Kaitao Song
Artificial Intelligence · 2018–2024
A researcher in the Science corpus: 10 papers; trusts 586 researchers and is trusted by 70 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 330 citations into it; #5,503 of 35,345 by trust here, #1,614 by citations
- Computer Vision and Pattern Recognition — 193 citations into it; #4,858 of 21,575 by trust here, #1,773 by citations
- Natural Language Processing — 111 citations into it; #5,258 of 5,688 by trust here, #2,660 by citations
- Speech & Audio — 78 citations into it
- Model Architectures — 73 citations into it; #1,501 of 2,278 by trust here, #398 by citations
- Large Language Models — 56 citations into it; #211 of 799 by trust here, #320 by citations
- Representation & Self-Supervised Learning — 24 citations into it
- Optimization & Training — 18 citations into it
Whom Kaitao Song trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Kaiming He
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Krizhevsky
- Ilya Sutskever
- Ross B. Girshick
- Quoc V. Le
- Yann LeCun
- Dzmitry Bahdanau
Who trusts Kaitao Song overall
- Xu Tan
- Myle Ott
- Xavier García
- Wenhui Wang
- Yinhan Liu
- Li Dong
- Furu Wei
- Maarten Grootendorst
- Lei Yu
- Tao Qin
Papers from Kaitao Song's perspective
Ordered by how strongly the researchers Kaitao Song 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)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (2021) — 5,140 citations
- MASS: Masked Sequence to Sequence Pre-training for Language Generation (2019) — 1,025 citations
- PVT v2: Improved baselines with Pyramid Vision Transformer (2021) — 2,512 citations
- HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face (2023) — 1,596 citations
- Double Path Networks for Sequence to Sequence Learning (2018) — 15 citations
- MPNet: Masked and Permuted Pre-training for Language Understanding (2020) — 1,779 citations
- NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models (2024) — 403 citations
- Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers (2024) — 334 citations
- PromptTTS 2: Describing and Generating Voices with Text Prompt (2023) — 87 citations
- Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech (2022) — 28 citations