Projects
Research & Projects
🎯 Reinforcement Learning (RL)

Comprehensive RL Implementation Suite: SARSA, Q-Learning, Hierarchical RL & Policy Gradients
Reinforcement Learning (CS6700), IIT Madras, 2024
Complete implementations of core RL algorithms including SARSA, Q-Learning, Dueling DQN variants, REINFORCE, and Hierarchical RL with SMDP & Intra-Option Q-Learning on various environments.

RL4LLM: Reinforcement Learning Framework for Large Language Model Fine-tuning
Advanced LLM Agents (CS294), UC Berkeley, 2025
Comprehensive toolkit implementing GRPO and other RL algorithms for fine-tuning large language models with human feedback and reward optimization.
🔤 Natural Language Processing (NLP)

Advanced Information Retrieval System with Causal NLP Integration
Natural Language Processing (CS6370), IIT Madras, 2024
Built comprehensive IR system with causal inference tools tailored for NLP tasks, featuring advanced retrieval algorithms and causality-aware language processing.
🤖 Machine Learning (ML)

Mathematical Essays on Fundamental Machine Learning Algorithms
Independent Research Series, 2023-2024
In-depth mathematical explorations and theoretical analysis of core ML algorithms including SVMs, Random Forests, Decision Trees, Naive Bayes, and Regression techniques.
🧠 Deep Learning (DL)

Complete Deep Learning Implementation Suite: FNN, CNN, and Seq2Seq Models
Deep Learning (CS6910), IIT Madras, 2024
Built neural networks from scratch including feedforward networks with multiple optimizers, CNNs with interpretability techniques, and sequence-to-sequence models with attention for transliteration tasks.
👁️ Computer Vision (CV)


YOLO-based Object Detection Suite: Aerial Imagery and Custom Datasets
Computer Vision Projects, 2023-2024
Comprehensive YOLO implementations for various applications including aerial car detection, plant disease detection, and custom object detection/segmentation pipelines.