Po-Sen Huang
Artificial Intelligence · 2012–2022
A researcher in the Science corpus: 26 papers; trusts 1,360 researchers and is trusted by 555 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 890 citations into it; #1,472 of 36,961 by trust here, #668 by citations
- Natural Language Processing — 457 citations into it; #1,453 of 5,725 by trust here, #596 by citations
- Safety, Robustness & Interpretability — 327 citations into it; #1,342 of 2,259 by trust here, #197 by citations
- Computer Vision and Pattern Recognition — 274 citations into it; #3,352 of 21,973 by trust here, #1,980 by citations
- Information Systems — 106 citations into it
- Evaluation & Benchmarks — 92 citations into it
- Model Architectures — 73 citations into it
- Signal Processing — 68 citations into it; #829 of 7,592 by trust here, #825 by citations
Whom Po-Sen Huang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Diederik P. Kingma
- Ilya Sutskever
- Alex Graves
- Yann LeCun
- Kaiming He
- Sepp Hochreiter
- Ronald J. Williams
Who trusts Po-Sen Huang overall
- Jianfeng Gao
- Li Deng
- Xiaodong He
- Xu Tan
- Ruohan Gao
- Dong Yu
- Aditya Arie Nugraha
- John Wieting
- Zhe Gan
- Bhaskar Mitra
Papers from Po-Sen Huang's perspective
Ordered by how strongly the researchers Po-Sen Huang 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
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- 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
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher (2021) — 1,640 citations
- Ethical and social risks of harm from Language Models (2021) — 1,580 citations
- Learning deep structured semantic models for web search using clickthrough data (2013) — 2,275 citations
- Competition-level code generation with AlphaCode (2022) — 2,356 citations
- Improving alignment of dialogue agents via targeted human judgements (2022) — 676 citations
- ReasoNet: Learning to Stop Reading in Machine Comprehension (2016) — 309 citations
- Challenges in Detoxifying Language Models (2021) — 248 citations
- Reducing Sentiment Bias in Language Models via Counterfactual Evaluation (2019) — 251 citations
- Taxonomy of Risks posed by Language Models (2022) — 1,066 citations
- Kernel methods match Deep Neural Networks on TIMIT (2014) — 131 citations
- Are Labels Required for Improving Adversarial Robustness? (2019) — 361 citations
- Natural Language to Structured Query Generation via Meta-Learning (2018) — 129 citations
- Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation (2019) — 184 citations
- Discourse-Aware Neural Rewards for Coherent Text Generation (2018) — 82 citations
- Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models (2022) — 69 citations
- Towards Robust Image Classification Using Sequential Attention Models (2019) — 72 citations
- Robust Text-to-SQL Generation with Execution-Guided Decoding (2018) — 120 citations
- Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations (2019) — 60 citations
- Unsupervised Learning of Predictors from Unpaired Input-Output Samples (2016) — 8 citations
- Predicting speech recognition confidence using deep learning with word identity and score features (2013) — 39 citations