Scholar
Wenda Chu
Google Scholar ID: 2QE98SEAAAAJ
PhD student, CMS, Caltech
Citations & Impact
Citations
171
H-index
6
i10-index
6
Publications
11
Co-authors
0
Publications
Resume
Academic Achievements
- Two papers accepted to NeurIPS 2025: 'Split Gibbs Discrete Diffusion Posterior Sampling' and 'Steering Generative Models with Experimental Data for Protein Fitness Optimization'
- Oral presentation at CVPR 2025: 'Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing' (DAPS)
- Spotlight presentation at ICLR 2025: 'InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems'
- Published in TMLR 2025: 'Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems'
- Published at CVPR 2024: 'PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees'
- Accepted to AAAI 2025: 'COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks'
- Published at CVPR 2023: 'Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling'
- Oral presentation at NeurIPS 2023 Federated Learning Workshop: 'FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data'
- Published at ICML 2022: 'TPC: Transformation-Specific Smoothing for Point Cloud Models'
Background
- Second-year PhD student in the Computing and Mathematical Sciences (CMS) department at Caltech
- Advised by Yisong Yue and Yang Song
- Research interests span both practical and theoretical aspects of machine learning
- Aims to make machine learning algorithms more robust, efficient, and powerful
- Recent work focuses on posterior sampling methods for diffusion models