Sayak Paul

KV caching [1] stores the key and value tensors from tokens a transformer has already processed.

A few days back, AMD gifted me a GMKtec EVO-X2 so that I could do some of my compute-heavy work locally.

This post has an accompanying talk I gave at the MIT BCS department.

Attention is a crucial component in generative neural architectures for continuous modalities like images and videos from natural language.

Releasing a new version of an open-source library is an exhilarating experience.

This work was done at Carted, where I worked as a (founding) machine learning engineer.

This work was done at Carted, where I worked as a (founding) machine learning engineer.

Many people who aspire to become Machine Learning (ML) practitioners find it particularly difficult to continue to hone relevant skills when they pursue a job that does not involve even a tiny bit of ML.

This work was done at Carted, where I worked as a (founding) machine learning engineer.

This work was done at Carted, where I worked as a (founding) machine learning engineer.

This work was done at Carted, where I worked as a (founding) machine learning engineer.

In this post, I discuss my perspective on two primary questions pertaining to the Google Summer of Code (GSoC) program.

This work was done at Carted, where I worked as a (founding) machine learning engineer.

I recently added 15 different variants of the ConvNeXt architecture to TensorFlow Hub (TF-Hub).

This post shows how to build and install OpenCV 4.5.0 on a MacBook Pro that comes with an M1 chip.

In the previous post, we saw how to convert the pre-trained CRAFT model from PyTorch to TensorFlow Lite (TFLite) and run inference with the converted TFLite model.

This year researchers from the University of Wisconsin-Madison and Google published their work on MobileDet.

Data augmentation is a favorite recipe among deep learning practitioners especially for the ones working in the field of computer vision.