Faculty
Research Interest
If you are here to seek "TL;DR"...
- Question: what should I read, if I just want to
have a very quick glance at what ScopeX lab is currently focusing on?
- Answer: Prof. Gu has broad research interests spanning
from emerging hardware design for
efficient computing (photonics, post-CMOS electronics, quantum), hardware-algorithm
co-design, AI/ML
algorithms, and electronic-photonic design automation. We pick six papers that
represent our recent flavors. The list will change over time:
- [ONN Review, JLT 2024]
- [AI for Optical Simulation, NeurOLight,
NeurIPS 2022]
- [Photonic AI Accelerator, Lightening-Transformer, HPCA 2024]
- [Automated Photonic Circuit Design,
ADEPT, DAC
2022]
- [Circuit/Algorithm Co-Design for
Optical Neural Network, FFT-ONN, TCAD 2021]
- [Training Algorithm for ONN On-Chip
Deployment, L2ight, NeurIPS 2021]
Please check the Research tab for details of research in our lab.
Follow @ScopeX-ASU
Academic Activities and Services
Dr. Gu received his Ph.D. degrees, under the supervision of Prof. David Z. Pan and Prof. Ray T. Chen, in Electrical and
Computer Engineering from The University of Texas at
Austin, Austin, TX, USA, in 2023.
Dr. Gu has authored 60+ peer-reviewed international journal/conference papers in above area.
He has received Best Paper Award at ASP-DAC 2020, selected as one out of 6 Best
Paper Finalists
at DAC 2020, won First Place at the ACM/SIGDA Student Research Competition (SRC) held at
ICCAD
2020, received the Best Poster Award at NSF Workshop on Machine Learning Hardware 2020,
won
First Place at the ACM Student Research Competition Grand Finals 2021, received the Best
Paper
Award at IEEE TCAD 2021, won the Robert S. Hilbert Memorial Optical Design
Competition 2022, and won Margarida Jacome Dissertation Prize at UT Austin ECE (2023).
He served as technical reviewers for over 18+ international journals/conferences, such as IEEE
TCAD, TODAES, DAC, ICCAD, ISVLSI, GLVLSI, IEEE TNNLS, NeurIPS, CVPR, ICCV, ECCV, AAAI, IROS,
Nature Communications, Science Advances, IEEE JSTQE, APL, IEEE PTL, etc. He also served as the
Technical
Program Committee member of DAC, ICCAD, ICCD, etc.
News
[Nov 2024]
- Our recent work, BOSON−1: Understanding and Enabling Physically-Robust Photonic Inverse Design with Adaptive Variation-Aware Subspace Optimization,
is accepted by IEEE DATE 2025. Cheers!
[BOSON InvDes, DATE 2025]
- Our recent work, qGDP: Quantum Legalization and Detailed Placement for Superconducting Quantum Computers,
is accepted by IEEE DATE 2025. Cheers!
[qGDP, DATE 2025]
- Our recent work, APR: Automated Photonic Integrated Circuit Detailed Routing with Curvy Waveguide and Adaptive Crossing Insertion,
is accepted by ACM ISPD 2025. Cheers!
[PIC Routing, ISPD 2025]
[Sep 2024]
- Our recent work, Selecting robust silicon photonic designs after Bayesian optimization without extra simulations,
is accepted by Optics Express 2024 (Editor's Pick). Cheers!
[Robust Bayesian Photonics, OE 2024]
[Aug 2024]
- Our recent work, The Unlikely Hero: Nonidealities in Analog Photonic Neural Networks as Built-in Adversarial Defenders,
is accepted by ACM/IEEE ASPDAC 2025. Cheers!
[ONN-Defense, ASPDAC 2025]
- Our recent work, ADEPT-Z: Zero-Shot Automated Circuit Topology Search for Pareto-Optimal Photonic Tensor Cores,
is accepted by ACM/IEEE ASPDAC 2025. Cheers!
[ADEPT-Z, ASPDAC 2025]
[Jul 2024]
- Our recent work, Photonic-Electronic Integrated Circuits for
High-Performance Computing and AI Accelerator,
is accepted by IEEE JLT 2024. Cheers!
[ONN-Review, JLT 2024]
[Jun 2024]
- Our recent work, SCATTER: Algorithm-Circuit Co-Sparse Photonic Accelerator with
Thermal-Tolerant, Power-Efficient In-situ Light Redistribution,
is accepted by ACM/IEEE ICCAD 2024. Cheers!
[SCATTER, ICCAD 2024]
- Our recent work, DOCTOR: Dynamic On-Chip Temporal Variation Remediation Toward Self-Corrected Photonic Tensor Accelerators,
is accepted by IEEE JLT 2024. Cheers!
[DOCTOR, JLT 2024]
- Our recent work, TeMPO: Efficient Time-Multiplexed Dynamic Photonic
Tensor Core for Edge AI with Compact Slow-Light Electro-Optic Modulator,
is accepted by JAP 2024. Cheers!
[TeMPO, JAP 2024]
[Mar 2024]
- Our recent work, FPQA-C: A Compilation Framework for Field Programmable Qubit Array,
is accepted by ISCA 2024. Cheers!
[FPQA-C, ISCA 2024]
[Feb 2024]
- Our recent work, Foundry Manufactured 6-bit Resolution, 150um Long SlowLight Electro-Optic
Modulator for On-Chip Photonic Tensor Computing,
is accepted by CLEO 2024. Cheers!
[SL-MZM, CLEO 2024]
- Our recent work, Realization of a Compact Photoelectric Platform for Optical Convolution Processing,
is accepted by CLEO 2024. Cheers!
[Optical CNN, CLEO 2024]
- Our recent work, Deep Learning Enhanced Early Detection of Pancreatic Cancer Using Integrated
Photonic Chip Based Optical Neural Networks,
is accepted by CLEO 2024. Cheers!
[OSNN for Cancer, CLEO 2024]
- Our recent work, Q-Pilot: Field Programmable Quantum Array Compilation with Flying Ancillas,
is accepted by DAC 2024. Cheers!
[Q-Pilot, DAC 2024]
[Jan 2024]
- Our recent work, M3ICRO: Machine Learning-Enabled Compact Photonic Tensor Core based on PRogrammable Multi-Operand Multimode Interference,
is accepted by APL Machine Learning 2024. Cheers!
[MO-MMI, APL ML 2024]
- Our recent work, A Hardware-Efficient Silicon Electronic-Photonic Chip for Optical Structured Neural Networks,
is accepted by SPIE Photonics West 2024. Cheers!
[OSNN, PW 2024]
[Dec 2023]
- Our recent work, Integrated Multi-Operand Optical Neurons for Scalable and Hardware-Efficient Deep Learning,
is accepted by Nanophotonics 2023. Cheers!
[MO-MZI, Nanophotonics 2023]
[Oct 2023]
- Our recent work, Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accelerator,
is accepted by HPCA 2024. Cheers!
[DOTA, HPCA 2024]
[Sep 2023]
- Our recent work, Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers,
is accepted by NeurIPS 2023 and selected as Spotlight paper. Cheers!
[PRE-RMSNorm, NeurIPS 2023]
- Our recent work, Domain-Specific Optimization for Quantized Optical AI Computing Systems,
is accepted by ICCV LBQNN workshop 2023. Cheers!