Sebastian Ruder
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 44 papers; trusts 3,391 researchers and is trusted by 4,196 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 2,261 citations into it; #308 of 36,961 by trust here, #440 by citations
- Natural Language Processing — 1,108 citations into it; #105 of 5,725 by trust here, #196 by citations
- Computer Vision and Pattern Recognition — 765 citations into it; #2,826 of 21,973 by trust here, #1,016 by citations
- Representation & Self-Supervised Learning — 467 citations into it; #248 of 3,156 by trust here, #281 by citations
- Evaluation & Benchmarks — 332 citations into it; #1,562 of 3,155 by trust here, #504 by citations
- Large Language Models — 225 citations into it
- Model Architectures — 162 citations into it; #1,021 of 2,288 by trust here, #499 by citations
- Optimization & Training — 126 citations into it; #150 of 2,605 by trust here, #507 by citations
Whom Sebastian Ruder trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Diederik P. Kingma
- Kaiming He
- Tomas Mikolov
- Yann LeCun
- Ross B. Girshick
- Alex Graves
Who trusts Sebastian Ruder overall
- Jonas Pfeiffer
- Ivan Vulic
- Mohit Bansal
- Yi Tay
- Ramakanth Pasunuru
- Han Guo
- Ameya Dilip Jagtap
- Alan Ramponi
- Matthew E. Peters
- Colin Raffel
Papers from Sebastian Ruder's perspective
Ordered by how strongly the researchers Sebastian Ruder 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)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Universal Language Model Fine-tuning for Text Classification (2018) — 4,208 citations
- An Overview of Multi-Task Learning in Deep Neural Networks (2017) — 3,307 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization (2020) — 1,171 citations
- Long Range Arena: A Benchmark for Efficient Transformers (2020) — 917 citations
- To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks (2019) — 485 citations
- Language Models are Multilingual Chain-of-Thought Reasoners (2022) — 634 citations
- On the Cross-lingual Transferability of Monolingual Representations (2019) — 968 citations
- ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning (2021) — 240 citations
- Pitfalls of Static Language Modelling (2021) — 54 citations
- MAD-X: An Adapter-based Framework for Multi-task Cross-lingual Transfer (2020) — 754 citations
- Fine-tuned Language Models for Text Classification (2018) — 284 citations
- Latent Multi-Task Architecture Learning (2017) — 414 citations
- Charformer: Fast Character Transformers via Gradient-based Subword Tokenization (2021) — 213 citations
- Episodic Memory in Lifelong Language Learning (2019) — 341 citations
- XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation (2021) — 234 citations
- AdapterHub: A Framework for Adapting Transformers (2020) — 753 citations
- Transfer Learning in Natural Language Processing (2019) — 625 citations
- Mind the Gap: Assessing Temporal Generalization in Neural Language Models (2021) — 298 citations
- Rethinking embedding coupling in pre-trained language models (2020) — 187 citations