Dr. Qian Lou目前的研究主要通过设计新的算法,神经网络模型,计算机系统来改善深度学习在计算机视觉和自然语言处理方面的有效性,隐私性,安全性。
1. Deep Learning: Computer Vision, Natural Language Processing, Multi-modal model, On-device ML, Model Compression, Transformer, Hardware Acceleration.
2. Security & Privacy: Privacy-preserving Machine Learning, Fully Homomorphic Encryption, Multi-Party Computation, Zero-Knowledge Proof, Differential Privacy, Federated Learning, Trusted Execution Environment, Backdoor Attack and Defense.
3. Systems & Computer Architecture: Hardware-software Co-design, Efficient and Secure Systems, GPU/FPGA acceleration.
Dr. Lou’s research outcomes are published in top-tier conferences like NeurIPS, ICML, CVPR, ICLR, EMNLP, IJCAI, PACT, DAC, DATE, ICCAD, etc.