Neeraj Kumar – Medium

Neeraj Kumar

Neeraj Kumar

Memory Service for Agentic Applications

Language models are stateless: they do not persist information across calls. In contrast, language agents may store and maintain…

Oct 24

Memory Service for Agentic Applications

Oct 24

Neeraj Kumar

ColPali and PLAID- Part 2

PLAID architecture :

Sep 20

ColPali and PLAID- Part 2

Sep 20

Neeraj Kumar

ColPali and PLAID- Part 1

ColPali:

Sep 20

ColPali and PLAID- Part 1

Sep 20

Neeraj Kumar

Logsumexp trick and Flash attention- Part 2

GPU memory hierarchy consists of various types of memory that differ in size and speed, where smaller memory is faster. For instance, the…

Sep 5

Logsumexp trick and Flash attention- Part 2

Sep 5

Neeraj Kumar

Logsumexp trick and Flash attention- Part 1

Softmax Concept:

Sep 5

Logsumexp trick and Flash attention- Part 1

Sep 5

Neeraj Kumar

GENERATIVE LEARNING TRILEMMA

At present, generative learning frameworks are unable to meet three essential criteria simultaneously, which are often necessary for their…

Apr 8, 2023

GENERATIVE LEARNING TRILEMMA

Apr 8, 2023

Neeraj Kumar

Why Contrastive loss for unsupervised learning.

Unsupervised learning holds out the possibility that we can acquire transferable representations even in the absence of direct human…

Sep 5, 2022

Why Contrastive loss for unsupervised learning.

Sep 5, 2022

Neeraj Kumar

Understanding Variational Autoencoder

Let us consider some dataset X = {x (i)} N i=1 consisting of N i.i.d. samples of some continuous or discrete variable x. We assume that the…

Aug 10, 2021

Understanding Variational Autoencoder

Aug 10, 2021

Neeraj Kumar

Document Ranking using Bert

Document ranking is a well-known problem in the NLP domain which has prominent use cases across the various industries in extractive…

Aug 7, 2021

Document Ranking using Bert

Aug 7, 2021

Neeraj Kumar

knowledge distillation in deep learning — A mathematical perspective

Some of the problems like object detection, speech recognition are common applications that are used in many industries. Several…

Feb 21, 2021

knowledge distillation in deep learning — A mathematical perspective

Feb 21, 2021

Neeraj Kumar

Neeraj Kumar

Staff ML Scientist and PHD @ IIT Delhi, B-Tech @ IIT Kharagpur Connect on Topmate for educational consulting, mock interviews - https://topmate.io/neeraj_kumar

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams