Anugunj Naman

I am a graduate student at Purdue University with a focus on machine learning. My prior role was as an Software Engineer at Elevance Health, where I collaborated with the Responsible AI and XAI Team on enhancing fairness, explainability, and addressing data drift in machine learning applications.

I earned a Bachelor of Technology degree in Computer Science and Engineering from the Indian Institute of Information Technology, Guwahati in 2022.

Previously, I served as a Research Intern at NVIDIA, focusing on speech recognition, meta-learning, and few-shot learning. Additionally, I was a Research Intern at the AI-ML-NLP Lab at IIT Patna, working on multimodal learning.

I have contributed to the open-source HuggingFace Transformers library, including two vision transformers: Microsoft's CvT: Introducing Convolutions to Vision Transformers and Meta's LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

I have a keen interest in applied machine learning, particularly in the area of multimodal learning. I am also dedicated to developing efficient and robust machine learning models. Over the past year, I have focused on developing sampling methods for large language models (LLMs).

Speech to Text conversion of different Indic Languages using Meta Learning.

Author profiling for gender prediction of anonymous twitter users.

Speech Emotion Recognition of different languages using Meta Learning.

A Deep Learning Solution for Automation of Pavement Condition Index.

A compact, concise, and customizable deep learning library. This library currently supports deep learning models for computer vision. Glasses is a model toolbox to make it easier for everybody to use, learn and share deep learning models.

Template from Jon Barron's website.