference On Computer Aided Design (ICCAD'22) (22%), Nov. 2022.
  

• Invited: Physics-aware Adversarial Machine Learning: An Experimental Study in Diffractive Optical Neural Networks
  Yingjie Li, Ruiyang Chen, Minhan Lou, Jichao Fan, Yingheng Tang, Berardi Sensale-Rodriguez, Weilu Gao, Cunxi Yu
  Invited talk at workshop 3rd ROAD4NN@Design Automation Conference (DAC '22).
  Talk@YouTube
  Pre-print
  

• LightRidge: An Open-source Compiler Framework for Diffractive Optical ML Architectures
  Yingjie Li, Ruiyang Chen, Minhan Lou, Berardi Sensale-Rodriguez, Weilu Gao and Cunxi Yu.
  First Workshop on Open-Source Computer Architecture Research (OSCAR) held in conjunction with ISCA (ISCA'49), June 2022.

• Exact Memory- and Communication-aware Scheduling of DNNs on Pipelined Edge TPUs
  Jiaqi Yin, Zhiru Zhang, and Cunxi Yu
  ACM/IEEE Symposium on Edge Computing (SEC'22) (17%). Seattle, WA, December 5-8, 2022

• IMpress: Large Integer Multiplication Expression Rewriting for FPGA HLS
  Ecenur Ustun, Ismail San, Jiaqi Yin, Cunxi Yu, and Zhiru Zhang
  Talk@YouTube
  International Symposium on Field-Programmable Custom Computing Machines (FCCM'22) (21%).

• Physics-informed Recurrent Neural Network for Time Dynamics in Optical Resonances
  Yingheng Tang, Jichao Fan, Xinwei Li, Jianzhu Ma, Minghao Qi, Cunxi Yu*, Weilu Gao*
  Nature Computational Science
  Github
  

• Combinatorial RL-based Scheduling for Pipelined Edge TPUs
  Jiaqi Yin, Yingjie Li, Cunxi Yu
  TinyML Research Symposium 2022 (TinyML'22)

• Physics-informed Neural Network for Forecasting Time-domain Signals in Terahertz Resonances.
  Tang, Yingheng, Jichao Fan, Xinwei Li, Jianzhu Ma, Minghao Qi, Cunxi Yu, and Weilu Gao.
  Conference on Lasers and Electro-Optics (CLEO'22).

• Complex-valued Reconfigurable Diffractive Optical Neural Networks using Cost-effective Spatial Light Modulators
  Ruiyang Chen, Yingjie Li, Minhan Lou, Cunxi Yu, Weilu Gao
  Conference on Lasers and Electro-Optics (CLEO'22).

  DLS Best Poster Honorable Mention, American Physics Society

2021

• Real-time Multi-Task Learning in Diffractive Deep Neural Networks via Hardware-Software Co-design
  extended version @ arXiv
  Yingjie Li, Ruiyang Chen, Berardi Sensale Rodriguez, Weilu Gao*, Cunxi Yu*
  Nature Scientific Reports (see demo video below)
  

• Physical Adversarial Attacks of Diffractive Deep Neural Networks
  Yingjie Li, Cunxi Yu
  IEEE/ACM 58th Design Automation Conference (DAC 2021).

• SLAP: A Supervised Learning Approach for Priority Cuts Technology Mapping
  [Github]
  Walter Lau Neto, Matheus Trevisan Moreira, Yingjie Li, Luca Amaru, Cunxi Yu, and Pierre-Emmanuel Gaillardon
  IEEE/ACM 58th Design Automation Conference (DAC 2021).

• Graphene Optoelectronic Artificial Intelligence Accelerators
  Weilu Gao*, Cunxi Yu, Ruiyang Chen
  Conference on Lasers and Electro-Optics (CLEO), Virtual Conference, May. 11-13, 2021.

• Artificial Intelligence Accelerators based on Graphene Optoelectronic Devices
  Weilu Gao, Cunxi Yu, Ruiyang Chen
  Advanced Photonics Research

• Read your Circuit: Leveraging Word Embedding to Guide Logic Optimization
  [Github]
  Walter Lau Neto, Matheus Trevisan Moreira, Luca Amaru, Cunxi Yu, and Pierre-Emmanuel Gaillardon
  IEEE/ACM 26th Asia and South Pacific Design Automation Conference (ASP-DAC 2021).

