Alexei Baevski
Artificial Intelligence · 2018–2024
A researcher in the Science corpus: 26 papers; trusts 2,083 researchers and is trusted by 2,949 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,025 citations into it; #438 of 36,961 by trust here, #581 by citations
- Natural Language Processing — 434 citations into it; #207 of 5,725 by trust here, #288 by citations
- Speech & Audio — 353 citations into it; #15 of 1,080 by trust here, #33 by citations
- Computer Vision and Pattern Recognition — 324 citations into it; #2,463 of 21,973 by trust here, #1,065 by citations
- Signal Processing — 313 citations into it; #193 of 7,592 by trust here, #203 by citations
- Representation & Self-Supervised Learning — 225 citations into it; #622 of 3,156 by trust here, #527 by citations
- Model Architectures — 114 citations into it; #1,378 of 2,288 by trust here, #675 by citations
- Evaluation & Benchmarks — 106 citations into it
Whom Alexei Baevski trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Ilya Sutskever
- Yoshua Bengio
- Alex Graves
- Alex Krizhevsky
- Kaiming He
- Myle Ott
- Jimmy Ba
- Oriol Vinyals
Who trusts Alexei Baevski overall
- Wei-Ning Hsu
- Abdel-rahman Mohamed
- Yu-An Chung
- Changhan Wang
- Michael Auli
- Alexis Conneau
- Qiantong Xu
- Yu Zhang
- Tatiana Likhomanenko
- Angela Fan
Papers from Alexei Baevski's perspective
Ordered by how strongly the researchers Alexei Baevski trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling (2019) — 3,399 citations
- Adaptive Input Representations for Neural Language Modeling (2018) — 440 citations
- Pay Less Attention with Lightweight and Dynamic Convolutions (2019) — 665 citations
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (2020) — 8,824 citations
- Cloze-driven Pretraining of Self-attention Networks (2019) — 210 citations
- Facebook FAIR’s WMT19 News Translation Task Submission (2019) — 424 citations
- data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language (2022) — 1,194 citations
- Pre-trained language model representations for language generation (2019) — 140 citations
- vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations (2019) — 744 citations
- The Llama 3 Herd of Models (2024) — 17,085 citations
- Self-Training and Pre-Training are Complementary for Speech Recognition (2020) — 180 citations
- Effectiveness of self-supervised pre-training for speech recognition (2019) — 158 citations
- Unsupervised Cross-lingual Representation Learning for Speech Recognition (2020) — 1,027 citations
- On Generative Spoken Language Modeling from Raw Audio (2021) — 483 citations
- Masked Autoencoders that Listen (2022) — 474 citations
- XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale (2021) — 1,102 citations
- Unsupervised Speech Recognition (2021) — 302 citations
- wav2vec: Unsupervised Pre-training for Speech Recognition (2019)
- Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training (2021) — 279 citations
- Large-Scale Self- and Semi-Supervised Learning for Speech Translation (2021) — 49 citations