Tianyu Ding, PhD   Senior Researcher Microsoft Redmond, Washington, USA Email: tianyuding [At] microsoft [Dot] com GitHub | Google Scholar | LinkedIn | Twitter | CV

Biography

I am a Senior Researcher in Applied Sciences Group at Microsoft, Redmond. I earned my PhD in Applied Mathematics and Statistics from Johns Hopkins University (JHU) in 2021, where I was advised by Dr. Daniel P. Robinson and Dr. René Vidal. Prior to my PhD, I received my Master's degrees in Computer Science and Financial Mathematics from JHU in 2020 and 2016, respectively. I began my academic journey with a Bachelor's degree in Mathematics from Sun Yat-sen University in 2014.

Throughout my career, I have focused on improving efficiency in machine learning and artificial intelligence, especially in areas like computer vision and generative models. I am constantly seeking new ways to push the boundaries of these fields and make contributions to the world of applied science.

I would appreciate Anyverse Anonymous Feedback from anyone on anything. Feel free to ping me!

Selected Publications

(* indicates equal contribution)

1. DREAM: Diffusion Rectification and Estimation-Adaptive Models
   Jinxin Zhou*, Tianyu Ding*, Tianyi Chen, Jiachen Jiang, Ilya Zharkov, Zhihui Zhu, and Luming Liang
   Computer Vision and Pattern Recognition (CVPR), 2024 AC rate = 23.6%
   pdf code arXiv project page
2. Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
   Wenxiao Deng, Wenbin Li, Tianyu Ding, Lei Wang, Hongguang Zhang, Kuihua Huang, Jing Huo, and Yang Gao
   Computer Vision and Pattern Recognition (CVPR), 2024 AC rate = 23.6%
   pdf code arXiv
3. InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
   Yanqi Bao, Tianyu Ding, Jing Huo, Wenbin Li, Yuxin Li, and Yang Gao
   International Conference on Learning Representations (ICLR), 2024 AC rate = 30.96%
   pdf code arXiv bibtex
4. Efficient Subgame Refinement for Extensive-form Games
   Zhenxing Ge, Zheng Xu, Tianyu Ding, Wenbin Li, and Yang Gao
   Neural Information Processing Systems (NeurIPS), 2023 AC rate = 26.1%
   pdf supplemental bibtex
5. Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs
   Yanqi Bao, Yuxin Li, Jing Huo, Tianyu Ding, Xinyue Liang, Wenbin Li, and Yang Gao
   ACM International Conference on Multimedia (ACMMM), 2023 AC rate = 29.3%
   pdf code arXiv bibtex
6. OTOv2: Automatic, Generic, User-Friendly
   Tianyi Chen, Luming Liang, Tianyu Ding, Zhihui Zhu, and Ilya Zharkov
   International Conference on Learning Representations (ICLR), 2023 AC rate = 31.79%
   pdf code arXiv bibtex
7. On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features Spotlight
   Jinxin Zhou*, Xiao Li*, Tianyu Ding, Chong You, Qing Qu, and Zhihui Zhu
   International Conference on Machine Learning (ICML), 2022 AC rate = 21.9%
   pdf code arXiv bibtex
8. RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution
   Zhicheng Geng*, Luming Liang*, Tianyu Ding, and Ilya Zharkov
   Computer Vision and Pattern Recognition (CVPR), 2022 AC rate = 25.3%
   pdf code arXiv supplemental bibtex
9. A Geometric Analysis of Neural Collapse with Unconstrained Features Spotlight, top 3%
   Zhihui Zhu*, Tianyu Ding*, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, and Qing Qu
   Neural Information Processing Systems (NeurIPS), 2021 AC rate = 25.7%
   pdf code arXiv supplemental bibtex
10. Only Train Once: A One-Shot Neural Network Training and Pruning Framework
    Tianyi Chen, Bo Ji, Tianyu Ding, Biyi Fang, Guanyi Wang, Zhihui Zhu, Luming Liang, Yixin Shi, Sheng Yi, Xiao Tu
    Neural Information Processing Systems (NeurIPS), 2021 AC rate = 25.7%
    pdf code arXiv supplemental bibtex
11. Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach
    Tianyu Ding, Zhihui Zhu, René Vidal, and Daniel P. Robinson
    International Conference on Machine Learning (ICML), 2021 AC rate = 21.5%
    pdf code poster slides bibtex
12. CDFI: Compression-Driven Network Design for Frame Interpolation
    Tianyu Ding*, Luming Liang*, Zhihui Zhu, and Ilya Zharkov
    Computer Vision and Pattern Recognition (CVPR), 2021 AC rate = 23.7%
    pdf code arXiv poster bibtex
13. Dual Principal Component Pursuit for Learning a Union of Hyperplanes: Theory and Algorithms
    Tianyu Ding, Zhihui Zhu, Manolis C. Tsakiris, René Vidal, and Daniel P. Robinson
    Artificial Intelligence and Statistics (AISTATS), 2021 AC rate = 29.8%
    pdf code poster slides bibtex
14. Orthant Based Proximal Stochastic Gradient Method for ℓ-1 Regularized Optimization
    Tianyi Chen, Tianyu Ding, Bo Ji, Guanyi Wang, Yixin Shi, Sheng Yi, Xiao Tu, and Zhihui Zhu
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2020 AC rate = 19%
    pdf code arXiv supplemental slides bibtex
15. A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning
    Zhihui Zhu, Tianyu Ding, Daniel P. Robinson, Manolis C. Tsakiris, and René Vidal
    Neural Information Processing Systems (NeurIPS), 2019 AC rate = 21.6%
    pdf code supplemental poster bibtex
16. Noisy Dual Principal Component Pursuit Oral
    Tianyu Ding*, Zhihui Zhu*, Tianjiao Ding, Yunchen Yang, René Vidal, Manolis C. Tsakiris, and Daniel P. Robinson
    International Conference on Machine Learning (ICML), 2019 AC rate = 22.6%
    pdf code poster slides bibtex

