Scholar
David W. Zhang
Google Scholar ID: MG3oLzUAAAAJ
Research Scientist, FAIR, Meta
Citations & Impact
Citations
329
H-index
9
i10-index
9
Publications
19
Co-authors
37
list available
Publications
Resume (English only)
Academic Achievements
- 1. Neural Networks Are Graphs! Graph Neural Networks for Equivariant Processing of Neural Networks, 2nd Annual Topology, Algebra, and Geometry in Machine Learning Workshop at ICML (TAG-ML), 2023;
- 2. Unlocking Slot Attention by Changing Optimal Transport Costs, International Conference on Machine Learning (ICML), 2023;
- 3. Self-Guided Diffusion Models, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023;
- 4. Robust Scheduling with GFlowNets, International Conference on Learning Representations (ICLR), 2023;
- 5. Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation, International Conference on Learning Representations (ICLR), 2022;
- 6. Pruning Edges and Gradients to Learn Hypergraphs from Larger Sets, Learning on Graphs (LoG), 2022;
- 7. Set Prediction without Imposing Structure as Conditional Density Estimation, International Conference on Learning Representations (ICLR), 2021.
Research Experience
- 1. Research Intern, Qualcomm AI Research, Jun 2022 – Sep 2022, Amsterdam, Netherlands, Researching machine learning methods for computation graph scheduling;
- 2. Consultant, KPMG, Jan 2018 – Mar 2019, Munich, Germany.
Education
- 1. PhD in Machine Learning, expected 2023, University of Amsterdam, Supervisors: Cees Snoek and Gertjan Burghouts;
- 2. MSc in Computer Science, 2017, Technical University of Munich;
- 3. BSc in Computer Science, 2015, Technical University of Munich.
Background
- AI/ML researcher at Qualcomm AI Research in Amsterdam. His research interests include structured prediction and generative models for structured data such as sets, graphs, or images.
