Research

Huanru Henry Mao (2022) Fine-Tuning Pre-trained Transformers into Decaying Fast Weights. 2022 Conference on Empirical Methods in Natural Language Processing.

Huanru Henry Mao (2020) A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks. Arxiv.

Huanru Henry Mao, Shuyang Li, Julian McAuley, Garrison Cottrell (2020) Speech Recognition and Multi-Speaker Diarization of Long Conversations. INTERSPEECH 2020.

Thomas Bachlechner*, Bodhisattwa Prasad Majumder*, Huanru Henry Mao*, Garrison W. Cottrell, Julian McAuley (2020) ReZero is All You Need: Fast Convergence at Large Depth. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI 2021).
* Equal contribution

Huanru Henry Mao, Bodhisattwa Prasad Majumder, Julian McAuley, Garrison W. Cottrell (2019) Improving Neural Story Generation by Targeted Common Sense Grounding. In the 2019 Conference on Empirical Methods in Natural Language Processing.

Chris Donahue, Henry Mao, Ethan Yiting, Garrison W Cottrell, Julian McAuley (2019) LakhNES: Improving multi-instrumental music generation with cross-domain pre-training. In the 19th International Society for Music Information Retrieval Conference.

Chris Donahue, Henry Mao, Julian McAuley (2018) The NES Music Database: A symbolic music dataset with expressive performance attributes. InProceedings of the International Society for Music Information Retrieval Conference (ISMIR-19).

Huanru Henry Mao, Taylor Shin, and Garrison W. Cottrell (2018) DeepJ: Style-Specific Music Generation. In the12th IEEE International Conference on Semantic Computing.