Tom Goldstein
Artificial Intelligence · 2009–2025
A researcher in the Science corpus: 49 papers; trusts 3,066 researchers and is trusted by 555 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,304 citations into it; #2,900 of 36,961 by trust here, #1,468 by citations
- Computer Vision and Pattern Recognition — 949 citations into it; #2,432 of 21,973 by trust here, #1,177 by citations
- Safety, Robustness & Interpretability — 326 citations into it; #700 of 2,259 by trust here, #199 by citations
- Optimization & Training — 243 citations into it; #872 of 2,605 by trust here, #355 by citations
- Representation & Self-Supervised Learning — 240 citations into it
- Computational Mechanics — 153 citations into it; #185 of 10,021 by trust here, #633 by citations
- Model Architectures — 152 citations into it; #2,134 of 2,288 by trust here, #1,834 by citations
- Generative Models — 150 citations into it
Whom Tom Goldstein trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Yann LeCun
- E.J. Candes
- Stanley J. Osher
- Ilya Sutskever
- Ross B. Girshick
Who trusts Tom Goldstein overall
- Laurent Condat
- José M. Bioucas-Dias
- Brendan O'Donoghue
- Xiaoqun Zhang
- Gavin Taylor
- Wotao Yin
- Simon Setzer
- Junfeng Yang
- Gabriele Steidl
- Soham De
Papers from Tom Goldstein's perspective
Ordered by how strongly the researchers Tom Goldstein 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Visualizing the Loss Landscape of Neural Nets (2017) — 2,377 citations
- Adversarial Training for Free! (2019) — 1,469 citations
- FreeLB: Enhanced Adversarial Training for Natural Language Understanding (2019) — 520 citations
- 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
- Are adversarial examples inevitable? (2018) — 305 citations
- Training Neural Networks Without Gradients: A Scalable ADMM Approach (2016) — 297 citations
- Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models (2022) — 505 citations
- The Split Bregman Method for L1-Regularized Problems (2009) — 4,469 citations
- DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation (2018) — 273 citations
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks (2018) — 1,286 citations
- FreeLB: Enhanced Adversarial Training for Language Understanding (2019) — 82 citations
- Universal Guidance for Diffusion Models (2023) — 495 citations
- Training Quantized Nets: A Deeper Understanding (2017) — 230 citations
- SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training (2021) — 556 citations
- ACE: Adapting to Changing Environments for Semantic Segmentation (2019) — 109 citations
- Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks (2020) — 83 citations
- Long-Short Transformer: Efficient Transformers for Language and Vision (2021) — 175 citations
- Stabilizing Adversarial Nets With Prediction Methods (2017) — 92 citations
- MetaPoison: Practical General-purpose Clean-label Data Poisoning (2020) — 237 citations