Saarang Arora
AI Engineer | Researcher | Author
I build intelligent systems and explore the frontiers of machine learning. Passionate about turning data into actionable insights and creating impactful solutions.
AI Engineer | Researcher | Author
I build intelligent systems and explore the frontiers of machine learning. Passionate about turning data into actionable insights and creating impactful solutions.
Implemented news classification models using Recurrent Neural Networks and Long Short-Term Memory networks for accurate text categorization.
Advanced news classification using Gated Recurrent Units and Bi-Directional LSTMs to capture context from both directions.
Built an efficient image similarity search engine using Facebook AI Similarity Search (FAISS) and ResNet50 for feature extraction.
Implemented a Transformer model from scratch for English-to-French machine translation, understanding the core attention mechanisms.
Developed a Deep Learning model using CNNs to detect pneumonia from chest X-ray images with high accuracy.
An innovative application involving art recognition or processing. (Description based on title, customizable).
Topic: Running LLM based chatbots on edge and low compute environments
Abstract: Deploying conversational AI systems on resource-constrained edge computing devices requires sophisticated optimization techniques to ensure computational efficiency without compromising performance quality. This paper presents a comprehensive study on the optimization and deployment of an end-to-end conversational AI pipeline - comprising Whisper automatic speech recognition (ASR), a 3-billion parameter Llama-3 large language model (LLM) and lightweight text-to-speech (TTS) - running entirely on a Raspberry Pi module.
I'm always open to discussing new projects, creative ideas, or opportunities to be part of your visions.
Say Hello