Hugo Touvron
Artificial Intelligence · 2019–2024
A researcher in the Science corpus: 17 papers; trusts 2,378 researchers and is trusted by 4,299 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 778 citations into it; #2,085 of 36,961 by trust here, #499 by citations
- Computer Vision and Pattern Recognition — 690 citations into it; #727 of 21,973 by trust here, #545 by citations
- Model Architectures — 244 citations into it; #389 of 2,288 by trust here, #347 by citations
- Representation & Self-Supervised Learning — 152 citations into it; #1,801 of 3,156 by trust here, #493 by citations
- Natural Language Processing — 146 citations into it
- Optimization & Training — 125 citations into it; #753 of 2,605 by trust here, #626 by citations
- Evaluation & Benchmarks — 123 citations into it
- Large Language Models — 115 citations into it
Whom Hugo Touvron trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ross B. Girshick
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Karen Simonyan
- Yann LeCun
- Christian Szegedy
Who trusts Hugo Touvron overall
- Weihao Yu
- Jianwei Yang
- Yongming Rao
- Chunyuan Li
- Qibin Hou
- Sachin Mehta
- Kai Han
- Meng-Hao Guo
- Quoc V. Le
- Matthieu Cord
Papers from Hugo Touvron's perspective
Ordered by how strongly the researchers Hugo Touvron 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Training data-efficient image transformers & distillation through attention (2020) — 9,450 citations
- Emerging Properties in Self-Supervised Vision Transformers (2021) — 9,706 citations
- LLaMA: Open and Efficient Foundation Language Models (2023) — 20,887 citations
- Going deeper with Image Transformers (2021) — 1,349 citations
- Fixing the train-test resolution discrepancy (2019) — 484 citations
- Llama 2: Open Foundation and Fine-Tuned Chat Models (2023) — 17,670 citations
- ConViT: improving vision transformers with soft convolutional inductive biases (2021) — 1,066 citations
- XCiT: Cross-Covariance Image Transformers (2021) — 669 citations
- LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference (2021) — 1,047 citations
- ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training (2021) — 901 citations
- DeiT III: Revenge of the ViT (2022) — 659 citations
- Are Large-scale Datasets Necessary for Self-Supervised Pre-training? (2021) — 170 citations
- ResNet strikes back: An improved training procedure in timm (2021) — 625 citations
- Fixing the train-test resolution discrepancy: FixEfficientNet (2020) — 113 citations
- Code Llama: Open Foundation Models for Code (2023) — 3,394 citations
- Grafit: Learning fine-grained image representations with coarse labels (2020) — 83 citations
- When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards (2024) — 153 citations