Papers

I would have written a shorter letter, but I did not have the time.

—Blaise Pascal

• Controlling Directions Orthogonal to a Classifier
  Yilun Xu, Hao He, Tianxiao Shen, Tommi Jaakkola.
  In ICLR 2022 (Spotlight).
  [PDF],[Code]
• Learning Representations that Support Robust Transfer of Predictors
  Yilun Xu, Tommi Jaakkola.
  In preprint.
  [PDF],[Code]
• Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
  Dinghuai Zhang, Kartik Ahuja, Yilun Xu, Yisen Wang, Aaron Courville.
  In ICML 2021 (Long talk).
  [PDF],[Code]
• Anytime Sampling for Autoregressive Models via Ordered Autoencoding
  Yilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon.
  In ICLR 2021.
  [PDF],[Code]
• A Theory of Usable Information under Computational Constraints
  Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon.
  In ICLR 2020 (Oral).
  [PDF],[Code]
• TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
  Xinwei Sun*, Yilun Xu*, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang.
  In ECCV 2020 (Oral).
  [PDF],[Code]
• L_{DMI} : A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
  Yilun Xu*, Peng Cao*, Yuqing Kong, Yizhou Wang.
  In NeurIPS 2019.
  [PDF],[Code]
• Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
  Peng Cao*, Yilun Xu*, Yuqing Kong, Yizhou Wang.
  In ICLR 2019.
  [PDF],[Code]