Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
- Mini Research Symposium of CFCS and Turing Class, Peking University, 2021.12
Your Transformer May Not be as Powerful as You Expect
- International Joint Conference on Theoretical Computer Science, Peking University, 2022.08
Is $L^2$ Physics-Informed Loss Always Suitable for Training Physics-Informed Neural Network?
- Turing Student Research Forum, Peking University, 2022.06 [Vedio (in Chinese)]
- Machine Learning+X Seminar, Brown University, 2022.10 [Vedio]