Hi, there! This is Avani Gupta. Welcome to my web-page.

I am working as a Research Associate at G42, Abu Dhabi, UAE. I did my masters under Prof. P J Narayanan in ML interpretability and Computer Vision. I specifically worked on post-hoc model evaluation as well as ante-hoc model training using human centered concepts. I completed my B.Tech in Computer Science from IIIT Hyderabad in 2021.

Other problems I have worked on: Reinforcement Learning in Business Process Automations (in my Internship at IBM Research, 2021); loose clothing in 3D human body in Independent Study with Prof. Avinash Sharma. I have also worked in NLP problems like scientific papers summarization, NER, Fake News Detection etc. I am proficient in Explainable AI, Deep Learning, Computer Vision, Reinforcement Learning, Natural Language Processing, web-dev, app-dev with demonstrated history of work. I am keen on learning new things and working on problems where I can make an impact. For more details please find my CV.

News

• Sepetember 22, 2023: Paper “Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement​” accepted in Neurips 2023!
• September 30, 2023: Successfully defended my Master’s thesis.
• September 12, 2023: Paper “Predicting Business Process Events in Presence of Anomalous IT Events” accepted in CODS-COMAD, 2024.
• December 10, 2022: Received the Oral and Best Paper Award for the paper titled “Interpreting Intrinsic Image Decomposition using Concept Activations” in ICVGIP, 2022.

Work experience

• March 2023 - Present: Research Associate

  • G42 Healthcare | Abu Dhabi, UAE

    Research project on building foundation model on Electronic Health Records (EHR) data. Will help in patient risk identification (chances of developing a certain diseases) and thus proactive diagnosis and treatment of diseases via personalized medicine.

• May 2021- August 2021: Research Intern

  • IBM Research | Bangalore, India

    Research project on building system for Goal Oriented Next Best Action Prediction in Business Processes using Deep Reinforcement Learning. Submitted Paper and US. patent (currently in last stage after signing)

• May 2020 - Sep 2023: Researcher

  • CVIT, IIIT Hyderabad

    Working on ML Interpretability applied in Computer Vision and Graphics under Professor P.J. Narayan. Worked in Neural rendering, ray tracing and 3D reconstruction of objects and scenes. Studied NeRF(Neural Radiance fields) line of work. Implemented and reproduced results of several papers in neural rendering.

• Jan 2020- Jan 2021: Independent Study and Researcher
  • CVIT, IIIT Hyderabad Independent Study under Professor Avinash Sharma. Worked on Realistic Human Body Reconstructions and Digital Humans. Working on temporal stability over 3D.
• June - July 2020: Crew Member and Mentee

  • Microsoft | Mars Colonization Program

    Worked on Automated mars rover web game. Developed the game in Agent Centric way. Used shortest path-finding algorithms like Collaborative Learning Agents, A, Dijkstra, Best first search, IDA, Jump-Point Finders and their bi-directional forms to make the AI rover navigate the mars. Applied Travelling salesmen algorithm and made the AI agent render multiple destinations in the shortest path avoiding all obstacles. Built using Object Oriented programming cocepts. Used Jquery, Rafael.js, and HTML, CSS and javascript.

• Jan 2020- May 2020: Applied Deep Learning and Software Engineering Intern

  • Scrapshut | Hyderabad

    Developed a web-app using Angular and Django where users can check genuineness of any site by providing it’s URL and get other user’s reviews along with predictions by DL model. Trained various Deep Learning models like LSTM, XGBoost and CNN on three datasets- Kaggle fake news net, Kaggle: getting real about fake news and Kaggle fake news Prediction. Also trained a passive aggressive classifier (online learning algorithm) and incorporated user-rated scraped reviews for real time prediction.

• Nov 2019- Jan 2020: RL Researcher

  • Robotics Research Centre

    Worked on several SOTA RL algorithms in Robotics and Control under Professor Madhav Krishna. Implemented algorithms from Monte-Carlo to PPO, TRPO, DDPG etc from scratch. Also used open AI gym, RLib, Vowpall wabbit and engines like Gazebo, Mojuco for control in robotics.