Veselin Stoyanov
Artificial Intelligence · 2009–2022
A researcher in the Science corpus: 20 papers; trusts 1,422 researchers and is trusted by 3,206 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 616 citations into it; #401 of 36,961 by trust here, #176 by citations
- Natural Language Processing — 414 citations into it; #128 of 5,725 by trust here, #42 by citations
- Computer Vision and Pattern Recognition — 204 citations into it; #7,074 of 21,973 by trust here, #1,961 by citations
- Evaluation & Benchmarks — 107 citations into it; #866 of 3,155 by trust here, #641 by citations
- Representation & Self-Supervised Learning — 101 citations into it; #1,198 of 3,156 by trust here, #332 by citations
- Large Language Models — 96 citations into it; #24 of 810 by trust here, #48 by citations
- Information Systems — 37 citations into it
- Optimization & Training — 32 citations into it
Whom Veselin Stoyanov trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Yann LeCun
- Ilya Sutskever
- N. Schraudolph
- Alex Krizhevsky
- Ronald J. Williams
- Tomas Mikolov
- Kaiming He
Who trusts Veselin Stoyanov overall
- Yoshua Bengio
- Mohit Bansal
- David Belanger
- Justin Domke
- Ian J. Goodfellow
- Yoon Kim
- Greg Durrett
- Vincent Ng
- Aaron C. Courville
- Matthew R. Gormley
Papers from Veselin Stoyanov's perspective
Ordered by how strongly the researchers Veselin Stoyanov 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
- 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)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019) — 30,530 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (2019) — 13,006 citations
- Unsupervised Cross-lingual Representation Learning at Scale (2019) — 8,807 citations
- XNLI: Evaluating Cross-lingual Sentence Representations (2018) — 1,635 citations
- Empirical Risk Minimization of Graphical Model Parameters Given Approximate Inference, Decoding, and Model Structure (2011) — 132 citations
- OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization (2022) — 307 citations
- Conundrums in Noun Phrase Coreference Resolution: Making Sense of the State-of-the-Art (2009) — 167 citations
- Emerging Cross-lingual Structure in Pretrained Language Models (2019) — 329 citations
- Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model (2019) — 216 citations
- SemEval-2015 Task 10: Sentiment Analysis in Twitter (2015) — 426 citations
- Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs (2021) — 92 citations
- Simple Fusion: Return of the Language Model (2018) — 78 citations
- Multi-Task Retrieval for Knowledge-Intensive Tasks (2021) — 69 citations
- SemEval-2013 Task 2: Sentiment Analysis in Twitter (2013) — 410 citations
- Minimum-Risk Training of Approximate CRF-Based NLP Systems (2012) — 32 citations
- General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference (2020) — 10 citations
- SemEval-2014 Task 9: Sentiment Analysis in Twitter (2014) — 587 citations
- Continual Few-Shot Learning for Text Classification (2021) — 14 citations
- Bridging the domain gap in cross-lingual document classification (2019) — 16 citations
- SemEval-2016 Task 4: Sentiment Analysis in Twitter (2016) — 341 citations