Research

Research Areas

• Transformers and Large Language Models (LLMs)

• Agentic AI and AI Agents

• Generative AI (GenAI) for Vision, Language, and Speech

• Multi-Modal Learning and Multi-Modal GenAI

• State Space Models (Mamba)

• Time Series Forecasting and Anomaly Detection

• Responsible AI (Explainable AI, Fairness, Privacy)

• Visual Question Answering

• Visual Question Generation

• Visual Dialog

• Image Captioning

Presentation

• Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction[PPT]

• Hierarchical Question-Image Co-Attention for Visual Question Answering[PPT]

• Deep learning library[PPT]

Deep Learning Library

• PyTorch

• TensorFlow

• Torch

• Hugging Face Transformers

Research Courses Material

• Linear Algebra

• Statistical Signal Processing

• Optimization

• Machine Learning and AI

• Information Theory

• Computer Vision

• Natural Language Processing

• Speech Signal Processing

• Audio and Misic Processing

• Video Signal Processing