Tech Musings – Shubham Gupta

GPUs go brrr with Mojo - Fundamentals

programming

gpu

mojo

Back on the blog after a long hiatus - this time, I’m shifting gears from just reviewing papers(which are available on my GitHub) to diving deep into hands-on implementations.

Jul 6, 2025

Shubham Gupta

BERT + BM25 = BISON

nlp

transformer

review

A new framework for information retrieval from documents

Aug 31, 2020

Shubham Gupta

LongFormer

nlp

transformer

review

longformer

Transformers for loooong documents

May 11, 2020

Shubham Gupta

TagLM

nlp

language_model

review

This is the TagLM paper mentioned in Lecture 13 in the CS224N course title Semi-supervised sequence tagging with bidirectional language models

Apr 23, 2020

Shubham Gupta

How much do you know?

nlp

language_model

review

Measure the amount of information stored in a model

Apr 21, 2020

Shubham Gupta

Attention is all you need

nlp

attention

review

New architecture based solely on attention mechanisms called Transformer. Gets rids of recurrent and convolution networks completely.

Apr 20, 2020

Shubham Gupta

REALM: Retrieval-Augmented Language MOdel Pre-Training

nlp

bert

review

A better Q&A system based on knowledge retrieval

Mar 14, 2020

Shubham Gupta

Bayesian Golf Putting Model

jupyter

bayesian

golf_putting

Are you the next Tiger Woods?

Mar 12, 2020

Yo!

intro

First post

Jan 14, 2020

Categories