Welcome to my website! I’m a 5th-year PhD candidate in the School of Computer Science at Georgia Tech, focusing on efficient & automated machine learning and algorithm-hardware co-design. My research philosophy centers on simplicity (“less is more”) and specialization (“jack of all trades, master of none”), aiming to develop generative AI systems that are both efficient and effective.

My CV is available at here in case you are interested !


Education

  • 12/2022Present: PhD Student at Georgia Tech
  • 08/201912/2022: Master Degree at Rice University
  • 09/201506/2019: Bachelor Degree at Huazhong University of Science and Technology

Industry Experience

  • Upcoming
    • 05/202408/2024: Full-time Research Intern @ Adobe Research
  • Past
    • 05/202308/2023: Startup Launch @ CREATE-X and Venture Lab
    • 08/202212/2022: Part-time Research Intern @ Meta Reality Labs
    • 05/202208/2022: Full-time Research Intern @ Meta Reality Labs
    • 08/202104/2022: Part-time Research Intern @ Baidu Research (USA)
    • 05/202108/2021: Full-time Research Intern @ Baidu Research (USA)

Publication List

> Conference:

  • H. You*, H. Shi*, Y. Guo*, Y. Lin.
    ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer. In NeurIPS 2023 (Acceptance rate: 26%).
    [Paper] [Code] [Slide] [Poster] [Talk@NeurIPS]

  • H. You*, Y. Xiong*, X. Dai, B. Wu, P. Zhang, H. Fan, P. Vajda, Y. Lin.
    Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference. In CVPR 2023 (Acceptance rate: 25%).
    [Paper] [Code] [Project] [Slide] [Poster] [Talk@CVPR]

  • H. You, Z. Sun, H. Shi, Z. Yu, Y. Zhao, Y. Zhang, C. Li, B. Li, Y. Lin.
    ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design. In HPCA 2023 (Acceptance rate: 25%).
    Selected as the Meta Faculty Research Award of 2022 !
    [Paper] [Code] [Project] [Slide] [Poster] [Talk@GT] [Talk@HPCA]

  • H. You, B. Li, Z. Sun, X. Ouyang, Y. Lin.
    SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning. In ECCV 2022 (Acceptance rate: 20%).
    [Paper] [Code] [Slide] [Poster] [Talk@ECCV]

  • H. You, B. Li, H. Shi, Y. Fu, Y. Lin.
    ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks. In ICML 2022 (Acceptance rate: 20%).
    [Paper] [Code] [Project] [Slide] [Talk@ICML]

  • H. You*, C. Wan*, Y. Zhao*, Z. Yu*, Y. Fu, J. Yuan, S. Wu, S. Zhang, Y. Zhang, C. Li, V. Boominathan, A. Veeraraghavan, Z. Li, Y. Lin.
    EyeCoD: Eye Tracking System Acceleration via FlatCam-Based Algorithm and Accelerator Co-Design. In ISCA 2022 (Acceptance rate: 17%).
    Selected as the IEEE Micro’s Top Pick of 2023 !
    [Paper] [Code] [Project] [Slide] [Poster@ISCA] [Poster@CoCoSys] [Talk@ISCA] [IEEE Micro’s TopPick’23]

  • H. You, T. Geng, Y. Zhang, A. Li, Y. Lin.
    GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design. In HPCA 2022 (Acceptance rate: 30%).
    [Paper] [Code] [Slide] [Talk@HPCA]

  • H. You, Z. Lu, Z. Zhou, Y. Fu, Y. Lin
    Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference. In AAAI 2022 (Acceptance rate: 15%).
    [Paper] [Code] [Slide] [Poster] [Talk@AAAI]

  • H. You, X. Cheng, Y. Zhang, S. Liu, Z. Liu, Z. Wang, Y. Lin.
    ShiftAddNet: A Hardware-Inspired Deep Network. In NeurIPS 2020 (Acceptance rate: 20%).
    [Paper] [Code] [Slide] [Poster] [Talk@NeurIPS] [Talk@RICE]

  • H. You, C. Li, P. Xu, Y. Fu, Y. Wang, X. Chen, R.G. Baraniuk, Z. Wang, Y. Lin.
    Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks. In ICLR 2020 Spotlight (Acceptance rate: 4%).
    Selected as an ICLR Spotlight !
    [Paper] [Code] [Slide] [OpenReview] [Talk@ICLR]

