2025

• A3FR: Agile 3D Gaussian Splatting with Incremental Gaze Tracked Foveated Rendering in Virtual Reality

         Shuo Xin, Haiyu Wang, Sai Qian Zhang

         ACM International Conference on Supercomputing (ICS), 2025.

 

• Process Only Where You Look: Hardware and Algorithm Co-optimization for Efficient Gaze-Tracked Image Rendering in Virtual Reality

         Haiyu Wang, Wenxuan Liu, Kenneth Chen, Qi Sun, Sai Qian Zhang

         ACM/IEEE International Symposium on Computer Architecture (ISCA), 2025.

 

• PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers

         Maximilian Augusting, Syed Shakib Sarwar, Mostafa Elhoushi, Yuecheng Li, Sai Qian Zhang, Barbara De Salvo

         Conference on Computer Vision and Pattern Recognition Mobile AI workshop and challenges (CVPRW), 2025.

         

• Speculative Decoding and Beyond: An In-Depth Survey of Techniques

         Yunhai Hu*, Zining Liu*, Zhenyuan Dong*, Tianfan Peng*, Bradley McDanel, Sai Qian Zhang

         In Submission.

 

• Foveated Instance Segmentation

         Hongyi Zeng*, Wenxuan Liu*, Tianhua Xia, Jinhui Chen, Ziyun Li, Sai Qian Zhang

         Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

 

• PICACHU: Plug-In CGRA Handling Upcoming Nonlinear Operations in LLMs

         Jiajun Qin, Tianhua Xia, Cheng Tan, Jeff Jun Zhang, Sai Qian Zhang

         ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025.

 

• Hardware and Algorithm Codesign for Efficient Gaze Tracking in Virtual Reality System

         Haiyu Wang, Wenxuan Liu, Sai Qian Zhang

         IEEE International Symposium on Quality Electronic Design (ISQED), 2025.

 

• FrameVoting: A Robust and Fast Method of Using Gaze Estimations to Identify Objects of Interest
  KD Chang, HY Hsieh, HT Kung, Ziyun Li, Sai Qian Zhang
  IEEE International Symposium on Circuits and Systems (ISCAS), 2025.

 

• System and Algorithm Co-design for Efficient Image Rendering in AR/VR System         

         Sai Qian Zhang

         Electronic Imaging (EI), 2025.

 

• HAAN: A Holistic Approach for Accelerating Normalization Operations in Large Language Models         

         Tianfan Peng*, Tianhua Xia*, Jiajun Qin*,  Sai Qian Zhang

         IEEE Design, Automation and Test in Europe Conference (DATE), 2025.

 

• FovealNet: Advancing AI-Driven Gaze Tracking Solutions for Efficient Foveated Rendering in Virtual Reality         

         Wenxuan Liu, Budmonde Duinkharjav, Qi Sun, Sai Qian Zhang

         IEEE Virtual Reality conference (VR), 2025.

         IEEE Transactions on Visualization and Computer Graphics (IEEE TVCG).

 

• DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing         

         Zhenyuan Dong, Sai Qian Zhang

         IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025.

 

• Neural Architecture Search of Hybrid Models for NPU-CIM Heterogeneous AR/VR Devices         

         Yiwei Zhao, Xiaoyu Sun, Jinhui Chen, Sai Qian Zhang, Syed Shakib Sarwar, Kleber Hugo Stangherlin, Jorge Tomas Gomez, Jae-Sun Seo, Barbara           De Salvo, Chiao Liu, Phillip B.Gibbons, Ziyun Li

         30th Asia and South Pacific Design Automation Conference (ASP-DAC), 2025.

 

2024

• MRAM Design-Technology-System Co-Optimization for Artificial Intelligence Edge Devices

          Win-San Khwa, Yi-Lun Lu, Sai Qian Zhang, Xiaoyu Sun, Syed Shakib Sarwar, Ziyun Li, Wu-Wun Chen, Jui-Jen Wu, Xiaochen Peng, Kerem                            Akarvardar, Ming-Yuan Song, Hung-Li Chiang, Xinyu Bao, Yu-Jen Wang, Wen-Ting Chu, Harry Chuang, Yu-Der Chih, Tsung-Yung Jonathan Chang,            Barbara De Salvo, Chiao Liu, Meng-Fan Chang

          70th Annual IEEE International Electron Devices Meeting (IEDM), 2024

 

• A Task-Oriented Deep Learning Approach for Human Localization

          Yu-jia Chen,  Wei Chen, Sai Qian Zhang, Hai-Yan Huang, HT Kung

          IEEE Transactions on Cognitive and Developmental Systems, 2024.

