Stanislav Fort

Artificial Intelligence · 2018–2022

A researcher in the Science corpus: 16 papers; trusts 499 researchers and is trusted by 23 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 395 citations into it; #8,004 of 35,345 by trust here, #1,439 by citations
• Computer Vision and Pattern Recognition — 158 citations into it; #7,832 of 21,575 by trust here, #2,704 by citations
• Safety, Robustness & Interpretability — 136 citations into it
• Optimization & Training — 84 citations into it; #1,168 of 2,601 by trust here, #1,178 by citations
• Large Language Models — 75 citations into it
• Natural Language Processing — 65 citations into it
• Scaling & Learning Theory — 63 citations into it
• Evaluation & Benchmarks — 59 citations into it

Whom Stanislav Fort trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Kaiming He
4. Diederik P. Kingma
5. Yoshua Bengio
6. Yann LeCun
7. Christian Szegedy
8. Ilya Sutskever
9. Alex Graves
10. Ian J. Goodfellow

Who trusts Stanislav Fort overall

1. Stanislaw Jastrzebski
2. Surya Ganguli
3. Mitchell Wortsman
4. Yeming Wen
5. Pavel Izmailov
6. Justin N. M. Pinkney
7. Jingkang Yang
8. Seyed Iman Mirzadeh
9. Maciej Szymczak
10. Dustin Tran

Papers from Stanislav Fort's perspective

Ordered by how strongly the researchers Stanislav Fort 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

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022) — 4,254 citations
• Constitutional AI: Harmlessness from AI Feedback (2022) — 3,377 citations
• Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022) — 837 citations
• Predictability and Surprise in Large Generative Models (2022) — 365 citations
• Deep Ensembles: A Loss Landscape Perspective (2019) — 770 citations
• Language Models (Mostly) Know What They Know (2022) — 1,782 citations
• Stiffness: A New Perspective on Generalization in Neural Networks (2019) — 109 citations
• Exploring the Limits of Out-of-Distribution Detection (2021) — 428 citations
• The Goldilocks zone: Towards better understanding of neural network loss landscapes (2018) — 60 citations
• The Break-Even Point on Optimization Trajectories of Deep Neural Networks (2020) — 203 citations
• A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection (2021) — 310 citations
• Measuring Progress on Scalable Oversight for Large Language Models (2022) — 226 citations
• Emergent properties of the local geometry of neural loss landscapes (2019) — 64 citations
• Adversarial vulnerability of powerful near out-of-distribution detection (2022) — 18 citations
• Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error (2021) — 36 citations
• Large Scale Structure of Neural Network Loss Landscapes (2019) — 106 citations