Pang Wei Koh
Artificial Intelligence · 2010–2023
A researcher in the Science corpus: 25 papers; trusts 1,644 researchers and is trusted by 1,833 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 761 citations into it; #877 of 36,961 by trust here, #743 by citations
- Computer Vision and Pattern Recognition — 368 citations into it; #1,854 of 21,973 by trust here, #2,277 by citations
- Safety, Robustness & Interpretability — 254 citations into it; #41 of 2,259 by trust here, #36 by citations
- Natural Language Processing — 131 citations into it; #346 of 5,725 by trust here, #582 by citations
- Evaluation & Benchmarks — 129 citations into it
- Optimization & Training — 90 citations into it
- Representation & Self-Supervised Learning — 83 citations into it; #3,037 of 3,156 by trust here, #983 by citations
- Signal Processing — 77 citations into it; #4,498 of 7,592 by trust here, #4,055 by citations
Whom Pang Wei Koh trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Yann LeCun
- Kaiming He
- Christian Szegedy
- Ilya Sutskever
- Diederik P. Kingma
- Ruslan Salakhutdinov
- Radford M. Neal
Who trusts Pang Wei Koh overall
- Quanshi Zhang
- Tianfu Wu
- Eric Wallace
- Yoshua Bengio
- Percy Liang
- Dongxian Wu
- Song-Chun Zhu
- Sercan Ö. Arik
- Nicholas Carlini
- Daniel S. Weld
Papers from Pang Wei Koh's perspective
Ordered by how strongly the researchers Pang Wei Koh 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)
- 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)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- Understanding Black-box Predictions via Influence Functions (2017) — 3,706 citations
- Tiled convolutional neural networks (2010) — 352 citations
- On Random Weights and Unsupervised Feature Learning (2011) — 462 citations
- Learning Deep Energy Models (2011) — 201 citations
- Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization (2019) — 1,692 citations
- Sparse Filtering (2011) — 276 citations
- DataComp: In search of the next generation of multimodal datasets (2023) — 734 citations
- Certified Defenses for Data Poisoning Attacks (2017) — 884 citations
- OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models (2023) — 642 citations
- An Investigation of Why Overparameterization Exacerbates Spurious Correlations (2020) — 450 citations
- Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020) — 480 citations
- ExpBERT: Representation Engineering with Natural Language Explanations (2020) — 45 citations
- Distributionally Robust Neural Networks (2020) — 768 citations
- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation (2023) — 1,471 citations
- Just Train Twice: Improving Group Robustness without Training Group Information (2021) — 724 citations
- Stronger data poisoning attacks break data sanitization defenses (2018) — 285 citations
- Are aligned neural networks adversarially aligned? (2023) — 387 citations
- Selective Classification Can Magnify Disparities Across Groups (2020) — 53 citations
- Concept Bottleneck Models (2020) — 1,388 citations