Harm de Vries
Artificial Intelligence · 2015–2024
A researcher in the Science corpus: 16 papers; trusts 1,020 researchers and is trusted by 2,260 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 399 citations into it; #1,603 of 36,961 by trust here, #1,010 by citations
- Computer Vision and Pattern Recognition — 241 citations into it; #1,154 of 21,973 by trust here, #1,306 by citations
- Natural Language Processing — 172 citations into it; #3,018 of 5,725 by trust here, #1,377 by citations
- Evaluation & Benchmarks — 72 citations into it
- Multimodal Learning — 59 citations into it; #138 of 1,215 by trust here, #136 by citations
- Model Architectures — 54 citations into it
- Optimization & Training — 35 citations into it; #791 of 2,605 by trust here, #1,156 by citations
- Reinforcement Learning — 33 citations into it
Whom Harm de Vries trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Sepp Hochreiter
- Yann LeCun
- Ronald J. Williams
- Jimmy Ba
Who trusts Harm de Vries overall
- Ethan Perez
- Chunyuan Li
- Takeru Miyato
- Dalu Guo
- Dacheng Tao
- Zhe Gan
- Tsendsuren Munkhdalai
- Yoshua Bengio
- Devi Parikh
- Qi Wu
Papers from Harm de Vries's perspective
Ordered by how strongly the researchers Harm de Vries 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- FiLM: Visual Reasoning with a General Conditioning Layer (2017) — 4,130 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Modulating early visual processing by language (2017) — 551 citations
- GuessWhat?! Visual Object Discovery through Multi-modal Dialogue (2016) — 444 citations
- Feature-wise transformations (2018) — 229 citations
- Learning Visual Reasoning Without Strong Priors (2017) — 65 citations
- End-to-end optimization of goal-driven and visually grounded dialogue systems (2017) — 141 citations
- Talk the Walk: Navigating New York City through Grounded Dialogue (2018) — 130 citations
- The Stack: 3 TB of permissively licensed source code (2022) — 482 citations
- Towards Ecologically Valid Research on Language User Interfaces (2020) — 61 citations
- RMSProp and equilibrated adaptive learning rates for non-convex optimization (2015) — 492 citations
- StarCoder: may the source be with you! (2023) — 1,263 citations
- SantaCoder: don't reach for the stars! (2023) — 247 citations
- Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation (2020) — 60 citations
- StarCoder 2 and The Stack v2: The Next Generation (2024) — 698 citations
- Equilibrated adaptive learning rates for non-convex optimization (2015)