Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping J Dodge, G Ilharco, R Schwartz, A Farhadi, H Hajishirzi, N Smith arXiv preprint arXiv:2002.06305, 2020 | 305 | 2020 |
Evaluating models’ local decision boundaries via contrast sets M Gardner, Y Artzi, V Basmov, J Berant, B Bogin, S Chen, P Dasigi, D Dua, ... Proceedings of the 2020 Conference on Empirical Methods in Natural Language …, 2020 | 283 | 2020 |
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time M Wortsman, G Ilharco, SY Gadre, R Roelofs, R Gontijo-Lopes, ... International Conference on Machine Learning, 23965-23998, 2022 | 111 | 2022 |
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation V Jain*, G Ilharco*, A Ku*, A Vaswani, E Ie, J Baldridge Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019 | 98 | 2019 |
Robust fine-tuning of zero-shot models M Wortsman*, G Ilharco*, JW Kim, M Li, S Kornblith, R Roelofs, RG Lopes, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 96 | 2022 |
Effective and general evaluation for instruction conditioned navigation using dynamic time warping G Ilharco, V Jain, A Ku, E Ie, J Baldridge arXiv preprint arXiv:1907.05446, 2019 | 85* | 2019 |
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus J Dodge, M Sap, A Marasović, W Agnew, G Ilharco, D Groeneveld, ... arXiv preprint arXiv:2104.08758, 2021 | 75* | 2021 |
Transferable representation learning in vision-and-language navigation H Huang, V Jain, H Mehta, A Ku, G Ilharco, J Baldridge, E Ie Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 | 64 | 2019 |
Large-scale representation learning from visually grounded untranscribed speech G Ilharco, Y Zhang, J Baldridge arXiv preprint arXiv:1909.08782, 2019 | 54 | 2019 |
MultiModalQA: Complex Question Answering over Text, Tables and Images A Talmor, O Yoran, A Catav, D Lahav, Y Wang, A Asai, G Ilharco, ... arXiv preprint arXiv:2104.06039, 2021 | 50 | 2021 |
Toward ML-centric cloud platforms R Bianchini, M Fontoura, E Cortez, A Bonde, A Muzio, AM Constantin, ... Communications of the ACM 63 (2), 50-59, 2020 | 41 | 2020 |
OpenCLIP G Ilharco, M Wortsman, N Carlini, R Taori, A Dave, V Shankar, ... Zenodo 4, 5, 2021 | 35* | 2021 |
Contrasting Contrastive Self-Supervised Representation Learning Pipelines K Kotar, G Ilharco, L Schmidt, K Ehsani, R Mottaghi Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 28 | 2021 |
Finetuning Pretrained Transformers into RNNs J Kasai, H Peng, Y Zhang, D Yogatama, G Ilharco, N Pappas, Y Mao, ... arXiv preprint arXiv:2103.13076, 2021 | 25 | 2021 |
Probing contextual language models for common ground with visual representations G Ilharco, R Zellers, A Farhadi, H Hajishirzi Proceedings of the 2021 Conference of the North American Chapter of the …, 2021 | 24 | 2021 |
Data determines distributional robustness in contrastive language image pre-training (clip) A Fang, G Ilharco, M Wortsman, Y Wan, V Shankar, A Dave, L Schmidt International Conference on Machine Learning, 6216-6234, 2022 | 16 | 2022 |
CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration SY Gadre, M Wortsman, G Ilharco, L Schmidt, S Song arXiv preprint arXiv:2203.10421, 2022 | 14 | 2022 |
Patching open-vocabulary models by interpolating weights G Ilharco*, M Wortsman*, SY Gadre*, S Song, H Hajishirzi, S Kornblith, ... arXiv preprint arXiv:2208.05592, 2022 | 9 | 2022 |
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP T Nguyen, G Ilharco, M Wortsman, S Oh, L Schmidt arXiv preprint arXiv:2208.05516, 2022 | 4 | 2022 |
Reproducible scaling laws for contrastive language-image learning M Cherti, R Beaumont, R Wightman, M Wortsman, G Ilharco, C Gordon, ... arXiv preprint arXiv:2212.07143, 2022 | 1 | 2022 |