Mitchell Wortsman

发表

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Ali Farhadi, Roozbeh Mottaghi, Mohammad Rastegari, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Alexander W. Fang, Ludwig Schmidt, Vaishaal Shankar, 2022, ArXiv.

Robust fine-tuning of zero-shot models

Jong Wook Kim, Ali Farhadi, Hannaneh Hajishirzi, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Ari S. Morcos, Ali Farhadi, Y. Carmon, 2022, ICML.

Patching open-vocabulary models by interpolating weights

Ali Farhadi, S. Song, Gabriel Ilharco, 2022, Neural Information Processing Systems.

LAION-5B: An open large-scale dataset for training next generation image-text models

Ludwig Schmidt, Mitchell Wortsman, Mehdi Cherti, 2022, NeurIPS.

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

Sewoong Oh, Gabriel Ilharco, Ludwig Schmidt, 2022, ArXiv.

Patching open-vocabulary models by interpolating weights

Ali Farhadi, S. Song, Gabriel Ilharco, 2022, NeurIPS.

How well do contrastively trained models transfer?

Ludwig Schmidt, Mitchell Wortsman, O. Saukh, 2022 .

Lo-fi: Distributed Fine-tuning without Communication

Ari S. Morcos, Michael G. Rabbat, Ali Farhadi, 2022, Trans. Mach. Learn. Res..

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

Sewoong Oh, Gabriel Ilharco, Ludwig Schmidt, 2022, Neural Information Processing Systems.

Lo-fi: Distributed Fine-tuning without Communication

Ari S. Morcos, Michael G. Rabbat, Ali Farhadi, 2022, Trans. Mach. Learn. Res..

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

Alexander W. Fang, Ludwig Schmidt, Vaishaal Shankar, 2022, ICML.

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

Gabriel Ilharco, Ludwig Schmidt, Mitchell Wortsman, 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Reproducible Scaling Laws for Contrastive Language-Image Learning

Gabriel Ilharco, Ludwig Schmidt, Mitchell Wortsman, 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

What’s Hidden in a Randomly Weighted Neural Network?

Ali Farhadi, Mohammad Rastegari, Aniruddha Kembhavi, 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Editing Models with Task Arithmetic

Marco Tulio Ribeiro, Gabriel Ilharco, Hannaneh Hajishirzi, 2022, ArXiv.

Exploring The Landscape of Distributional Robustness for Question Answering Models

Ian H. Magnusson, Gabriel Ilharco, Hannaneh Hajishirzi, 2022, EMNLP.

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

Sewoong Oh, Gabriel Ilharco, Ludwig Schmidt, 2022, NeurIPS.

Editing Models with Task Arithmetic

Marco Tulio Ribeiro, Ali Farhadi, Gabriel Ilharco, 2022, ICLR.

Supermasks in Superposition pdf

Ali Farhadi, Jason Yosinski, Rosanne Liu, 2020, NeurIPS.

Learning Neural Network Subspaces pdf

Ali Farhadi, Carlos Guestrin, Mitchell Wortsman, 2021, ICML.

The Role of Pre-training Data in Transfer Learning

Hanie Sedghi, Ludwig Schmidt, Mitchell Wortsman, 2023, ArXiv.

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

Ludwig Schmidt, Mitchell Wortsman, S. Gadre, 2022, ArXiv.

Soft Threshold Weight Reparameterization for Learnable Sparsity

S. Kakade, Ali Farhadi, Prateek Jain, 2020, ICML.

Stable and low-precision training for large-scale vision-language models

Ari S. Morcos, Luke Zettlemoyer, Ali Farhadi, 2023, ArXiv.

DataComp: In search of the next generation of multimodal datasets

Pang Wei Koh, Ali Farhadi, A. Dimakis, 2023, ArXiv.

Discovering Neural Wirings

Ali Farhadi, Mohammad Rastegari, Mitchell Wortsman, 2019, NeurIPS.

THE ROLE OF LANGUAGE IMAGE PRE-TRAINING DATA IN TRANSFER LEARNING

Ludwig Schmidt, Mitchell Wortsman, O. Saukh, 2023 .

DataComp: In search of the next generation of multimodal datasets

Pang Wei Koh, Ali Farhadi, A. Dimakis, 2023, ArXiv.

DataComp: In search of the next generation of multimodal datasets

Pang Wei Koh, Ali Farhadi, A. Dimakis, 2023, ArXiv.

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

Pang Wei Koh, Gabriel Ilharco, Ludwig Schmidt, 2023, 2308.01390.

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

Pang Wei Koh, Gabriel Ilharco, Ludwig Schmidt, 2023, ArXiv.

Deconstructing the Structure of Sparse Neural Networks pdf

Mitchell Wortsman, Kiana Ehsani, Maxwell Van Gelder, 2020, ArXiv.

DataComp: In search of the next generation of multimodal datasets

Pang Wei Koh, Ali Farhadi, A. Dimakis, 2023, NeurIPS.

Stable and low-precision training for large-scale vision-language models

Ari S. Morcos, Luke Zettlemoyer, Ali Farhadi, 2023, NeurIPS.

OLMo: Accelerating the Science of Language Models

Khyathi Raghavi Chandu, Dirk Groeneveld, Kyle Lo, 2024, ArXiv.

Supermasks in Superposition pdf

Ali Farhadi, Jason Yosinski, Rosanne Liu, 2020, NeurIPS.