Scholar
Yangdi Lu
Google Scholar ID: LJ0x1FAAAAAJ
Phd, McMaster University
Citations & Impact
Citations
374
H-index
8
i10-index
6
Publications
20
Co-authors
2
list available
Contact
Resume (English only)
Academic Achievements
- [{'Paper': 'Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting', 'Conference': 'NeurIPS 2025', 'Type': 'spotlight (top ~3%)'}, {'Paper': 'Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstruction', 'Platform': 'arxiv.org', 'Year': '2024'}, {'Paper': 'VastGaussian: Vast Gaussian for Large Scene Reconstruction', 'Conference': 'CVPR 2024', 'Year': '2024'}, {'Paper': 'Rethinking Label Refurbishment: Model Robustness under Label Noise', 'Conference': 'AAAI 2023', 'Year': '2023'}, {'Paper': 'Robust Approaches for Learning with Noisy Labels', 'Type': 'Ph.D. Thesis', 'Year': '2022'}, {'Paper': 'Noise Attention Learning', 'Conference': 'NeurIPS 2022', 'Year': '2022'}, {'Paper': 'SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels', 'Conference': 'IJCAI 2022', 'Type': 'regular paper', 'Year': '2022'}, {'Paper': 'An Ensemble Model for Combating Label Noise', 'Conference': 'WSDM 2022', 'Type': 'regular paper', 'Year': '2021'}, {'Paper': 'Confidence Adaptive Regularization for Deep Learning with Noisy Labels', 'Platform': 'arxiv.org', 'Year': '2021'}, {'Paper': 'CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition', 'Platform': 'arxiv.org', 'Year': '2021'}]
Background
- Current research interests broadly include theory and applications of machine learning, such as trustworthy machine learning, 3D reconstruction and generation, approximate nearest neighbor search, image and video classification.
Miscellany
- Served as a reviewer for ICML 2022, NeurIPS 2022, AAAI 2023, AAAI 2024, and IEEE Transactions on Neural Networks and Learning Systems 2023.