Preprints

1. AdaContour: Adaptive Contour Descriptor with Hierarchical Representation
   Tianyu Ding, Jinxin Zhou, Tianyi Chen, Zhihui Zhu, Ilya Zharkov, and Luming Liang
   arXiv:2404.08292, 2024
   
2. S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing
   Guangzhi Wang, Tianyi Chen, Kamran Ghasedi, HsiangTao Wu, Tianyu Ding, Chris Nuesmeyer, Ilya Zharkov, Mohan Kankanhalli, and Luming Liang
   arXiv:2404.08111, 2024
   
3. ONNXPruner: ONNX-Based General Model Pruning Adapter
   Dongdong Ren, Wenbin Li, Tianyu Ding, Lei Wang, Qi Fan, Jing Huo, Hongbing Pan, and Yang Gao
   arXiv:2404.08016, 2024
   
4. OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators
   Tianyi Chen, Tianyu Ding, Zhihui Zhu, Zeyu Chen, HsiangTao Wu, Ilya Zharkov, and Luming Liang
   arXiv:2312.09411, 2023
   
5. The Efficiency Spectrum of Large Language Models: An Algorithmic Survey
   Tianyu Ding, Tianyi Chen, Haidong Zhu, Jiachen Jiang, Yiqi Zhong, Jinxin Zhou, Guangzhi Wang, Zhihui Zhu, Ilya Zharkov, and Luming Liang
   arXiv:2312.00678, 2023
   
6. CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering
   Haidong Zhu*, Tianyu Ding*, Tianyi Chen, Ilya Zharkov, Ram Nevatia, and Luming Liang
   arXiv:2311.15510, 2023
   project page
7. LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery
   Tianyi Chen, Tianyu Ding, Badal Yadav, Ilya Zharkov, and Luming Liang
   arXiv:2310.18356, 2023
   
8. Towards Automatic Neural Architecture Search within General Super-Networks
   Tianyi Chen, Luming Liang, Tianyu Ding, and Ilya Zharkov
   arXiv:2305.18030, 2023
   
9. Sparsity-guided Network Design for Frame Interpolation
   Tianyu Ding*, Luming Liang*, Zhihui Zhu, Tianyi Chen, and Ilya Zharkov
   arXiv:2209.04551, 2022
   
10. Neural Network Compression via Sparse Optimization
    Tianyi Chen*, Bo Ji*, Yixin Shi, Tianyu Ding, Biyi Fang, Sheng Yi, and Xiao Tu
    arXiv:2011.04868, 2020
    
11. Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem
    Tianyi Chen, Guanyi Wang, Tianyu Ding, Bo Ji, Sheng Yi, and Zhihui Zhu
    arXiv:2009.12078, 2020
    

Student Mentoring & Supervision

• Haidong Zhu (Microsoft Research Intern, Summer 2023)
  Area of Focus: Generalizable & Few-Shot NeRF
  Intern Project: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering
  project page
  
• Jinxin Zhou (Microsoft Research Intern, Summer 2023)
  Area of Focus: Efficient Training of Diffusion Models
  Intern Project: Diffusion Rectification and Estimation-Adaptive Models
  project page »»» The work has been accepted by CVPR 2024!
  

Teaching

• Teaching Fellow at Department of Applied Mathematics and Statistics, JHU (Spring 2021)
• Instructor for EN 553.282.13(14) A Hands-On Introduction to MATLAB (Intersession 2016, 2017, 2018 & 2019)
• Teaching Assistant for EN 553.665 Introduction to Convexity (Fall 2019)
  Teaching Assistant for EN 553.761 Nonlinear Optimization (Fall 2016 & Fall 2017)
  Teaching Assistant for EN 553.644 Introduction to Financial Derivatives (Fall 2017)
  Teaching Assistant for EN 553.645 Interest Rate and Credit Derivatives (Spring 2016 & Spring 2017)
  Teaching Assistant for EN 553.627 Stochastic Processes (Fall 2015 & Fall 2016)
  Teaching Assistant for EN 553.628 Stochastic Processes and Applications to Finance II (Spring 2016)
  

Services

• Reviewer for AISTATS 2021
  Reviewer for CVPR 2021, 2022, 2023, 2024
  Reviewer for ECCV 2022, 2024
  Reviewer for ECML-PKDD 2020
  Reviewer for ICCV 2021, 2023
  Reviewer for ICLR 2021, 2022, 2023, 2024
  Reviewer for ICML 2021, 2023, 2024
  Reviewer for NeurIPS 2020, 2021, 2022, 2023
  
• Reviewer for Computer Science Review
  Reviewer for Journal of Electronic Imaging (JEI)
  Reviewer for IEEE Transactions on Multimedia (TMM)
  Reviewer for IEEE Transactions on Image Processing (TIP)
  Reviewer for IEEE Transactions on Mobile Computing (TMC)
  Reviewer for Transactions on Machine Learning Research (TMLR)
  Reviewer for ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
  

© 2024 Tianyu Ding     (Last update: April 2024)