 

• DLoRA: Distributed parameter-efficient fine-tuning solution for large language model

          Chao Gao, Sai Qian Zhang

          Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

 

• Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design

          Andre Nakkab, Sai Qian Zhang, Ramesh Karri, Siddharth Garg

          ACM/IEEE International Symposium on Machine Learning for CAD (MLCAD), 2024.

 

• Murmuration: On-the-fly DNN Adaptation for SLO-Aware Distributed Inference in Dynamic Edge Environments

          Jieyu Lin, Minghao Li, Sai Qian Zhang, Alberto Leon-Garcia

          International Symposium on Parallel Processing (ICPP), 2024.

 

• Estimating Power, Performance, and Area for On-Sensor Deployment of AR/VR Workloads

          Xiaoyu Sun, Xiaochen Peng, Sai Qian Zhang, Jorge Gomez, Win-San Khwa, Syed Shakib Sarwar, Ziyun Li, Weidong Cao, Zhao Wang, Chiao Liu,              Meng-Fan Chang, Barbara De Salvo, Kerem Akarvardar, H.-S. Philip Wong

          ACM Transactions on Design Automation of Electronic Systems.

 

• Parameter-efficient fine-tuning for large models: A comprehensive survey

  Zeyu Han, Chao Gao, Jinyang Liu, Jeff Zhang, Sai Qian Zhang

  Transactions on Machine Learning Research, 2024.

 

• Hyft: Softmax Acceleration with Adaptive Numeric Format for both Training and Inference

  Tianhua Xia, Sai Qian Zhang

          ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), 2024.

 

• Accelerating DNN Execution with Adaptive N:M Pruning on Both Weight and Data

         Sai Qian Zhang, Thierry Tambe, David Brooks, Gu-Yeon Wei

         ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), 2024.

 

• T3M: Text Guided 3D Human Motion Synthesis from Speech

         Wenshuo Peng, Kaipeng Zhang, Sai Qian Zhang

         Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024.

 

• sLLM: Accelerating LLM Inference using Semantic Load Balancing with Shared Memory Data Structures

         Jieyu Lin, Sai Qian Zhang, Alberto Leon-Garcia

         International Symposium on Quality Electronic Design (ISQED), 2024.

 

• Learning Client Selection Strategy for Federated Learning across Heterogeneous Mobile Devices

         Sai Qian Zhang, Jieyu Lin, Qi Zhang, Yu-jia Chen

         International Symposium on Quality Electronic Design (ISQED), 2024.

 

• Co-Designing AI Models and eDRAMs for Efficient On-Device Learning

         Sai Qian Zhang*, Thierry Tambe*, Nestor Cuevas, David Brooks, Gu-Yeon Wei

         IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2024.

2023

• HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization

  Wenxuan Liu, Sai Qian Zhang

  Under submission.

 

• BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling

          Yixuan Luo, Sai Qian Zhang

          Under submission.

2022

• Hyperspherical Federated Learning

         Xin Dong, Sai Qian Zhang, Ang Li, H.T. Kung

         European Conference on Computer Vision (ECCV), 2022.

 

• A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning

  Sai Qian Zhang, Jieyu Lin, Qi Zhang

  Thirty-sixth AAAI Conference on Artificial Intelligence (AAAI), 2022.

 

• FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding

         Sai Qian Zhang, Bradley McDanel, H.T. Kung

         IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2022

2021

• Training for Multi-resolution Inference Using Reusable Quantization Terms

         Sai Qian Zhang, Bradley McDanel, H.T. Kung, Xin Dong

         ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2021.

 

• Saturation RRAM Leveraging Bit-Level Sparsity Resulting from Term Quantization

  Bradley McDanel, H.T. Kung, Sai Qian Zhang

  IEEE International Symposium on Circuits and Systems (ISCAS), 2021.

2020

• Succinct and Robust Multi-Agent Communication With Temporal Message Control

         Sai Qian Zhang, Qi Zhang, Jieyu Lin

         Neural Information Processing System (NeurIPS), 2020.

 

• Term Quantization: Furthering Quantization at Run Time

  H.T. Kung*, Bradley McDanel*, Sai Qian Zhang*

          ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2020.

 

• Adaptive Distributed Convolutional Neural Network Inference at the Network Edge with ADCNN

         Sai Qian Zhang, Jieyu Lin, Qi Zhang

         International Conference on Parallel Processing (ICPP), 2020.

 

• RTN: Reparameterized Ternary Network

         Yuhang li, Xin Dong, Sai Qian Zhang, Haoli Bai, Yuanpeng chen, Wei Wang

         Thirty-forth AAAI Conference on Artificial Intelligence (AAAI), 2020.

