The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and
language model, both in terms of size of the components and the breadth of its training task …

Given the increasing prevalence of facial analysis technology, the problem of bias in the
tools is now becoming an even greater source of concern. Several studies have highlighted …

We explore the boundaries of scaling up a multilingual vision and language model both in
terms of size of the components and the breadth of its training task mixture. Our model …

Existing facial analysis systems have been shown to yield biased results against certain
demographic subgroups. Due to its impact on society, it has become imperative to ensure …

Nowadays, Artificial Intelligence (AI) algorithms show a strong performance for many use
cases, making them desirable for real-world scenarios where the algorithms provide high …

We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity
for multiclass classification with non-binary sensitive attributes via a reduction to a sequence …

We study the effectiveness of data-balancing for mitigating biases in contrastive language-
image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffirm prior …

Demographic biases in source datasets have been shown as one of the causes of
unfairness and discrimination in the predictions of Machine Learning models. One of the …

Abstract Facial Expression Recognition (FER) uses images of faces to identify the emotional
state of users, allowing for a closer interaction between humans and autonomous systems …