Scholar
Yufei Cui
Google Scholar ID: eiXIBZ0AAAAJ
McGill University, MILA
Citations & Impact
Citations
811
H-index
15
i10-index
19
Publications
20
Co-authors
9
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Paper 'The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks' accepted in ICML 2024.
- Paper 'Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion' accepted in ICLR 2024.
- Team HugeRabbit secured the 2nd place winner at 2023 ACM/IEEE TinyML Design Contest.
- Paper 'Retrieval-Augmented Multiple Instance Learning' accepted in NeurIPS 2023.
- Paper 'Faster and stronger Lossless Compression with Optimized Autoregressive framework' accepted in DAC 2023.
- Paper 'Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images' accepted in ICLR 2023.
- Paper 'Variational Nested Dropout' accepted in IEEE TPAMI.
- Paper 'Precise Augmentation and Counting of Helicobacter Pylori in Histology Image' accepted in MED-NEURIPS 2022.
- Paper 'Bits-Ensemble: Towards Light-Weight Robust Deep Ensemble by Bits-Sharing' accepted in CASES 2022 and TCAD.
- Paper 'Accelerating General-purpose Lossless Compression via Simple and Scalable Parameterization' accepted in ACM MM 2022.
- Preprint 'Variational Nested Dropout' available on arXiv and under review as a journal paper.
- Paper 'NFL: Robust Learned Index via Distribution Transformation' accepted in VLDB 2022.
- Paper 'A Fast Transformer-based General-Purpose Lossless Compressor' accepted in TheWebConf 2022.
- Paper 'CacheSifter: Sifting Cache Files for Boosted Mobile Performance and Lifetime' accepted in FAST 2022.
- Served as a reviewer for CVPR-22, NeurIPS-22, ICML-22.
- Paper 'Online Rare Category Identification and Data Diversification for Edge Computing' accepted in TCAD.
- Code for 'Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression' using proposed variational nested dropout released.
- Paper 'FlashEmbedding: Storing embedding tables in SSD for large-scale recommender systems' accepted in APSys 2021.
- Paper 'Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations' accepted in ICML Workshop on Adversarial Machine Learning.
Research Experience
- Currently a postdoc at McGill University and MILA, advised by Prof. Xue Liu. Also an advisor for the medical AI research lab at Bingli Tech, Guangzhou. Previously a postdoc at MLab, CityU HK (July 2021 to June 2022).
Education
- Ph.D. from City University of Hong Kong, supervised by Prof. Chun Jason Xue, Prof. Antoni B. Chan, and Prof. Tei-Wei Kuo; M.S. in Telecommunications from HKUST; B.E. in Communication Engineering from Shandong University.
Background
- Research interests include probabilistic deep learning with applications in medical images and histopathology, light-weight neural networks and embedded AI, data compression and learned index, retrieval-augmented language models.
