Large Language Models (LLMs) Measuring Hallucination Evaluating hallucinations in LoRA finetuned domain adapted LLMs. Safety Awareness in LLMs Assessing the Safety Awareness in Large Language Models using generated embeddings. Graph/Transformers TransRecG Sequential Recommendation System Graph Augmented Transformer Model for Sequential Movie Recommendation. Semi-Supervised Document Classification Augmenting a DistillBERT based text classifier with Graph Neural Networks for semi-supervised document classification. Multi-Modal Sarcasm Detection Analysed audio, video, and text components of clips from TV series to detect sarcasm. Reinforcement Learning Reinforcement Learning - DQfD Analysing the optimal strategy for using expert demonstrations during online RL after bootstrapping. Adversarial ML Adversarial ML An elaborate study to determine the effects of Adversarial ML in ML/DL based Intrusion Detection Systems used in Power Plants. Continual Learning Covariate Shift and Continual Learning Investigate the problem of covariate shift in real-world datasets and propose continual learning based solutions. Federated Learning Federated Learning IDS Study the effectiveness of federated learning models to serve as IDS, and their robustness to adversaries. Algorithms Minimum Vertex Cover Analysed various algorithms including greedy, branch and bound, local search - hill climbing, and local search - simulated annealing for solving the minimum vertex cover (MVC) problem.
