Hanxiao Liu
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 21 papers; trusts 2,452 researchers and is trusted by 3,682 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 827 citations into it; #1,211 of 36,961 by trust here, #1,241 by citations
- Computer Vision and Pattern Recognition — 609 citations into it; #864 of 21,973 by trust here, #950 by citations
- Model Architectures — 219 citations into it; #90 of 2,288 by trust here, #151 by citations
- Natural Language Processing — 145 citations into it; #670 of 5,725 by trust here, #592 by citations
- Optimization & Training — 131 citations into it
- Representation & Self-Supervised Learning — 129 citations into it
- Evaluation & Benchmarks — 93 citations into it; #721 of 3,155 by trust here, #545 by citations
- Large Language Models — 92 citations into it
Whom Hanxiao Liu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Quoc V. Le
- Yoshua Bengio
- Barret Zoph
- Diederik P. Kingma
- Karen Simonyan
- Ilya Sutskever
- Ross B. Girshick
Who trusts Hanxiao Liu overall
- Xuanyi Dong
- Martin Wistuba
- Jiahui Yu
- Quoc V. Le
- Quanming Yao
- Colin White
- Han Cai
- Hang Xu
- Ekin Dogus Cubuk
- Xiangxiang Chu
Papers from Hanxiao Liu's perspective
Ordered by how strongly the researchers Hanxiao Liu 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)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- DARTS: Differentiable Architecture Search (2018) — 5,020 citations
- RACE: Large-scale ReAding Comprehension Dataset From Examinations (2017) — 1,655 citations
- Hierarchical Representations for Efficient Architecture Search (2017) — 955 citations
- CoAtNet: Marrying Convolution and Attention for All Data Sizes (2021) — 1,668 citations
- Gated-Attention Readers for Text Comprehension (2016) — 435 citations
- Combined Scaling for Zero-shot Transfer Learning (2021) — 248 citations
- Primer: Searching for Efficient Transformers for Language Modeling (2021) — 224 citations
- Pay Attention to MLPs (2021) — 883 citations
- Larger language models do in-context learning differently (2023) — 488 citations
- BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models (2020) — 335 citations
- Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS (2020) — 131 citations
- Combined Scaling for Open-Vocabulary Image Classification (2022)
- Neural Predictor for Neural Architecture Search (2019) — 238 citations
- DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining (2023) — 393 citations
- Evolving Normalization-Activation Layers (2020) — 93 citations
- Transformer Quality in Linear Time (2022) — 357 citations
- Large Language Models as Optimizers (2023) — 977 citations
- Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks (2017) — 2,865 citations
- Rethinking Pre-training and Self-training (2020) — 743 citations
- Analogical Inference for Multi-relational Embeddings (2017) — 406 citations