Indian Institute of Information Technology

Design and Manufacturing, Kurnool

Department of Computer Science and Engineering

Generative AI &
Large Language Models

Learn Transformers, GPT, Large Language Models, Prompt Engineering, Retrieval-Augmented Generation (RAG), Agentic AI, Vision Language Models, and Responsible AI.

Course Code

AD470

Credits

3-0-3

Instructor

Dr. Alapan Kuila

Explore Course

About the Course

Course Objectives

  • Understand Generative AI fundamentals.
  • Learn Transformer architecture.
  • Build RAG systems.
  • Fine-tune LLMs.
  • Study AI Safety and Ethics.

Prerequisites

  • Machine Learning
  • Python Programming
  • Deep Learning
  • Linear Algebra
  • Probability
  • Basic NLP

Learning Outcomes

  • Understand Transformers
  • Fine-tune LLMs
  • Develop RAG Systems
  • Vision Language Models
  • Responsible AI

Course Modules

01

Foundations of NLP

NLP Fundamentals, Language Models, Deep Learning, PyTorch, Word2Vec, GloVe, FastText and Tokenization.

02

Neural Language Models

RNN, LSTM, GRU, Seq2Seq, Attention, Beam Search and Decoding Strategies.

03

Transformers

Self Attention, BERT, GPT, T5, Llama, Mistral, Gemini, Hugging Face.

04

Prompt Engineering

Prompt Engineering, Instruction Tuning, RLHF, DPO, LoRA, QLoRA, Planning and Reasoning.

05

RAG & Agentic AI

Retrieval Augmented Generation, Vector Databases, GraphRAG, Knowledge Graphs, Tool Calling, AI Agents.

06

Vision Language Models

CLIP, BLIP, LLaVA, Qwen-VL, Diffusion Models, AI Safety, Ethics, Efficient Inference.

14-Week Course Timeline

Week 1

Introduction to Generative AI & Natural Language Processing

Week 2

Language Models and Probability Foundations

Week 3

Deep Learning Fundamentals using PyTorch

Week 4

RNN, LSTM, GRU and Sequence Models

Week 5

Attention Mechanism and Sequence-to-Sequence Models

Week 6

Transformer Architecture & Self Attention

Week 7

BERT, GPT, T5, Llama and Foundation Models

Week 8

Prompt Engineering, LoRA and QLoRA

Week 9

RLHF, Alignment and Instruction Tuning

Week 10

Retrieval Augmented Generation (RAG)

Week 11

Knowledge Graphs and Agentic AI

Week 12

Vision Language Models & Diffusion Models

Week 13

Evaluation, Hallucinations, AI Safety & Ethics

Week 14

Semester Project Presentation & Course Revision

Course Materials

📚 Week 1

Introduction to Generative AI

Evaluation Scheme

End Semester Exam

50%

Main written examination covering the complete syllabus.

Semester Project

15%

Complete implementation, experiments and final demonstration.

Mid Semester Exam

30%

Evaluation of the first half of the course.

Assignments & Labs

5%

Programming assignments and laboratory exercises.

Paper Presentation

Extra Credits

Presentation of a recent research paper in Generative AI.

Semester Project Roadmap

01

Problem Definition

Literature Survey
Dataset Collection

4 Marks
02

Baseline Model

Implementation
Initial Results

3 Marks
03

Proposed Method

Experiments
Evaluation

5 Marks
04

Final Submission

GitHub
Report
Poster
Demo

8 Marks

Books & References

Foundations of Large Language Models

Tong Xiao & Jingbo Zhu

Speech and Language Processing

Jurafsky & Martin

Natural Language Processing

Jacob Eisenstein

Research Papers

ACL • EMNLP • NeurIPS • ICML • ICLR

Academic Integrity & AI Usage Policy

Academic Integrity

Technical discussions, knowledge sharing, and brainstorming with classmates are encouraged. However, every submission must reflect your own understanding and your team's original work.

Copying code, reports, figures, experimental results, or text from another student, group, online source, or AI system without proper acknowledgement constitutes academic misconduct.

Any collaboration with another student, group, or external source must be explicitly acknowledged. Violations may result in negative marking, course deregistration, and disciplinary action as per institute policy.


AI Usage Policy

LLMs such as ChatGPT, Claude, Gemini, and Copilot are treated as learning companions. They may be used to understand concepts, learn syntax, debug code, brainstorm ideas, or improve technical writing.

Students must not copy AI-generated code or text into assignments or projects without understanding and proper disclosure.

Every submission must include an AI Usage Statement describing how AI tools were used. Failure to disclose AI assistance or inability to explain submitted work during evaluation may be treated as academic misconduct.

Failure to follow these rules will be considered cheating and dealt with according to the institute's academic integrity guidelines.