2020

• Decision Making in Synthesis cross Technologies using LSTMs and Transfer Learning [Github] [Talk]
  Cunxi Yu, Wang Zhou
  2nd ACM/IEEE Workshop on Machine Learning for CAD (MLCAD) 16-20 November, 2020.

• FlowTune: Practical Multi-armed Bandits in Boolean Optimization
  [Github] [Talk]
  Cunxi Yu
  IEEE/ACM International Conference On Computer Aided Design (ICCAD'20), Nov. 2020.

• EaSyOpt: Predicting Post Place and Route Critical Paths for Early Synthesis Optimization
  Walter Lau Neto*, Matheus Trevisan Moreira, Luca Amaru, Cunxi Yu, and Pierre-Emmanuel Gaillardon
  IWLS 2020. Virtual

2019

• Understanding Algebraic Rewriting for Arithmetic Circuit Verification: a Bit-Flow Model
  Github Maciej Ciesielski, Tiankai Su, Atif Yasin, Cunxi Yu
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)

• LAMDA: Learning-Assisted Multi-Stage Autotuning for FPGA Design Closure [Talk]
  Ecenur Ustun, Shaojie Xiang, Jinny Gui, Cunxi Yu, and Zhiru Zhang.
  IEEE Symp. on Field Programmable Custom Computing Machines (FCCM), 2019.

• Painting on Placement: Forecasting Routing Congestion using Conditional Generative Adversarial Nets [GIF Link] [Slides]
  Cunxi Yu, Zhiru Zhang
  ACM/IEEE Design Automation Conference (DAC'19)
  

• Spectral Approach to Verifying Non-linear Arithmetic Circuits [Algebraic Spectrum Gallery & Github]
  Cunxi Yu, Atif Yasin, Tiankai Su and Maciej Ciesielski
  ACM/IEEE Asia and South Pacific Design Automation Conference (ASP-DAC'19)

• Performance Estimation of Synthesis Flows cross Technologies using LSTMs and Transfer Learning
  Cunxi Yu, Wang Zhou
  arXiv preprint:1811.06017 [cs.LG]

• Algorithmic Obfuscation over GF($2^m$)
  Cunxi Yu, Daniel Holcomb
  arXiv preprint:1809.06207 [cs.CR]

2018

• Rewriting Environment for Arithmetic Circuit Verification [Github]
  Cunxi Yu, Atif Yasin, Tiankai Su, Alan Mishchenko and Maciej Ciesielski
  International Conference on Logic Programming and Automated Reasoning (LPAR-22) vol 57, pages 656--666.2019

• Developing Synthesis Flows without Human Knowledge [Datasets & Demo @Github] [Slides]
  Cunxi Yu, Houping Xiao and Giovanni De Micheli
  ACM/IEEE Design Automation Conference (DAC'18)

• End-to-End Industrial Study of Retiming
  Cunxi Yu, Chau-Chin Huang, Gi-Joon Nam, Mihir Choudhury, Victor N. Kravets, Andrew Sullivan, Maciej Ciesielski, Giovanni De Micheli
  2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI'18)

• Generating Safety Guidance for Medical Injection with Three-Compartment Pharmacokinetics Model
  Cunxi Yu, Heinz Riener, Francesca Stradolini, Giovanni De Micheli
  2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI'18)

• Formal Analysis of Galois Field Arithmetic - Parallel Verification and Reverse Engineering [Github] [Benchmarks] [arXiv]
  Cunxi Yu, Maciej Ciesielski
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. (TCAD'18) 10.1109/TCAD.2018.2808457

• Fast Algebraic Rewriting based on And-Inv-Graphs [Github]
  Cunxi Yu, Maciej Ciesielski and Alan Mishchenko
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. (TCAD'18) 10.1109/TCAD.2017.2772854

• Survey on applications of formal methods in reverse engineering and intellectual property protection
  Shahrzad Keshavarz, Cunxi Yu, Samaneh Ghandali, Xiaolin Xu, Daniel Holcomb
  2018 Journal of Hardware and Systems Security (HaSS'18)

• Computer Algebraic Approach to Verification and Debugging of Galois Field Multipliers
  Tiankai Su, Atif Yasin, Cunxi Yu, Maciej Ciesielski
  IEEE International Symposium on Circuits and System (ISCAS'18) IEEE, May 2018

2017

• Advanced Datapath Synthesis using Graph Isomorphism [Slides]
  Cunxi Yu, Mihir Choudhury, Andrew Sullivan and Maciej Ciesielski
  2017 International Conference On Computer Aided Design (ICCAD'17), Nov. 13 - 16, 2017, Irvine, CA, USA.

