Articles by Mitchell Wortsman | Synthical

Synthical

Your space

Profile

Activity

Favorites

Folders

Feeds

Contacts

About

Claim page

Mitchell Wortsman

Follow

Activity

Upvotes

Folders

Articles

25

Resolving Discrepancies in Compute-Optimal Scaling of Language Models

28 October 2024 by Tomer Porian and others

Machine Learning, Computation and Language

Scaling Exponents Across Parameterizations and Optimizers

16 July 2024 by Katie Everett and others at

Machine Learning

Reproducible scaling laws for contrastive language-image learning

13 July 2024 by Mehdi Cherti and others

Machine Learning, Artificial Intelligence

DataComp-LM: In search of the next generation of training sets for language models

20 June 2024 by Jeffrey Li and others

Machine Learning, Computation and Language

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

13 March 2024 by Samir Yitzhak Gadre and others at

University of Washington

Computation and Language, Machine Learning

OLMo: Accelerating the Science of Language Models

28 February 2024 by Dirk Groeneveld and others at

University of Washington

Computation and Language

DataComp: In search of the next generation of multimodal datasets

20 October 2023 by Samir Yitzhak Gadre and others at

Tel Aviv University

Computer Vision and Pattern Recognition, Computation and Language

Replacing softmax with ReLU in Vision Transformers

17 October 2023 by Mitchell Wortsman and others at

Computer Vision and Pattern Recognition, Machine Learning

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

17 October 2023 by Mitchell Wortsman and others

Machine Learning, Computer Vision and Pattern Recognition

Small-scale proxies for large-scale Transformer training instabilities

16 October 2023 by Mitchell Wortsman and others

Machine Learning

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

7 August 2023 by Anas Awadalla and others

Computer Vision and Pattern Recognition, Artificial Intelligence

Editing Models with Task Arithmetic

29 March 2023 by Gabriel Ilharco and others

Machine Learning, Computation and Language

The Role of Pre-training Data in Transfer Learning

1 March 2023 by Rahim Entezari and others

Computer Vision and Pattern Recognition, Machine Learning

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

14 December 2022 by Samir Yitzhak Gadre and others

Computer Vision and Pattern Recognition, Machine Learning

Exploring The Landscape of Distributional Robustness for Question Answering Models

22 October 2022 by Anas Awadalla and others

Computation and Language, Machine Learning

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

16 October 2022 by Christoph Schuhmann and others

Computer Vision and Pattern Recognition, Artificial Intelligence

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

14 October 2022 by Thao Nguyen and others

Machine Learning, Computer Vision and Pattern Recognition

Patching open-vocabulary models by interpolating weights

11 October 2022 by Gabriel Ilharco and others

Computer Vision and Pattern Recognition, Machine Learning

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

22 August 2022 by Alex Fang and others

Computer Vision and Pattern Recognition, Computation and Language

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

21 June 2022 by Mitchell Wortsman and others

Machine Learning, Computation and Language

Robust fine-tuning of zero-shot models

25 February 2022 by Mitchell Wortsman and others

Computer Vision and Pattern Recognition, Machine Learning

Learning Neural Network Subspaces

9 June 2021 by Mitchell Wortsman and others

Machine Learning, Computer Vision and Pattern Recognition

Deconstructing the Structure of Sparse Neural Networks

30 November 2020 by Maxwell Van Gelder and others

Machine Learning, Computer Vision and Pattern Recognition

Supermasks in Superposition

30 June 2020 by Mitchell Wortsman and others

Machine Learning, Artificial Intelligence

What's Hidden in a Randomly Weighted Neural Network?

31 March 2020 by Vivek Ramanujan and others

Computer Vision and Pattern Recognition, Machine Learning

Soft Threshold Weight Reparameterization for Learnable Sparsity

14 February 2020 by Aditya Kusupati and others

Machine Learning, Computer Vision and Pattern Recognition

Discovering Neural Wirings

1 July 2019 by Mitchell Wortsman and others

Machine Learning, Computer Vision and Pattern Recognition

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

26 March 2019 by Mitchell Wortsman and others

Computer Vision and Pattern Recognition, Artificial Intelligence

This is an AI-generated summary

Key points

Topics

Machine Learning Computer Vision and Pattern Recognition Computation and Language Artificial Intelligence Robotics Neural and Evolutionary Computing