Minjoon Seo
Artificial Intelligence · with Hajishirzi · 2014–2023
A researcher in the Science corpus: 23 papers; trusts 1,969 researchers and is trusted by 1,963 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 634 citations into it; #621 of 36,961 by trust here, #1,030 by citations
- Natural Language Processing — 392 citations into it; #161 of 5,725 by trust here, #292 by citations
- Computer Vision and Pattern Recognition — 320 citations into it; #2,943 of 21,973 by trust here, #1,735 by citations
- Information Retrieval & Search — 100 citations into it; #132 of 1,022 by trust here, #137 by citations
- Evaluation & Benchmarks — 97 citations into it; #2,249 of 3,155 by trust here, #1,712 by citations
- Large Language Models — 76 citations into it
- Model Architectures — 54 citations into it; #1,964 of 2,288 by trust here, #1,860 by citations
- Information Systems — 42 citations into it; #97 of 9,233 by trust here, #129 by citations
Whom Minjoon Seo trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Diederik P. Kingma
- Jason Aaron Edward Weston
- Alex Krizhevsky
- Ilya Sutskever
- Sepp Hochreiter
- Richard Socher
- Kaiming He
- Alex Graves
Who trusts Minjoon Seo overall
- Jinhyuk Lee
- Mohit Bansal
- Robin Jia
- Sewon Min
- Minghao Hu
- Hannaneh Hajishirzi
- Mrinmaya Sachan
- Richard Socher
- Caiming Xiong
- Luke S. Zettlemoyer
Papers from Minjoon Seo's perspective
Ordered by how strongly the researchers Minjoon Seo 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)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Bidirectional Attention Flow for Machine Comprehension (2016) — 2,143 citations
- Zero-Shot Relation Extraction via Reading Comprehension (2017) — 854 citations
- MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension (2019) — 335 citations
- Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (2019) — 165 citations
- REPLUG: Retrieval-Augmented Black-Box Language Models (2023) — 1,051 citations
- Question Answering through Transfer Learning from Large Fine-grained Supervision Data (2017) — 121 citations
- Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension (2017) — 387 citations
- A Diagram is Worth a Dozen Images (2016) — 1,022 citations
- Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension (2018) — 60 citations
- Neural Speed Reading via Skim-RNN (2017) — 81 citations
- A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization (2019) — 276 citations
- Diagram Understanding in Geometry Questions (2014) — 123 citations
- Towards Continual Knowledge Learning of Language Models (2021) — 210 citations
- Is Retriever Merely an Approximator of Reader? (2020) — 44 citations
- Solving Geometry Problems: Combining Text and Diagram Interpretation (2015) — 266 citations
- Knowledge Unlearning for Mitigating Privacy Risks in Language Models (2022) — 490 citations
- Contextualized Sparse Representation with Rectified N-Gram Attention for Open-Domain Question Answering (2019) — 53 citations
- TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models (2022) — 137 citations
- Contextualized Sparse Representations for Real-Time Open-Domain Question Answering (2019) — 31 citations
- Mixture Content Selection for Diverse Sequence Generation (2019) — 64 citations