My Projects

This study project investigates the effectiveness of reasoning-enhancement techniques (e.g., advanced prompting, multi-stage finetuning, and the hybrid STaR method) on a 1-billion parameter language model, comparing its performance against a larger 3B model. The research demonstrates that with the right approach—specifically by finetuning on a mixed dataset and applying Plan-and-Solve prompting—a 1B model can significantly outperform its larger counterpart on complex reasoning tasks like GSM8K. The project concludes that the success of these techniques is highly dependent on the model's pre-training and the specific task, highlighting a path to creating smaller, yet highly capable language models.

This project implements a real-time fruit classification system using a deep learning model (MobileNetV2) and a webcam. Its key feature is an interactive feedback loop that allows users to correct misclassifications. This feedback is collected to augment the dataset, enabling the model to be retrained and continuously improved. The system also features background augmentation to enhance generalization from the Fruits-360 dataset to real-world scenarios.

This project implements a sentiment analysis pipeline for movie reviews using Word2Vec embeddings, a Noise Robust Learning technique, and a FastText-based neural network classifier. The goal is to classify movie reviews based on their text content as either positive or negative.

Achieved second place in a Kaggle competition focused on image classification. The project involved designing, training, and fine-tuning a Convolutional Neural Network (CNN) to achieve a high accuracy score (Public: 0.937, Private: 0.928).

This project simulates a 2D environment where robotic arm tools interact with various objects. The simulation includes elements like grip arms, sticks, and magnets, designed to explore intrinsic motivated learning and tool use in a controlled setting for a Machine Learning in Robotics seminar.

In a team of four, we divided the tasks of construction, programming, and testing to create a customizable, self-sufficient vacuum cleaner. I was primarily responsible for the software development, ensuring the vacuum cleaner's efficient navigation and obstacle avoidance.

Our team developed a speech control system for controlling a model factory as part of a collaborative project with PI-Informatik. I was instrumental in the development of designing the GUI, implementing the speech recognition, and the integration with the Raspberry Pi.