Home
Home
Hi ! This is your friendly neighborhood Yash Srivastava. This is the homepage of my GitHub Pages website. This page will serve as a navigator for some of my most loved and cherished projects. While the good stuff is about to come, I hope what I love doing doesn’t get unnoticed.
How to contact me? ☎️
It’s pretty easy. Just hit me up on Twitter, LinkedIn or Mail. I’ll get back to you pretty soon, if I’m not busy.
About Me 🙇♂️:
Well, where to start ? I am Yashovardhan Srivastava(quite a mouthful - Yash is good) an undergraduate engineering student in National Institute of Technology, Warangal. From a young age, I have been fascinated by computers. As I grew older, this fascination turned into crush and crush turned into love - and from that moment, I haven’t looked back. I believe opensource projects has played a significant role in that. They made me fall in love with research, development and much more. Since now I believe I am capable enough to produce some original work, I want to be a part of this beautiful journey, in which all of you play an important role,
All of projects are a result of extreme dedication, meticulousness, and hardwork. Most of them are just random thoughts that I once had, and thought-What If ? They do not need recognition, they need discussions. I might have reached a dead end with some of those - but their cycle isn’t complete. I have plenty of projects in pipeline, which I hope will be just beautiful as the ones which are already there.
Experience 👷 :
-
Research Intern, Indian Institute of Technology-Banaras Hindi University: Worked under Prof. A.K. Singh on a research project on developing a machine translation system for low resource languages such as Hindi, Bhojpuri, Magahi, Maithali.
-
Executive Member, Research and Development Cell(National Institute of Technolgy, Warangal): Part of Undergraduate Research Association team of NIT Warangal which actively takes part in educating and fostering academic growth among undergraduate students.
-
Executive Member, Big Data Analytics and Consulting Cell(National Institute of Technolgy, Warangal) : Part of a dynamic team that has collaborated in several of the student club events such as Kaggle, Pytorch Workshop and Case study competitions, among other initiatives to develop a community of machine learning enthusiasts in NIT Warangal.
Proficiency and Interests ⭐ :
-
Research Interests : Natural Language Processing, Generative AI.
-
Learning : Artificial Intelligence Research, Data Science and Natural Language Processing.
-
Languages Familiarity : Spoken(Hindi, English, Very Basic Spanish), Programming(C, C++,Python, R, Julia)
-
Developer Tools: Github, Excel
-
Frameworks: Tensorflow, Pytorch, Keras
Achievements 🥇
-
Honour : Received Kaggle Notebook and Dataset Expert with an overall rank of 699 and 573 respectively.
-
Personal Interests : Football, badminton, avid reader, philosophy connoisseur and writing.
Career Goals 🥅:
Wooh. That’s a tough one. There are many things that I like and I feel it is difficult to commit to something. But, there comes a time when we need commit to a field. Balance between exploration and exploitation needs to be made-and for me, that comes from working on research problems. I want to study more, to do things that make me happy.
The place where I come from, this is NOT a trend. We are hard-working, talented people-but we realise very later in life what matters to us. True satisfaction comes from happiness-and that is the purpose of life. I choose to take the road not taken.
I see myself as a research scientist in the near future-specifically in the field of AI, but let’s see where life takes me.
Reseach Papers I Love 📎
In no particular order, I am listing doen some really awesome reserach papers that in one way or other have helped me think outside of the box.
-
The Hardware Lottery : Probably one of my favorite papers till day. The way Sara Hookor explained how AI/ML research should proceed, and how is it going till now is a real eye opener. Highly highly recommend if you want to look at the bigger picture of AI research.
-
Building Machines that Learn and Think for Themselves - Commentary on Lake, Ullman, Tenenbaum, and Gershman : Not exactly a paper, but this really forced me to think about some things. Definitely recommend this for casual reading.
-
A Two-Systems Perspective for Computational Thinking : This is one of the first papers that I read and it blew my mind. Inspired by the Kahneman’s Two Systems Approach of Thinking(Thinking Fast and Slow), this papers presents the cognitive models against which computational thinking can be analyzed and evaluated.
