William Chan
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 34 papers; trusts 2,663 researchers and is trusted by 2,748 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 884 citations into it; #678 of 36,961 by trust here, #639 by citations
- Computer Vision and Pattern Recognition — 647 citations into it; #1,383 of 21,973 by trust here, #589 by citations
- Natural Language Processing — 364 citations into it; #458 of 5,725 by trust here, #445 by citations
- Generative Models — 358 citations into it; #174 of 1,963 by trust here, #71 by citations
- Signal Processing — 319 citations into it; #52 of 7,592 by trust here, #44 by citations
- Speech & Audio — 244 citations into it; #103 of 1,080 by trust here, #82 by citations
- Model Architectures — 192 citations into it; #670 of 2,288 by trust here, #625 by citations
- Evaluation & Benchmarks — 88 citations into it; #2,836 of 3,155 by trust here, #2,101 by citations
Whom William Chan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Graves
- Geoffrey E. Hinton
- Dzmitry Bahdanau
- Yoshua Bengio
- Oriol Vinyals
- Diederik P. Kingma
- Ilya Sutskever
- Alex Krizhevsky
- Kyunghyun Cho
- Sepp Hochreiter
Who trusts William Chan overall
- Yu Zhang
- Chitwan Saharia
- Takaaki Hori
- Shinji Watanabe
- Changhan Wang
- Rohit Prabhavalkar
- Bo Li
- Jinyu Li
- Mohammad Norouzi
- Andros Tjandra
Papers from William Chan's perspective
Ordered by how strongly the researchers William Chan 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)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (2022) — 8,628 citations
- Listen, attend and spell: A neural network for large vocabulary conversational speech recognition (2015) — 2,461 citations
- Video Diffusion Models (2022) — 2,743 citations
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (2019) — 4,125 citations
- Palette: Image-to-Image Diffusion Models (2021) — 2,308 citations
- Cascaded Diffusion Models for High Fidelity Image Generation (2021) — 1,672 citations
- Image Super-Resolution via Iterative Refinement (2021) — 2,574 citations
- Imagen Video: High Definition Video Generation with Diffusion Models (2022) — 2,108 citations
- WaveGrad: Estimating Gradients for Waveform Generation (2020) — 957 citations
- Insertion Transformer: Flexible Sequence Generation via Insertion Operations (2019) — 283 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- KERMIT: Generative Insertion-Based Modeling for Sequences (2019) — 67 citations
- Very deep convolutional networks for end-to-end speech recognition (2016) — 420 citations
- Latent Sequence Decompositions (2016) — 62 citations
- Transferring knowledge from a RNN to a DNN (2015) — 77 citations
- Non-Autoregressive Machine Translation with Latent Alignments (2020) — 169 citations
- Imputer: Sequence Modelling via Imputation and Dynamic Programming (2020) — 130 citations
- Learning to Efficiently Sample from Diffusion Probabilistic Models (2021) — 163 citations
- Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality (2022) — 241 citations
- Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes (2018) — 140 citations