 

• On the Robustness of Cooperative Multi-Agent Reinforcement Learning

         Jieyu Lin, Kristina Dzeparoska, Sai Qian Zhang, Alberto Leon-Garcia, Nicolas Papernot

         IEEE Symposium on Security and Privacy (S&P) Deep Learning and Security workshop, 2020.

2019

• Full-stack Optimization for Accelerating CNNs with FPGA Validation

         Sai Qian Zhang* , Bradley McDanel*, H.T. Kung, Xin Dong

         ACM International Conference on Supercomputing (ICS), 2019.

 

• Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control

  Sai Qian Zhang, Qi Zhang, Jieyu Lin

  Neural Information Processing System (NeurIPS), 2019.

 

• Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization

         H.T. Kung*, Bradley McDanel*, Sai Qian Zhang*

         ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2019.

 

• Maestro: A Memory-on-Logic Architecture for Coordinated Parallel Use of Many Systolic Arrays

         H.T. Kung*, Bradley McDanel*, Sai Qian Zhang*, Xin Dong, Chih Chiang Chen

         IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP), 2019.

 

• Systolic Building Block for Logic-on-Logic 3D-IC Implementations of Convolutional Neural Networks

         H.T. Kung*, Bradley McDanel*, Sai Qian Zhang*, et al

         IEEE International Symposium on Circuits and Systems (ISCAS), 2019.

2018

• A Machine Learning Assisted Cell Selection Method for Drones in Cellular Networks

         Sai Qian Zhang, Feng Xue, Nageen Himayat, Shilpa Talwar, H.T. Kung

          IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2018.

 

• Adaptive Tiling: Applying Fixed-size Systolic Arrays To Sparse Convolutional Neural Networks

  H.T. Kung, Bradley McDanel, Sai Qian Zhang

  24th International Conference on Pattern Recognition (ICPR), 2018.

 

• Mapping Systolic Arrays Onto 3D Circuit Structures: Accelerating Convolutional Neural Network Inference

         H.T. Kung*, Bradley McDanel*, Sai Qian Zhang*

         IEEE Workshop on Signal Processing Systems (SiPS), 2018.

2017-2015

• TCAM Space-effcient Routing on Software Defined Network

         Sai Qian Zhang, Qi Zhang, Ali Tizghadam, Byungchul Park, Hadi Bannazadeh, Alberto Leon-Garcia, Raouf Boutaba

         Computer Networks 125: 26-40, 2017.

 

• Sector: TCAM Space Aware Routing on SDN

         Sai Qian Zhang, Qi Zhang, Ali Tizghadam, Byungchul Park, Hadi Bannazadeh, Alberto Leon-Garcia, Raouf Boutaba

          International Teletraffic Congress (ITC), 2016.

 

• Joint NFV Placement and Routing for Multicast Service on SDN

         Sai Qian Zhang, Ali Tizghadam, Byungchul Park, Hadi Bannazadeh, Alberto Leon-Garcia

         IEEE/IFIP Network Operation and Management Symposium (NOMS), 2016.

 

• Aurora: Adaptive Block Replication in Distributed File Systems

         Qi Zhang, Sai Qian Zhang, Alberto Leon-Garcia, Raouf Boutaba

         IEEE International Conference on Distributed Computing Systems (ICDCS), 2015.

 

• Routing algorithms for network function virtualization enabled multicast topology on SDN

         Sai Qian Zhang, Qi Zhang, Hadi Bannazadeh, Alberto Leon-Garcia

         IEEE Transaction on Network and Service Management (TNSM): 580-594, 2015.

 

• Network Function Virtualization Enabled Multicast Routing on SDN

         Sai Qian Zhang, Qi Zhang, Hadi Bannazadeh, Alberto Leon-Garcia

         IEEE International Conference on Communication (ICC), 2015.

         (best paper award)

 

• Fast Network Flow Resumption for Live Virtual Machine Migration on SDN

         Sai Qian Zhang, Pouya Yasrebi, Ali Tizghadam, Hadi Bannazadeh, Alberto Leon-Garcia

         IEEE International Conference on Network Protocol (ICNP) workshop on Control, Operation and Application in SDN Protocol, 2015.

 

• Kaleidoscope: Real-Time Content Delivery in Software Defined Infrastructures

         Qi Zhang, Sai Qian Zhang, Jieyu Lin, Hadi Bannazadeh, Alberto Leon-Garcia

         IEEE International Symposium on Integrated Net-work Management (IM), 2015.