-
Attention is all you need : It’s everyone’s favourite research paper-and mine too. This was the paper that introduced transformers, and the rest is history. This paper taught me how to communicate your research and how to present your work.
-
Recsim-A configurable platform for recommender systems : This opened my eyes. I was in awe when I found out we can use reinforcement learning in recommendation setting. I even emailed the author of the paper thanking and asking him what he thinks whether this will be used in future recommendation systems. Google Research for the WIN.
-
Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation: This was a really well written and structured paper, which I was able to understand easily, and even used for testing in my internship project.
Projects 🧰
Here I’ll pin some of my favorite projects, more on the research 👨🔬 side(Feel free to critique me on this(and try to contribute if possible :) ) :
-
Secure BPE (Work in Progress) : A modified, secure version of Byte Pair Encoding algorithm.
-
Collaborative Debating (Work in Progress) : A hacky implementation of the paper “Improving Factuality and Reasoning in Language Models through Multiagent Debate”.
-
NEAT-JAX (Work in Progress) : An implementation of Neuroevolution of Augmented Topologies Algorithm in JAX which is compatible with EvoJAX.
-
Nexus Theory : Can we really trust our human-ness for the messages that we send into the cosmos? Nexus theory is a gamified version to understand machine learning interpretability using Large Language Models.
-
Elixr : Elixr an autograd library using Complex Numbers similar to Pytorch.
-
Attention Free Revolution : Developed Leviathan architectures, and alternate to Transformer architecture using a modified attention scores, taking inspiration from signal processing.
-
P-GLAm : P-GLAm is a random thought experiment on Infinite Monkey Theorem. In this, I developed a GPT-2 inspired Large Language Model which aims to test the arithmetic correctness.
Here I’ll pin some of my favorite projects, more on the development 💻 side. Feedback is always appreciated for projects like these.:
-
Synapse : Synapse is hackernews-type platform that can be used by any community as a forum. Tried making this for my college, but need more inspiration.
-
Pandora : Pandora is domain agnostic framework for case study generation and solving.
-
Verizon : A Git like version control system, from scratch, in Python, spelled out.
-
YeetCode : YeetCode is a sassy version of Python made for all GenZ people. The aim is to create a new programming language which is bussin’.
-
Blaze : Developed a RAG(Retrieval Augmentation Generation) system by using Cohere LLM and Metaphor as a part of recruitement process for Metaphor, which is made using Langchain, Chainlit and deployed on Huggingface.
-
CodeSmith : Developed a ChatGPT-inspired chatbot trained on a Python programming problems on custom created dataset, made using Langchain, and deployed on Huggingface.
-
Alzhemist : One of the first projects that got me in to the world of Attention. A Deep Learning Model to see which classifies Brain MRI on the basis of the dementia (AD). The images are classified as follows - Mildly Demented, Moderate Demented, Non Demented, Very Mild Demented.
-
Maxwell : One of my most priced possession. Maxwell is twisted take on One Shot Frequency Dominant Neighborhood Search. The scheme provided in the paper is a bit modified to generate fingerprint for an image.
-
SpiceyDicey : SpicyDicey is a end to end machine learning project that aims to predicts the number that appears on a dice. All of the work in collecting the data and editing the images has been done individually and from scratch.
Here are some of the awesome notebooks 📓 I’ve made on Kaggle(I’m a 2x Kaggle Expert also !!) :
-
FC Barcelona is Back! : Analyzed FC Barcelona’s LaLiga performance in the 2022-23 season on Kaggle, achieving Bronze Medal and 200+ views apart from receiving recognition from Kaggle.
-
BART Pretrainig from Scratch : Developed a BART model from scratch using Huggingface on Shakespere dataset in a notebook on Kaggle, which received a silver medal and 600+ views.
-
Tensorflow Recommendation System : Demonstrated on using Tensorflow Recommendation System in a Kaggle notebook that gained bronze medal, and 500+ views.
Much is yet to come, so keep an 👀