  • Y. Fu, H. You, Y. Zhao, Y. Wang, C. Li, K. Gopalakrishnan, Z. Wang, Y. Lin.
    FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training. In NeurIPS 2020 (Acceptance rate: 20%).
    [Paper]

  • Y. Zhang, H. You, Y. Fu, T. Geng, A. Li, Y. Lin.
    G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency. In ICCAD 2021 (Acceptance rate: 23%).
    [Paper]

  • H. Shi, H. You, Y. Zhao, Z. Wang, Y. Lin.
    NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks. In ICCAD 2022 (Acceptance rate: 24%).
    [Paper]

  • Y. Zhao, Z. Li, H. You, Y. Fu, Y. Zhang, C. Li, C. Wan, S. Wu, X. Ouyang, V. Boominathan, A. Veeraraghavan, Y. Lin
    i-FlatCam: A 253 FPS, 91.49 µJ/Frame Ultra-Compact Intelligent Lensless Camera System for Real-Time and Efficient Eye Tracking in VR/AR. In VLSI 2022.
    Won the first place in University Best Demonstration at DAC 2022 !
    [Paper] [Demo]

  • C. Li, T. Chen, H. You, Z. Wang, Y. Lin.
    HALO: Hardware-Aware Learning to Optimize. In ECCV 2020 (Acceptance rate: 27%).
    [Paper]

  • Y. Zhao, X. Chen, Y. Wang, C. Li, H. You, Y. Fu, Y. Xie, Z. Wang, Y. Lin.
    SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation. In ISCA 2020 (Acceptance rate: 18%).
    [Paper]

  • T. Geng, C. Wu, Y. Zhang, C. Tan, C. Xie, H. You, M. Herbordt, Y. Lin, A. Li
    I-GCN: A GCN Accelerator with Runtime Locality Enhancement through Islandization. In MICRO 2021 (Acceptance rate: 22%).
    [Paper]

  • C. Li, Z. Yu, Y. Fu, Y. Zhang, Y. Zhao, H. You, Q. Yu, Y. Wang, C. Hao, Y. Lin.
    HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark. In ICLR 2021 Spotlight (Acceptance rate: 4%).
    [Paper]

  • Y. Fu, Z. Ye, J. Yuan, S. Zhang, S. Li, H. You, Y. Lin.
    Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design. In ISCA 2023 (Acceptance rate: 21%).
    [Paper]

  • S. Li, C. Li, W. Zhu, B. Yu, Y. Zhao, C. Wan, H. You, H. Shi, Y. Lin.
    Instant-3D: Instant Neural Radiance Fields Training Towards Real-Time AR/VR 3D Reconstruction. In ISCA 2023 (Acceptance rate: 21%).
    [Paper]

  • Z. Yu, Y. Fu, S. Wu, M. Li, H. You, Y. Lin.
    LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference. In TinyML 2022
    [Paper]

> Journal:

  • H. You, R. Balestriero, Z. Lu, Y. Kou, H. Shi, S. Zhang, S. Wu, Y. Lin, R. Baraniuk
    Max-Affine Spline Insights Into Deep Network Pruning. In TMLR.
    [Paper] [Code]

  • H. You, Y. Cheng, T. Cheng, C. Li, P. Zhou.
    Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling. In IEEE TNNLS.
    [Paper@IEEE] [Paper@arXiv] [Code]

  • H. Shi, H. You, Z. Wang, Y. Lin.
    NASA+: Neural Architecture Search and Acceleration for Multiplication-Reduced Hybrid Networks. In IEEE Transactions on Circuits and Systems I.
    [Paper@IEEE] [Code]

  • X. Chen, Y. Zhao, Y. Wang, P. Xu, H. You, C. Li, Y. Fu, Y. Lin, Z. Wang
    SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training. In IEEE TNNLS.
    [Paper] [Code]

  • Y. Zhang, Y. Fu, W. Jiang, C. Li, H. You, M. Li, V. Chandra, Y. Lin
    DIAN: differentiable accelerator-network co-search towards maximal DNN efficiency. In ISLPED 2021.
    [Paper]


Research Interests


Review Services

  • 2024
    • AAAI; ICLR; ICML; CVPR; ECCV
  • 2023
    • ICLR; CVPR; ICML; ICCV; NeurIPS; TPAMI
  • 2022
    • ICML; NeurIPS; ECCV; CVPR; AAAI; ICLR
  • 2021
    • ICML; NeurIPS; ICLR; MLSys; IEEE TNNLS
  • 2020
    • ICML; ICLR; CVPR