May '23 - Jul '23

ScaleViz: Scaling Visualization Recommendation Models on Large Data
Enable state of the art Vis-Rec models to achieve up to 10X speedup in time-to-visualize on large real-world datasets.
Paper

Mar '22 - Jan '23

An illustration of a quasi-interpolation driven technique for feedback synthesis
Guide: Prof. Debasish Chatterjee
A method to approximate feedback maps for Linear Quadratic Regulator controllers
Code Paper

Aug '23 - Present

Composed Image Retrieval
Guide: Prof. Biplab Banerjee, CSRE, IIT Bombay
Composed Image Retrieval (CIR) is the task involves retrieving images from a large database based on a query composed of multiple elements, such as text, images, and sketches. The goal is to develop algorithms that can understand and combine multiple sources of information to accurately retrieve images that match the query, extending the user’s expression ability.
Code

Jan '24 - Present

Research and Development Project, Koita Centre for Digital Health
Guide: Dr. Kshitij Jadhav, KCDH, IIT Bombay
This involves fine-tuning the SAM model using Low Rank Approximation to segment pleural effusion using few-shot learning. This is further going to be consolidated into an LLM to bring interpretability to medical diagnosis systems
Code

May '23 - Aug '23

Scalability of Approximate Visualizations
Automated visualization recommendation (Vis-Rec) models help users to derive crucial insights from new datasets. Typically, such automated Vis-Rec models first calculate a large number of statistics from the datasets and then use machine-learning models to score or classify multiple visualizations choices to recommend the most effective ones, as per the statistics.

Summer '22

International Aerial Robotics Competition Mission 9
Developed CV pipelines to track mast in a moving environment
Code Demo

March '22

DRDO’s UAV-Guided UGV Navigation Challenge
Used UAV feed to navigate UGV through snowy environment
Code

Fall '21

Foundations of Intelligent Learning Agents
Collection of basic Reinforcement Learning algorithms from scratch
Code

Fall '22

Visual Explanation for CNNs
Techniques to visualize outputs of CNNs
Code