About me

Hello, I’m a first-year MSCS student at Georgia Tech specializing in Machine Learning. My research is currently focused on domain generalization by leveraging sample-to-sample relationships at the Neural Data Science Lab (NerDS) under the supervision of Prof. Eva Dyer. I am also working on assessing the synthetic-to-real generalization of vision modules for aerial imagery under the guidance of Prof. Judy Hoffman.

I completed my Bachelor’s degree in Computer Science at MIT Manipal, India in 2022, where I was fortunate enough to conduct research at the Artificial Intelligence and Robotics Lab (AIRL) in IISc Bangalore, mentored by Prof. Suresh Sundaram and Dr. Chandan Gautam. I have also conducted research under Prof. Harish Kumar J. R. at MIT, Manipal. During my undergraduate studies, I was an AI Developer at Project MANAS, where I contributed to the development of their self-driving car. I was also a member of the Research Society Manipal, where I began my research journey.

My research interests span several areas, including Computer Vision, NLP, Semi/Self-supervised Learning, Zero-Shot Learning, Domain Adaptation/Generalization, and Continual Learning. I am particularly interested in developing deep learning solutions using minimal or no supervision. My ultimate goal is to create intelligent systems that can learn from and adapt to the complex, ever-changing environments we encounter in the real world.

In my free time, I enjoy sharing my research interests and insights by streaming research paper explanations on my YouTube channel. I am currently seeking ML research positions for the summer of 2023, and I invite you to check out my CV and contact me if you are interested in collaborating. Let’s make progress together!

Publications

2022

• NeurIPS 2022 [Visted my first in-person conference in New Orleans!]
  • [Poster] Continual VQA for Disaster Response Systems at CCAI
• ICML 2022
  • [Best Paper Award 🌟] An Efficient Modern Baseline for FloodNet VQA at New In ML
• ACL 2022
  • [Oral] Transformer based ensemble for emotion detection at WASSA

2021

• NeurIPS 2021
  1. [Spotlight Paper 🌟] Semi-Supervised Classification and Segmentation on High Resolution Aerial Images at CCAI
  2. XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches at 1. [Oral] New in ML 2. [Paper] CtrlGen 3. [Paper] ML4CD 4. [Poster] DGM
  3. [Poster] A Studious Approach to Semi-Supervised Learning at ICBINB
• NAACL 2021
  • [Oral] BERT based Transformers lead the way in Extraction of Health Information from Social Media at SMM4H

Recent Updates

[ 🌟: Important | 💡: Research Paper | 🎬: YouTube Video | 📆: Miscellaneous ]

• 🌟 Attending NeurIPS 2022 at New Orleans, LA, USA. My first in-person conference!

• 💡 Oct 20, 2022: Our paper - Continual VQA for Disaster Response Systems is accepted in the Tackling Climate Change with ML workshop at NeurIPS 2022!

• 🌟 Aug 22, 2022: I begin my graduate studies at Georgia Tech. Hoping to reach new limits.

• 💡 Jun 23, 2022: Our paper - An Efficient Modern Baseline for FloodNet VQA is accepted in the New In ML workshop at ICML 2022! [🌟 Update: Best Paper Award!]

• 💡 Apr 5, 2022: Our paper - Transformer based ensemble for emotion detection is accepted in the WASSA workshop at ACL 2022!

• 🌟 Apr 4, 2022: Admitted to the MS CS program of Georgia Tech for Fall 2022!

• 💡 Mar 22, 2022: Our pre-print - Transformer based ensemble for emotion detection is made public on arxiv.

• 🎬 Feb 4, 2022: Released our 18th stream on YouTube, having Ankita Ghosh present to us her amazing paper titled IS-CAM: Integrated Score-CAM for axiomatic-based explanations.

• 🎬 Jan 30, 2022: Released our 17th stream on YouTube - a amazing paper on Open World Object Detection.

• 📆 Oct 25, 2021: Adding another feed blog answering the question - What is the most beautiful idea about Deep Learning?

• 💡 Oct 23, 2021: Our paper - Semi-Supervised Classification and Segmentation on High Resolution Aerial Images is accepted in the Tackling Climate Change with ML workshop at NeurIPS 2021! 🌟All 3 papers accepted in various workshops at NeurIPS 2021!🌟

• 💡 Oct 21, 2021: Our paper - XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches is accepted in the 1. ML for Creativity and Design, 2. Deep Generative Models and Downstream Applications, 3. CtrlGen: Controllable Generative Modeling in Language and Vision, and 4. New in ML workshop at NeurIPS 2021!

• 💡 Oct 18, 2021: Our paper - A Studious Approach to Semi-Supervised Learning is accepted in the ICBINB workshop at NeurIPS 2021!

• 📆 Oct 11, 2021: Added a Feed section to share interesting insights and ideas that I come across. (Go read it!)

• 🎬 Oct 2, 2021: Released our 16th stream on YouTube - a amazing paper on Zero-Shot Object Detection (BLC).

• 💡 Sep 18, 2021: Our pre-print - A Studious Approach to Semi-Supervised Learning is made public on arxiv.

• 🎬 Sep 12, 2021: Released our 15th stream on YouTube - very recent Google Research paper FLAN: Finetuned Language Models are Zero-Shot Learners.

• 🎬 Sep 05, 2021: Released our 14th stream on YouTube - a amazing paper on Self-Distillation.

• 📆 Sep 03, 2021: Fruitpunch AI Hyderabad chapter is made public on LinkedIn. I am leading the team as the AI Expertise Head.

• 📆 Aug 30, 2021: Published my second blog on Medium explaining a fundamental concept of Zero-Shot Learning.

• 🎬 Aug 29, 2021: Released our 13th stream on YouTube, having Shruti Jain present to us a amazing paper on Zero-Shot Object Detection.

• 💡 Aug 26, 2021: Our pre-print - XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches is made public on arxiv.