Mitchell Wortsman

I am a member of the technical staff on the pretraining team at Anthropic. Previously, I was a PhD student at the University of Washington, advised by Ali Farhadi and Ludwig Schmidt.

Email  /  Google Scholar  /  Twitter

profile photo
Select publications, preprints & projects
(*indicates equal contribution)

Small-scale proxies for large-scale Transformer training instabilities
Mitchell Wortsman, Peter J. Liu, Lechao Xiao, Katie Everett, Alex Alemi, Ben Adlam, John D. Co-Reyes, Izzeddin Gur, Abhishek Kumar, Roman Novak, Jeffrey Pennington, Jascha Sohl-dickstein, Kelvin Xu, Jaehoon Lee, Justin Gilmer, Simon Kornblith
ICLR, 2024 (oral)
arxiv

Replacing softmax with ReLU in Vision Transformers
Mitchell Wortsman, Jaehoon Lee, Justin Gilmer, Simon Kornblith
ArXiv, 2023
arxiv

DataComp: In search of the next generation of multimodal datasets
Samir Yitzhak Gadre*, Gabriel Ilharco*, Alex Fang*, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, et al., Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
NeurIPS, 2023
arXiv

Stable and low-precision training for large-scale vision-language models
Mitchell Wortsman*, Tim Dettmers*, Luke Zettlemoyer, Ari S. Morcos, Ali Farhadi, Ludwig Schmidt
NeurIPS, 2023
arxiv

OpenFlamingo: an open-source framework for training large multimodal models
Anas Awadalla, Irena Goa, Joshua Gardner, Jack Hessel, et al., Mitchell Wortsman, Ludwig Schmidt
GitHub, 2023

lo-fi: distributed fine-tuning without communication
Mitchell Wortsman, Suchin Gururangan, Shen Li, Ali Farhadi, Ludwig Schmidt, Micheal Rabbat, Ari S. Morcos
TMLR, 2022
arxiv

Patching open-vocabulary models by interpolating weights
Gabriel Ilharco*, Mitchell Wortsman*, Samir Yitzhak Gadre*, Shuran Song Hannaneh Hajishirzi, Simon Kornblith, Ali Farhadi, Ludwig Schmidt
NeurIPS, 2022
arxiv

CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration
Samir Yitzhak Gadre, Mitchell Wortsman, Gabriel Ilharco, Ludwig Schmidt Shuran Song
ArXiv, 2022
arxiv

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon**, Simon Kornblith**, Ludwig Schmidt**
ICML, 2022
arxiv

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Alex Fang, Gabriel Ilharco, Mitchell Wortsman, Yuhao Wan, Vaishaal Shankar, Achal Dave, Ludwig Schmidt
ICML, 2022
arxiv

Robust fine-tuning of zero-shot models
Mitchell Wortsman*, Gabriel Ilharco*, Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo-Lopes, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt
CVPR, 2022 (oral, best paper finalist)
arxiv / code

OpenCLIP: An open source implementation of CLIP
Gabriel Ilharco*, Mitchell Wortsman*, Ross Wightman*, Cade Gordon*, Nicholas Carlini, Rohan Taori, Achal Dave, Vaishaal Shankar, Hongseok Namkoong, John Miller, Hannaneh Hajishirzi, Ali Farhadi, Ludwig Schmidt
GitHub, 2021

What's Hidden in a Randomly Weighted Neural Network?
Vivek Ramanujan*, Mitchell Wortsman*, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari
CVPR, 2020
arxiv / code












Template modified from here.