research
∙
08/02/2023
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
We introduce OpenFlamingo, a family of autoregressive vision-language mo...
share
research
∙
07/19/2023
Improving Multimodal Datasets with Image Captioning
Massive web datasets play a key role in the success of large vision-lang...
research
∙
05/22/2023
TaskWeb: Selecting Better Source Tasks for Multi-task NLP
Recent work in NLP has shown promising results in training models on lar...
research
∙
04/27/2023
DataComp: In search of the next generation of multimodal datasets
Large multimodal datasets have been instrumental in recent breakthroughs...
research
∙
12/14/2022
Reproducible scaling laws for contrastive language-image learning
Scaling up neural networks has led to remarkable performance across a wi...
research
∙
12/08/2022
Editing Models with Task Arithmetic
Changing how pre-trained models behave – e.g., improving their performan...
research
∙
12/06/2022
Adaptive Testing of Computer Vision Models
Vision models often fail systematically on groups of data that share com...
research
∙
10/22/2022
Exploring The Landscape of Distributional Robustness for Question Answering Models
We conduct a large empirical evaluation to investigate the landscape of ...
research
∙
08/10/2022
Patching open-vocabulary models by interpolating weights
Open-vocabulary models like CLIP achieve high accuracy across many image...
research
∙
08/10/2022
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
Web-crawled datasets have enabled remarkable generalization capabilities...
research
∙
05/03/2022
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Contrastively trained image-text models such as CLIP, ALIGN, and BASIC h...
research
∙
03/20/2022
CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration
Households across the world contain arbitrary objects: from mate gourds ...
research
∙
03/10/2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
The conventional recipe for maximizing model accuracy is to (1) train mu...
research
∙
09/04/2021
Robust fine-tuning of zero-shot models
Large pre-trained models such as CLIP offer consistent accuracy across a...
research
∙
04/18/2021
Documenting the English Colossal Clean Crawled Corpus
As language models are trained on ever more text, researchers are turnin...
research
∙
03/25/2021
Contrasting Contrastive Self-Supervised Representation Learning Models
In the past few years, we have witnessed remarkable breakthroughs in sel...
research
∙
03/24/2021
Finetuning Pretrained Transformers into RNNs
Transformers have outperformed recurrent neural networks (RNNs) in natur...
research
∙
05/01/2020
Probing Text Models for Common Ground with Visual Representations
Vision, as a central component of human perception, plays a fundamental ...
research
∙
04/06/2020
Evaluating NLP Models via Contrast Sets
Standard test sets for supervised learning evaluate in-distribution gene...
research
∙
02/15/2020
Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
Fine-tuning pretrained contextual word embedding models to supervised do...
research
∙
09/19/2019