Mohammad Aflah Khan

Summer Analyst, Goldman Sachs · Researcher, LCS2 · aflah20082@iiitd.ac.in

Hey, how's it going? I'm Aflah, a senior studying at Indraprastha Institute of Information Technology, Delhi (IIIT-D). You can usually find me engrossed in backend engineering, natural language processing (NLP), and deep learning. What really interests me is the idea of using NLP for social good. Currently I'm involved in exploring large language models, detecting hate speech, and leveraging NLP to tackle other societal challenges. It's a wild ride, and I'm excited to make a positive impact with my research.

About Me

I embarked on a thrilling journey into the world of programming during my first year at IIITD. It didn't take long for me to develop a deep affection for deep learning and NLP. Those neural networks had me captivated from the get-go, like a kid in a candy store with all the possibilities they offered.
Now, let's venture into the realm of the backend, the vital core of any robust system. I find myself captivated by the intricate machinery that orchestrates seamless operations. It's like embarking on an exhilarating puzzle-solving journey that I simply can't resist. Delving into the inner workings of databases, APIs, and server architecture provides me with a deep sense of fulfillment and accomplishment.
Speaking of UI, well, we had our differences. At first, it was a love-hate relationship. But over time, I learned to appreciate its importance and the harmony it brings to the overall user experience. Let's just say we've come to terms and found a way to coexist peacefully.
So, if you're in need of someone who's passionate about deep learning, NLP, and has a knack for exploring the backend, look no further. I'm here to bring a blend of technical expertise and a dash of humor to help you conquer your tech challenges. Let's team up and create some digital magic together!

Experience

Ongoing Roles on Top followed by sorted by End Date

Research Intern

Max Planck Institute for Software Systems: MPI SWS

I'm working under Dr Krishna Gummadi towards understanding memorization behavior alongside factual knowledge present in Large Language Model

August 2023 - Present

Open Source Contributor

Eleuther AI

Working on predicting memorization behavior in LLMs by finding which strings from the training data will be memorized. Previously worked on the Pythia model suite.

December 2022 - Present

Undergraduate Student Researcher

Laboratory of Computational Social Systems (LCS2)

Laboratory for Computational Social Systems (LCS2) is a multi-institute research group led by Dr. Tanmoy Chakraborty and Dr. Md. Shad Akhtar. Broad research interests of this group include Natural Language Processing, Social Computing, and Graph Mining. I worked on my B.Tech. Thesis which involved studying implicit hate speech and dynamics of training of large language models.

June 2021 - Present

Summer Analyst

Goldman Sachs, India

I worked in the Finance, Planning & Analysis Engineering division under the guidance of my manager Aneesh Karayil, and worked towards the comprehensive overhaul of the central hub that serves as the department's landing page. With a focus on improving efficiency and user experience, I actively participated in the development and implementation of strategic initiatives.
Additionally, I took the lead in building proof-of-concepts (POCs) based on valuable user feedback, specifically targeting the enhancement of search functionality and access experience on the web application. This involved leveraging cutting-edge technologies, collaborating with cross-functional teams, and continuously iterating based on user insights.

May 2023 - July 2023

Open Source Developer - Google Summer of Code

TensorFlow

I worked with Matthew Watson & Chen Qian towards adding support for data augmentation layers to KerasNLP a library under the Keras/TensorFlow Ecosystem which aims to build industry oriented NLP Solutions. I also contributed to several bug fixes and other utilities such as tokenizers and transformer encoder & decoder.

May 2022 - September 2022

Publications

  1. Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling Arxiv Github

    Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, Aviya Skowron, Lintang Sutawika, Oskar Van Der Wal

    Proceedings of the 40th International Conference on Machine Learning (ICML) [2023]

  2. Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization Arxiv Github

    Sarah Masud, Manjot Bedi, Mohammad Aflah Khan, Md Shad Akhtar, Tanmoy Chakraborty

    Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining [2022]

  3. The Art of Embedding Fusion: Optimizing Hate Speech Detection Arxiv Github

    Mohammad Aflah Khan, Neemesh Yadav, Mohit Jain & Sanyam Goyal

    The First Tiny Papers Track at Eleventh International Conference on Learning Representations (ICLR) [2023]

  4. Beyond Negativity: Re-Analysis and Follow-Up Experiments on Hope Speech Detection Arxiv Github

    Neemesh Yadav, Mohammad Aflah Khan, Diksha Sethi & Raghav Sahni

    The First Tiny Papers Track at Eleventh International Conference on Learning Representations (ICLR) [2023]

Education

Indraprastha Institute of Information Technology, Delhi

B.Tech Computer Science Engineering

GPA: 9.59/10

January, 2021 - Present

LBS School

Twelfth grade

Percentage: 95%

2018 - 2020

Banyan Tree School

Tenth grade

Percentage: 95.8%

2006 - 2018

Other Work

@ Conferences
  • Organizer - Fire HASOC Task 3: Identification of Tokens Contributing to Explicit Hate in Text by Span Detection
  • Reviewer - The 7th Workshop on Online Abuse and Harms (WOAH) [Part of ACL 2023]
  • Volunteer - 19th International Conference on Natural Language Processing (ICON)
Talks
  • @ MPI-SWS - On Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
  • @ Goldman Sachs Internal NLP Paper Reading Club - On Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
@ University
  • Teaching Assistant - Machine Learning under Dr. Anubha Gupta
  • Teaching Assistant - Data Structures and Algorithms under Dr. Piyus Kedia
  • Research Event Organizing Team Lead - Esya 2023 - IIITD's Annual Technical Festival
  • Coordinator - BioBytes: The Computational Biology and Data Science Club at IIITD
  • Coordinator & Core Member - Byld: The Development Club at IIITD
  • Mentor - Undergraduate Research Club

Interests

Research Interests
  • Deep Learning
  • Natural Language Processing for Social Good
  • Training Dynamics of Large Language Models
  • Model Probing
  • Social Media Analysis
Programming Languages & Tools

Awards, Achievements & Certifications

  • Dean's List Award for Academic Excellence, IIIT Delhi, 2023
  • Dean's List for Innovation in Research and Development, IIIT Delhi, 2023
  • Dean's List Award for Academic Excellence, IIIT Delhi, 2022
  • Selected for Amazon ML Summer School 2022
  • Finalist Anveshan Hackathon
  • 2 nd Place - Byld Hackathon
  • 2 nd Place in Association for Computing Machinery (ACM) IIITD Induction Ideathon
  • JEE Mains : Paper 2 – AIR 491
  • JEE Mains : Paper 1 – Top .66 Percentile
  • Undergraduate Entrance Examination (UGEE): AIR 130