Gabriel Ilharco

Artificial Intelligence · 2019–2024

A researcher in the Science corpus: 22 papers; trusts 1,380 researchers and is trusted by 24 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 872 citations into it; #8,027 of 35,345 by trust here, #1,672 by citations
• Computer Vision and Pattern Recognition — 663 citations into it; #9,170 of 21,575 by trust here, #1,847 by citations
• Natural Language Processing — 377 citations into it
• Evaluation & Benchmarks — 271 citations into it
• Multimodal Learning — 163 citations into it; #782 of 1,211 by trust here, #374 by citations
• Representation & Self-Supervised Learning — 144 citations into it; #2,471 of 3,145 by trust here, #1,127 by citations
• Large Language Models — 141 citations into it; #403 of 799 by trust here, #416 by citations
• Safety, Robustness & Interpretability — 110 citations into it

Whom Gabriel Ilharco trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Kaiming He
4. Alex Krizhevsky
5. Yoshua Bengio
6. Ilya Sutskever
7. Yann LeCun
8. Ross B. Girshick
9. Jimmy Ba
10. Sepp Hochreiter

Who trusts Gabriel Ilharco overall

1. David F. Harwath
2. Puyuan Peng
3. Prateek Yadav
4. Mitchell Wortsman
5. Mohit Bansal
6. Jialu Li
7. Le Yu
8. Belinda Z. Li
9. Phúc H. Lê Khắc
10. Rowan Zellers

Papers from Gabriel Ilharco's perspective

Ordered by how strongly the researchers Gabriel Ilharco trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Reproducible Scaling Laws for Contrastive Language-Image Learning (2022) — 1,494 citations
• Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022) — 1,632 citations
• Robust fine-tuning of zero-shot models (2021) — 1,012 citations
• Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus (2021) — 696 citations
• CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration (2022) — 118 citations
• Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping (2020) — 739 citations
• DataComp: In search of the next generation of multimodal datasets (2023) — 734 citations
• OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models (2023) — 642 citations
• Large-Scale Representation Learning from Visually Grounded Untranscribed Speech (2019) — 62 citations
• Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020) — 462 citations
• Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (2019) — 231 citations
• Transferable Representation Learning in Vision-and-Language Navigation (2019) — 95 citations
• Evaluating NLP Models via Contrast Sets (2020) — 85 citations
• MultiModalQA: Complex Question Answering over Text, Tables and Images (2021) — 252 citations
• Editing Models with Task Arithmetic (2022) — 1,114 citations
• Probing Contextual Language Models for Common Ground with Visual Representations (2020) — 28 citations
• CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation (2022) — 324 citations
• DataComp-LM: In search of the next generation of training sets for language models (2024) — 374 citations
• Documenting the English Colossal Clean Crawled Corpus (2021) — 51 citations
• Probing Text Models for Common Ground with Visual Representations (2020) — 14 citations