Resource Library
M.Sc. Program
Semester: 4051
Course Materials & Downloads
Searchable hub for lecture slide PDFs, landmark literature, interactive Jupyter notebooks, and evaluation datasets.
S1 • Foundations
PDF
History of NLP & Modern LLM Landscape
CMU Ref: Lecture 1 (Intro & Fundamentals)
Stanford Ref: Week 1 Tue (History of NLP)
S2 • Foundations
PDF
Word Vectors & Learned Representations
CMU Ref: Lecture 2 (Learned Reps)
Stanford Ref: Week 1 Thu (Word Vectors)
S3 • Foundations
PDF
Backpropagation & Neural Computing for NLP
Stanford Ref: Week 2 Tue (Backpropagation & NN)
S4 • Foundations
PDF
Autoregressive Language Modeling
CMU Ref: Lecture 3 (Autoregressive LM)
Stanford Ref: Week 2 Thu (LMs & RNNs I)
S5 • Architectures
PDF
Recurrent Neural Networks (RNN, LSTM, GRU)
CMU Ref: Lecture 4 (RNNs)
Stanford Ref: Week 2 Thu (LMs & RNNs II)
S6 • Architectures
PDF
Attention Mechanisms & The Transformer Architecture
CMU Ref: Lecture 5 (Attention & Transformers)
Stanford Ref: Week 3 Tue (Transformers)
S7 • Architectures
PDF
Tokenization & Multilingual Language Modeling
Stanford Ref: Week 7 Thu (Tokenization)
S8 • Pretraining
PDF
LLM Pretraining: Data, Systems & Architectures
CMU Ref: Lecture 6 (Pretraining)
Stanford Ref: Week 4 Tue (Pretraining)
S9 • