Avi Schwarzschild

Artificial Intelligence · 2019–2024

A researcher in the Science corpus: 9 papers; trusts 341 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 417 citations into it
• Computer Vision and Pattern Recognition — 262 citations into it
• Safety, Robustness & Interpretability — 111 citations into it
• Representation & Self-Supervised Learning — 109 citations into it
• Model Architectures — 51 citations into it
• Optimization & Training — 49 citations into it
• Generative Models — 31 citations into it
• Statistical and Nonlinear Physics — 11 citations into it

Whom Avi Schwarzschild trusts overall

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

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

Who trusts Avi Schwarzschild overall

1. Quentin Cappart
2. Denny Zhou
3. Collin Burns
4. Alexander Robey

Papers from Avi Schwarzschild's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks (2021) — 115 citations
• Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses (2020) — 406 citations
• Universal Guidance for Diffusion Models (2023) — 495 citations
• SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training (2021) — 556 citations
• Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory (2019) — 37 citations
• A Cookbook of Self-Supervised Learning (2023) — 398 citations
• TOFU: A Task of Fictitious Unlearning for LLMs (2024) — 510 citations
• Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text (2024) — 325 citations
• Baseline Defenses for Adversarial Attacks Against Aligned Language Models (2023) — 743 citations