Amir Globerson
Artificial Intelligence · 2003–2023
A researcher in the Science corpus: 29 papers; trusts 1,791 researchers and is trusted by 390 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 447 citations into it; #1,645 of 36,961 by trust here, #2,280 by citations
- Computer Vision and Pattern Recognition — 251 citations into it; #12,385 of 21,973 by trust here, #8,764 by citations
- Natural Language Processing — 169 citations into it; #3,266 of 5,725 by trust here, #3,077 by citations
- Optimization & Training — 64 citations into it; #367 of 2,605 by trust here, #429 by citations
- Representation & Self-Supervised Learning — 49 citations into it; #2,292 of 3,156 by trust here, #2,339 by citations
- Large Language Models — 44 citations into it; #563 of 810 by trust here, #746 by citations
- Evaluation & Benchmarks — 40 citations into it
- Information Retrieval & Search — 40 citations into it
Whom Amir Globerson trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Alex Krizhevsky
- Yann LeCun
- Ilya Sutskever
- Kaiming He
- Michael I. Jordan
- Ruslan Salakhutdinov
- Dimitri P. Bertsekas
Who trusts Amir Globerson overall
- Battista Biggio
- Blaine Nelson
- L. V. D. van der Maaten
- Pavel Laskov
- Masashi Sugiyama
- Giorgio Fumera
- Simon Shaolei Du
- Fabio Roli
- David A. Sontag
- Michael Brückner
Papers from Amir Globerson's perspective
Ordered by how strongly the researchers Amir Globerson 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)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Nightmare at test time: robust learning by feature deletion (2006) — 366 citations
- Learning to generalize to new compositions in image understanding (2016) — 71 citations
- Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs (2017) — 319 citations
- Weakly Supervised Semantic Parsing with Abstract Examples (2017) — 70 citations
- Introduction to dual composition for inference (2011) — 156 citations
- SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data (2017) — 287 citations
- Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks (2008) — 184 citations
- Structured Prediction Models via the Matrix-Tree Theorem (2007) — 170 citations
- Few-Shot Question Answering by Pretraining Span Selection (2021) — 104 citations
- Convex Learning with Invariances (2007) — 114 citations
- Collective Entity Resolution with Multi-Focal Attention (2016) — 107 citations
- Learning to Retrieve Passages without Supervision (2021) — 68 citations
- Euclidean Embedding of Co-occurrence Data (2004) — 267 citations
- Visual Prompting via Image Inpainting (2022) — 324 citations
- BERTese: Learning to Speak to BERT (2021) — 139 citations
- Explaining in Style: Training a GAN to explain a classifier in StyleSpace (2021) — 184 citations
- Pre-training of Mention Representations in Coreference Models (2020) — 10 citations
- Learning Bayesian Network Structure using LP Relaxations (2010) — 236 citations
- Tightening LP Relaxations for MAP using Message Passing (2008) — 323 citations
- Dissecting Recall of Factual Associations in Auto-Regressive Language Models (2023) — 547 citations