This blog includes some thoughts on recent fantastic works in machine learning, natural language processing and applied mathematics.
Purify Adversarial samples with diffusion models. Published at ICML 2022.
This paper studies the geometrical properties of the representations learned by neural networks. Published at NeurIPS 2019.
A paper on shortcut removal, published at AISTATS 2022.
A study on spurious correlations which is induced by a causal pespective of stress tests, published at NeurIPS 2021.
This is an inspiring work on ICLR 2020 about how to realize the potential of generative models on downstream discriminative problems.