Gabriel Ilharco

Affiliations:

University of Washington, WA, USA

According to our database¹, Gabriel Ilharco authored at least 35 papers between 2019 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2024

Language models scale reliably with over-training and on downstream tasks.

[BibT_eX]

[DOI]

CoRR, 2024

2023

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Improving multimodal datasets with image captioning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DataComp: In search of the next generation of multimodal datasets.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Editing models with task arithmetic.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Adaptive Testing of Computer Vision Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

TaskWeb: Selecting Better Source Tasks for Multi-task NLP.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Reproducible Scaling Laws for Contrastive Language-Image Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Editing Models with Task Arithmetic.

[BibT_eX]

[DOI]

CoRR, 2022

CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration.

[BibT_eX]

[DOI]

CoRR, 2022

Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Patching open-vocabulary models by interpolating weights.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.

[BibT_eX]

[DOI]

Raphael Gontijo Lopes

Proceedings of the International Conference on Machine Learning, 2022

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP).

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Exploring The Landscape of Distributional Robustness for Question Answering Models.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

Robust fine-tuning of zero-shot models.

[BibT_eX]

[DOI]

Raphael Gontijo Lopes

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Robust fine-tuning of zero-shot models.

[BibT_eX]

[DOI]

CoRR, 2021

Documenting the English Colossal Clean Crawled Corpus.

[BibT_eX]

[DOI]

CoRR, 2021

Contrasting Contrastive Self-Supervised Representation Learning Models.

[BibT_eX]

[DOI]

CoRR, 2021

Probing Contextual Language Models for Common Ground with Visual Representations.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021

MultiModalQA: complex question answering over text, tables and images.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Contrasting Contrastive Self-Supervised Representation Learning Pipelines.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Finetuning Pretrained Transformers into RNNs.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

2020

Probing Text Models for Common Ground with Visual Representations.

[BibT_eX]

[DOI]

CoRR, 2020

Evaluating NLP Models via Contrast Sets.

[BibT_eX]

[DOI]

CoRR, 2020

Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping.

[BibT_eX]

[DOI]

CoRR, 2020

Toward ML-centric cloud platforms.

[BibT_eX]

[DOI]

Commun. ACM, 2020

High Performance Natural Language Processing.

[BibT_eX]

[DOI]

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, 2020

Evaluating Models' Local Decision Boundaries via Contrast Sets.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

2019

General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping.

[BibT_eX]

[DOI]

Proceedings of the Visually Grounded Interaction and Language (ViGIL), 2019

Transferable Representation Learning in Vision-and-Language Navigation.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Large-Scale Representation Learning from Visually Grounded Untranscribed Speech.

[BibT_eX]

[DOI]

Gabriel Ilharco

Yuan Zhang

Jason Baldridge

Proceedings of the 23rd Conference on Computational Natural Language Learning, 2019

Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation.

[BibT_eX]

[DOI]

Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019

Gabriel Ilharco

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...