Mitchell Wortsman

Artificial Intelligence · 2018–2024

A researcher in the Science corpus: 17 papers; trusts 1,203 researchers and is trusted by 27 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 701 citations into it; #11,888 of 35,345 by trust here, #1,819 by citations
• Computer Vision and Pattern Recognition — 644 citations into it; #6,150 of 21,575 by trust here, #1,435 by citations
• Evaluation & Benchmarks — 170 citations into it
• Optimization & Training — 139 citations into it
• Representation & Self-Supervised Learning — 134 citations into it
• Multimodal Learning — 111 citations into it; #1,130 of 1,211 by trust here, #227 by citations
• Natural Language Processing — 106 citations into it
• Efficiency & Compression — 90 citations into it; #891 of 1,264 by trust here, #339 by citations

Whom Mitchell Wortsman trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Kaiming He
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Diederik P. Kingma
5. Yoshua Bengio
6. Yann LeCun
7. Ilya Sutskever
8. Ross B. Girshick
9. Jia Deng
10. Christian Szegedy

Who trusts Mitchell Wortsman overall

1. Gyuhak Kim
2. S. Gadre
3. Seyed Iman Mirzadeh
4. Michael Matena
5. Gabriel Ilharco
6. Zixuan Ke
7. Haeyong Kang
8. Prateek Yadav
9. B. Ermiş
10. Changnan Xiao

Papers from Mitchell Wortsman's perspective

Ordered by how strongly the researchers Mitchell Wortsman trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• LAION-5B: An open large-scale dataset for training next generation image-text models (2022) — 5,389 citations
• Reproducible Scaling Laws for Contrastive Language-Image Learning (2022) — 1,494 citations
• Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022) — 1,632 citations
• Robust fine-tuning of zero-shot models (2021) — 1,012 citations
• CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration (2022) — 118 citations
• Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning (2018) — 264 citations
• DataComp: In search of the next generation of multimodal datasets (2023) — 734 citations
• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models (2023) — 642 citations
• What’s Hidden in a Randomly Weighted Neural Network? (2019) — 414 citations
• Soft Threshold Weight Reparameterization for Learnable Sparsity (2020) — 274 citations
• Learning Neural Network Subspaces (2021) — 104 citations
• Editing Models with Task Arithmetic (2022) — 1,114 citations
• CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation (2022) — 324 citations
• OLMo: Accelerating the Science of Language Models (2024) — 700 citations
• Stable and low-precision training for large-scale vision-language models (2023) — 94 citations
• DataComp-LM: In search of the next generation of training sets for language models (2024) — 374 citations
• Supermasks in Superposition (2020) — 352 citations