Currently working on large language models (LLMs), generative AI, and agentic frameworks to push the boundaries of AI capabilities.

1. Survey Summarization, Theme Identification, and RAG: Developed an LLM-based summarization tool for user survey responses, which generates a summary and identifies top themes and top negative items. Developed a retrieval-augmented generation framework to gather deeper and specific insights for the same. Also developed a POC to create Knowledge graph-based RAG(retrieval augmented generation) system to improve retrieval time.2. App placement using Recommender systems: Experimented and deployed Multi-armed bandit-based recommender systems to order components and contents(video collections on Discover page) with a solution to handle the cold start problem.3. Growers and Reducers: Created a modelling ensemble to identify customers that were more likely to increase their assets(growers) and likely to take out their assets(reducers) in the next year by analyzing profile and interaction data(clicks, calls, etc) so that business can intercept at the right time and target the right customers.4. Explainable AI Library: Created an in-house library used by data scientists across AICOE that generates HTML reports(which includes performance reports, explainability, drift, and counterfactual analysis) that support classification(binary and multi-class) and regression use-cases for Torch, TensorFlow, and scikit-learn models.5. Lead Generation Framework: Developed a generic Deep learning framework that generates leads as per the given KPI criteria and rank orders the leads based on customizable metrics users provide. Created the featurization layer by creating time interval weighted embeddings followed by a modeling layer that takes sequential features as input.

1. Question Generation: Developed a system to generate MCQ questions, True or False questions, and Descriptive questions (models based on T5 and GPT2) from a given text along with an automated validation model using a QA model(T5 based) to answer the generated questions to filter out unsatisfactory questions.2. Video Summarization: Developed a model for video summarization(in text) to find context for ad placement. Bi-modal Transformer is used for Multi-modal Dense Video Captioning by applying the model in a bidirectional manner through the video.3. Ad revenue Maximization: Generating a week’s schedule for custom advertisement(region-based) so that the given contract does not fail (weekly, monthly, and yearly contracts) based on the number of impressions and generate maximum profit for the broadcaster. Used a probability-based constraint formulation and Reinforcement learning model to generate future schedule for advertisement deal.

1. Worked on Time-Series Data (Sensor data):A. Imputation of missing data: Compared GAIN - Missing Data Imputation using Generative Adversarial Nets(http://proceedings.mlr.press/v80/yoon18a/yoon18a.pdf) and Multi-directional Recurrent Neural Networks(https://arxiv.org/abs/1711.08742) for missing real-world sensor data.B. Forecasting for sensor data:Performed Multivariate Time series forecasting using Temporal pattern attention for multivariate time series forecasting(https://link.springer.com/article/10.1007/s10994-019-05815-0) and GRU-D(https://www.nature.com/articles/s41598-018-24271-9)2. Adaptive Traffic Signal Control using Reinforcement Learning:Worked on dynamic traffic signal control using Deep RL as part of M.Tech thesis.