Germán Kruszewski
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 16 papers; trusts 1,216 researchers and is trusted by 317 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 577 citations into it; #1,908 of 36,961 by trust here, #1,143 by citations
- Natural Language Processing — 338 citations into it; #624 of 5,725 by trust here, #674 by citations
- Computer Vision and Pattern Recognition — 144 citations into it; #4,503 of 21,973 by trust here, #2,241 by citations
- Large Language Models — 95 citations into it
- Reinforcement Learning — 78 citations into it
- Evaluation & Benchmarks — 70 citations into it
- Model Architectures — 70 citations into it; #2,040 of 2,288 by trust here, #2,225 by citations
- Representation & Self-Supervised Learning — 59 citations into it; #620 of 3,156 by trust here, #812 by citations
Whom Germán Kruszewski trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Tomas Mikolov
- Ilya Sutskever
- Diederik P. Kingma
- Alex Krizhevsky
- Richard Socher
- Ronald J. Williams
- Yann LeCun
- Kaiming He
Who trusts Germán Kruszewski overall
- Yonatan Belinkov
- John Wieting
- Tal Linzen
- Dieuwke Hupkes
- Nadir Durrani
- Samuel R. Bowman
- Douwe Kiela
- Alex Warstadt
- Tomasz Korbak
- Kevin Gimpel
Papers from Germán Kruszewski's perspective
Ordered by how strongly the researchers Germán Kruszewski 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
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- 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)
Their papers
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- The LAMBADA dataset: Word prediction requiring a broad discourse context (2016) — 1,160 citations
- What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties (2018) — 1,024 citations
- BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
- Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors (2014) — 1,522 citations
- Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model (2015) — 48 citations
- The emergence of number and syntax units in LSTM language models (2019) — 190 citations
- Convolutional Neural Network Language Models (2016) — 40 citations
- Aligning Language Models with Preferences through f-divergence Minimization (2023) — 126 citations
- On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting (2022) — 94 citations
- CommAI: Evaluating the first steps towards a useful general AI (2017) — 19 citations
- Controlling Conditional Language Models without Catastrophic Forgetting (2021) — 43 citations
- Memorize or generalize? Searching for a compositional RNN in a haystack (2018) — 82 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
- Energy-Based Models for Code Generation under Compilability Constraints (2021) — 14 citations
- Learning compositionally through attentive guidance (2018) — 31 citations