论文列表

The NLP Task Effectiveness of Long-Range Transformers

[J]. arXiv preprint arXiv:2202.07856, 2022

EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation

[J]. arXiv preprint arXiv:2202.07959, 2022

Testing the Tools of Systems Neuroscience on Artificial Neural Networks

[J]. arXiv preprint arXiv:2202.07035, 2022

Tidy Data

[J]. Stat. Soft. 2014, 59, 1-23.

A Few Useful Things to Know about Machine Learning

[J]. Communications of the ACM, 2012, 55(10): 78-87.

Statistical Modeling: The Two Cultures

[J]. Statistical science, 2001, 16(3): 199-231.

ImageNet Classification with Deep Convolutional Neural Networks

  • 2 年前
  • 0

[J]. Advances in neural information processing systems, 2012, 25.

Manifold mixup: learning better representations by interpolating hidden states

[J]. stat, 2018, 1050: 4.

Kharitonov E, Copet J, Lakhotia K, et al. textless-lib: a Library for Textless Spoken Language Processing[J]. arXiv preprint arXiv:2202.07359, 2022.

[J]. arXiv preprint arXiv:2202.08341, 2022.

textless-lib: a Library for Textless Spoken Language Processing

[J]. arXiv preprint arXiv:2202.07359, 2022.

How Do Vision Transformers Work?

[J]. arXiv preprint arXiv:2202.06709, 2022.

Revisiting Few-sample BERT Fine-tuning

[J]. arXiv preprint arXiv:2006.05987, 2020.