Aditi Raghunathan
Artificial Intelligence · 2018–2022
A researcher in the Science corpus: 14 papers; trusts 1,094 researchers and is trusted by 222 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 480 citations into it; #2,301 of 36,961 by trust here, #1,400 by citations
- Computer Vision and Pattern Recognition — 231 citations into it; #3,752 of 21,973 by trust here, #2,896 by citations
- Safety, Robustness & Interpretability — 225 citations into it; #124 of 2,259 by trust here, #76 by citations
- Representation & Self-Supervised Learning — 72 citations into it
- Evaluation & Benchmarks — 59 citations into it
- Natural Language Processing — 58 citations into it; #5,043 of 5,725 by trust here, #4,063 by citations
- Optimization & Training — 50 citations into it
- Scaling & Learning Theory — 42 citations into it
Whom Aditi Raghunathan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Nicholas Carlini
- Geoffrey E. Hinton
- Diederik P. Kingma
- Ian J. Goodfellow
- Kaiming He
- Christian Szegedy
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
Who trusts Aditi Raghunathan overall
- Eric Wong
- Francesco Croce
- Matthias Hein
- Shiqi Wang
- J. Kolter
- Maksym Andriushchenko
- Jeremy M. Cohen
- Huan Zhang
- Florian Tramèr
- Pratyush Maini
Papers from Aditi Raghunathan's perspective
Ordered by how strongly the researchers Aditi Raghunathan trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- Certified Defenses against Adversarial Examples (2018) — 1,019 citations
- Unlabeled Data Improves Adversarial Robustness (2019) — 814 citations
- An Explanation of In-context Learning as Implicit Bayesian Inference (2021) — 1,108 citations
- Adversarial Training Can Hurt Generalization (2019) — 257 citations
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (2022) — 972 citations
- Understanding and Mitigating the Tradeoff Between Robustness and Accuracy (2020) — 256 citations
- Certified Robustness to Adversarial Word Substitutions (2019) — 341 citations
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations (2020) — 450 citations
- The Pitfalls of Simplicity Bias in Neural Networks (2020) — 478 citations
- Semidefinite relaxations for certifying robustness to adversarial examples (2018) — 461 citations
- Just Train Twice: Improving Group Robustness without Training Group Information (2021) — 724 citations
- Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift (2022) — 48 citations
- Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization (2021) — 331 citations