• Formal Verification of Truncated Multipliers using Algebraic Approach
  Tiankai Su, Cunxi Yu, Atif Yasin, and Maciej Ciesielski
  2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI'17), July 3-5, 2017, Bochum, Germany

• Advanced Logic synthesis of Datapaths using Graph Isomorphism
  Cunxi Yu, Mihir Choudhury, David Geiger, Andrew Sullivan and Maciej Ciesielski
  IWLS 2017, June 2016, Austin, USA.

• Reverse Engineering Irreducible Polynomial of GF(2^m) Arithmetic (Benchmarks)
  Cunxi Yu, Daniel Holcomb and Maciej Ciesielski
  IEEE/ACM/EDAA Design, Automation and Test in Europe (DATE'17), March 2017. Lausanne, Switzerland

• Efficient Parallel Verification of Galois Field Multipliers. (Best Paper Nomination) (Benchmarks)
  Cunxi Yu and Maciej Ciesielski
  IEEE/ACM 22nd Asia and South Pacific Design Automation Conference (ASP-DAC'17), Jan. 16-19, Chiba/Tokyo, Japan.

2016

• Formal Verification of Arithmetic Circuits by Function Extraction. [Tool] [Benchmarks](Best Paper Nomination)
  Cunxi Yu, Walter Brown, Duo Liu, Andre Rossi , Maciej Ciesielski.
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. (TCAD'16) 10.1109/TCAD.2016.2547898

• Incremental SAT-based Reverse Engineering of Camouflaged Logic Circuits. [Project Web] [Source code] [Benchmarks]
  Cunxi Yu, Xiangyu Zhang, Duo Liu, Maciej Ciesielski, Daniel Holcomb.
  IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. (TCAD'16)

• Formal Verification using Don’t-care and Vanishing Polynomials.
  Cunxi Yu and Maciej Ciesielski
  2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI'16) , July 2016, Pittsburgh, PA, USA

• Analyzing Imprecise Adders using BDDs - A Case Study.
  Cunxi Yu and Maciej Ciesielski
  2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI'16) , July 2016, Pittsburgh, PA, USA

• DAG-Aware Logic synthesis of Datapaths (Corrected version).
  Cunxi Yu, Mihir Choudhury, Andrew Sullivan and Maciej Ciesielski
  IEEE/ACM 53rd Design Automation Conference (DAC'16), June 2016, Austin, USA.

• Automatic Word-level Abstraction on Datapaths.
  Cunxi Yu and Maciej Ciesielski
  IEEE International Symposium on Circuits and System (ISCAS'16) IEEE, May 2016, Montreal, Canada.

• Oracle-Guided Incremental SAT Solving to Reverse Engineer Camouflaged Logic Circuits.
  Duo Liu, Cunxi Yu and Daniel Holcomb
  IEEE/ACM/EDAA Design, Automation and Test in Europe (DATE'16), March 2016, Dresden, Germany.

2015

• Logic Debugging of Arithmetic Circuits.
  Samaneh Ghandali, Cunxi Yu, Duo Liu, Maciej Ciesielski
  2015 IEEE Computer Society Annual Symposium on VLSI (ISVLSI'15) , July 2015, Montpellier, France.

• Verification of Arithmetic Datapath Designs using Word-level Approach.
  Cunxi Yu, Walter. Brown and Maciej. Ciesielski
  2015 IEEE International Symposium on Circuits and Systems (ISCAS). May 2015, Lisbon,Portugal.

• Verification of Gate-level Arithmetic Circuits by Function Extraction[Tools + Benchmarks] [Slides]
  Maciej Ciesielski, Cunxi Yu, Walter Brown, Duo Liu and Andre Rossi
  IEEE/ACM 52nd Design Automation Conference (DAC). June, 2015, San Francisco, CA, USA.

• Diagnosis and Debugging of Arithmetic Circuits
  Samaneh Ghandali, Cunxi Yu, Duo Liu, Maciej Ciesielski
  IEEE/ACM 52nd Design Automation Conference (DAC-WIP). June, 2015, San Francisco, CA, USA.

• Verification of Sequential Arithmetic Circuit.
  Cunxi Yu, Duo Liu, Walter Brown, Samaneh Ghandali, Maciej Ciesielski
  IEEE/ACM 52nd Design Automation Conference (DAC-WIP). June, 2015, San Francisco, CA, USA.