David Bau
Computer Vision and Pattern Recognition · 2017–2024
A researcher in the Science corpus: 23 papers; trusts 2,348 researchers and is trusted by 1,203 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 591 citations into it; #1,693 of 21,973 by trust here, #1,442 by citations
- Artificial Intelligence — 511 citations into it; #3,434 of 36,961 by trust here, #1,874 by citations
- Generative Models — 216 citations into it; #320 of 1,963 by trust here, #282 by citations
- Safety, Robustness & Interpretability — 170 citations into it; #325 of 2,259 by trust here, #169 by citations
- Natural Language Processing — 104 citations into it
- Representation & Self-Supervised Learning — 94 citations into it
- Large Language Models — 64 citations into it; #477 of 810 by trust here, #461 by citations
- Model Architectures — 62 citations into it
Whom David Bau trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Karen Simonyan
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Ross B. Girshick
- Christian Szegedy
Who trusts David Bau overall
- Bolei Zhou
- Jun-Yan Zhu
- Yujun Shen
- Quanshi Zhang
- Richard Zhang
- Chenlin Meng
- Antonio Torralba
- Miaoyun Zhao
- Lucy Chai
- Jinjin Gu
Papers from David Bau's perspective
Ordered by how strongly the researchers David Bau 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Network Dissection: Quantifying Interpretability of Deep Visual Representations (2017) — 1,795 citations
- Semantic photo manipulation with a generative image prior (2019) — 368 citations
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks (2018) — 513 citations
- Seeing What a GAN Cannot Generate (2019) — 353 citations
- Paint by Word (2021) — 138 citations
- Explaining Explanations: An Overview of Interpretability of Machine Learning (2018) — 2,256 citations
- Locating and Editing Factual Associations in GPT (2022) — 2,886 citations
- Interpreting Deep Visual Representations via Network Dissection (2017) — 361 citations
- Diverse Image Generation via Self-Conditioned GANs (2020) — 122 citations
- Rewriting a Deep Generative Model (2020) — 162 citations
- Locating and Editing Factual Knowledge in GPT (2022) — 83 citations
- What makes fake images detectable? Understanding properties that generalize (2020) — 454 citations
- Erasing Concepts from Diffusion Models (2023) — 604 citations
- Mass-Editing Memory in a Transformer (2022) — 1,108 citations
- Interpretable Basis Decomposition for Visual Explanation (2018) — 328 citations
- Understanding the role of individual units in a deep neural network (2020) — 535 citations
- Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models (2024) — 394 citations
- Unified Concept Editing in Diffusion Models (2023) — 425 citations
- Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task (2022) — 503 citations
- Learning Words by Drawing Images (2019) — 9 citations