Krzysztof Marcin Choromanski

Artificial Intelligence · 2015–2023

A researcher in the Science corpus: 23 papers; trusts 737 researchers and is trusted by 37 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 436 citations into it; #11,029 of 35,345 by trust here, #2,869 by citations
• Computer Vision and Pattern Recognition — 338 citations into it; #5,007 of 21,575 by trust here, #1,929 by citations
• Reinforcement Learning — 131 citations into it
• Model Architectures — 96 citations into it; #1,173 of 2,278 by trust here, #482 by citations
• Natural Language Processing — 79 citations into it
• Optimization & Training — 58 citations into it
• Representation & Self-Supervised Learning — 55 citations into it; #1,029 of 3,145 by trust here, #1,741 by citations
• Large Language Models — 50 citations into it

Whom Krzysztof Marcin Choromanski trusts overall

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

1. Geoffrey E. Hinton
2. Yoshua Bengio
3. Alex Krizhevsky
4. Ilya Sutskever
5. Diederik P. Kingma
6. Kaiming He
7. Yann LeCun
8. J. Urgen Schmidhuber
9. Sepp Hochreiter
10. Alex Graves

Who trusts Krzysztof Marcin Choromanski overall

1. Tri Dao
2. Valerii Likhosherstov
3. Han Lin
4. Yi Tay
5. Haoxian Chen
6. Mark Rowland
7. Beidi Chen
8. David Dohan
9. Adrian Weller
10. Xingyou Song

Papers from Krzysztof Marcin Choromanski's perspective

Ordered by how strongly the researchers Krzysztof Marcin Choromanski 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. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Rethinking Attention with Performers (2020) — 2,365 citations
• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language (2022) — 742 citations
• Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car (2017) — 437 citations
• Quantization based Fast Inner Product Search (2015) — 117 citations
• VisualBackProp: visualizing CNNs for autonomous driving (2016) — 78 citations
• Orthogonal Random Features (2016) — 247 citations
• The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings (2017) — 92 citations
• Optimizing Simulations with Noise-Tolerant Structured Exploration (2018) — 12 citations
• Ready Policy One: World Building Through Active Learning (2020) — 54 citations
• Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers (2020) — 96 citations
• Sub-Linear Memory: How to Make Performers SLiM (2020) — 25 citations
• Learning to Score Behaviors for Guided Policy Optimization (2019) — 46 citations
• Orthogonal Estimation of Wasserstein Distances (2019) — 53 citations
• Demystifying Orthogonal Monte Carlo and Beyond (2020) — 11 citations
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control (2023) — 3,674 citations
• Hybrid Random Features (2021) — 27 citations
• Effective Diversity in Population-Based Reinforcement Learning (2020) — 191 citations
• Unifying Orthogonal Monte Carlo Methods (2019) — 29 citations
• KAMA-NNs: Low-dimensional Rotation Based Neural Networks (2019) — 6 citations
• Initialization matters: Orthogonal Predictive State Recurrent Neural Networks (2018) — 22 citations