About Me
Hello! I'm a current Master's student in Computer Science at UT Dallas. I began my journey in tech building websites, but my curiosity soon led me to the fields of AI and Machine Learning. Today, my goal is to build systems with the ability to understand language and interpret the visual world.
I am focused on the intersection of Computer Vision and Natural Language Processing. I enjoy working on a range of projects, from fine-tuning large language models to creating systems that process images and audio. I value clean, well-structured code and hold a firm belief in learning by building.
Research Interests
I am fascinated by the challenge of creating machines that can perceive and reason about the world in a holistic way, much like humans do. My primary research interest, therefore, lies in Multimodal Machine Learning, which integrates different data types like vision, language, and audio.
My previous work with audio data, such as in "Depression Detection through Speech Analysis" and time-series classification, has given me a solid foundation. I am now eager to expand upon this by exploring how visual and linguistic information can be combined to create more robust and context-aware AI systems
As a thesis-track Master's student, I am actively seeking opportunities to contribute to ongoing lab projects in these areas. I am a dedicated and fast learner, eager to engage with challenging research questions and support the lab's goals through meaningful and consistent work.
Publications
AI-Driven Gait Classification Using Portable Wearable Sensors: Advances and Case Study
Sonam Nahar, Preet Sojitra, and Vineet Vashista
Chapter in "Design and Control of Rehabilitation Robots", Springer, July 2025.
Experience
AI & NLP Research Intern @ 9series Pvt Ltd
Feb 2025 - Jun 2025
- Engineered an end-to-end computer vision system using YOLOv8 to detect and classify counterfeit luxury goods, achieving over 95% classification accuracy on real-world data.
- Developed and deployed the system's backend with FastAPI on AWS, integrating it directly into the client's Shopify store and e-commerce platform.
- Architected and implemented a scalable inference pipeline using Celery and Redis to manage high-volume asynchronous requests, significantly reducing API response latency.
- Utilized explainable AI techniques like Grad-CAM to validate model behavior and ensure decision transparency.
- Led the fine-tuning of Large Language Models (Llama 3, Gemma) to automate the classification of customer chargeback disputes.
- Generated a synthetic, multi-turn conversational dataset to train the models to identify valid disputes by interacting with customers.
- Implemented LoRA-based fine-tuning using Unsloth and Hugging Face, successfully teaching the model to recognize dispute categories and adopt a specific conversational tone.
Research Intern @ HCR Lab, IIT Gandhinagar
May 2024 - Oct 2024
- Conducted a 5-month research project on AI-driven gait analysis using wearable sensor data, managing the full project lifecycle from participant data collection to final analysis.
- Developed and benchmarked deep learning models (GRUs and 1D-CNNs) for time-series classification of IMU sensor data to identify gait patterns.
- This work culminated in a book chapter published by Springer (see Publications section).
Featured Projects
Depression Detection through Speech Analysis
An end-to-end research project to detect depression from speech recordings using the DAIC-WOZ dataset. Systematically evaluated a range of models, from classic CNNs (VGGNet, ResNet) to Vision Transformers (ViT), on spectrograms and raw audio data.
Accomplishment: Gained experience in the full research pipeline, including feature engineering for audio, comparative model benchmarking, and handling class imbalance.
imgcv: A Image Processing Library from Scratch
Developed and published a Python package on PyPI that re-implements core image processing OpenCV functions from the ground up using only NumPy. The goal was to build a deep, fundamental understanding of how computer vision and image processing algorithms work under the hood.
Accomplishment: Solidified my understanding of algorithms for filtering, color space manipulation, morphological operations, and edge detection.
nanoGPT: Building a Transformer from Scratch
Implemented a decoder-only GPT-style language model from scratch in PyTorch, training it to generate text in the style of Shakespeare. This project was a deep dive into the fundamental mechanics of the Transformer architecture.
Accomplishment: Gained a code-level understanding of self-attention, which I am now extending to train a similar model on the more complex Sanskrit language.