Nan Duan
Artificial Intelligence · 2013–2023
A researcher in the Science corpus: 52 papers; trusts 3,039 researchers and is trusted by 927 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,487 citations into it; #2,208 of 36,961 by trust here, #856 by citations
- Natural Language Processing — 903 citations into it; #1,675 of 5,725 by trust here, #387 by citations
- Computer Vision and Pattern Recognition — 844 citations into it; #1,983 of 21,973 by trust here, #1,015 by citations
- Evaluation & Benchmarks — 288 citations into it
- Large Language Models — 288 citations into it; #480 of 810 by trust here, #274 by citations
- Multimodal Learning — 254 citations into it; #161 of 1,215 by trust here, #160 by citations
- Information Systems — 250 citations into it; #4,211 of 9,233 by trust here, #156 by citations
- Model Architectures — 153 citations into it
Whom Nan Duan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Diederik P. Kingma
- Geoffrey E. Hinton
- Ilya Sutskever
- Kaiming He
- Alex Krizhevsky
- Yann LeCun
- Alex Graves
- Sepp Hochreiter
- Karen Simonyan
Who trusts Nan Duan overall
- Zhe Gan
- Linjie Li
- Shiyue Zhang
- Yen-Chun Chen
- Mohit Bansal
- Yanghoon Kim
- Pengchuan Zhang
- Xiaowei Hu
- Jianfeng Wang
- Jianfeng Gao
Papers from Nan Duan's perspective
Ordered by how strongly the researchers Nan Duan 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training (2019) — 975 citations
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages (2020) — 4,078 citations
- UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation (2020) — 412 citations
- NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion (2021) — 369 citations
- Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models (2023) — 869 citations
- CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval (2021) — 1,161 citations
- GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions (2021) — 317 citations
- Visual Question Generation as Dual Task of Visual Question Answering (2017) — 177 citations
- Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks (2019) — 242 citations
- K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (2020) — 629 citations
- AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models (2023) — 867 citations
- Dense Procedure Captioning in Narrated Instructional Videos (2019) — 59 citations
- GraphCodeBERT: Pre-training Code Representations with Data Flow (2020) — 1,778 citations
- Question Answering and Question Generation as Dual Tasks (2017) — 190 citations
- PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph (2019) — 110 citations
- Knowledge-Based Question Answering as Machine Translation (2014) — 136 citations
- Pretraining-Based Natural Language Generation for Text Summarization (2019) — 228 citations
- Question Generation for Question Answering (2017) — 295 citations
- XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation (2020) — 398 citations
- Reasoning Over Semantic-Level Graph for Fact Checking (2019) — 186 citations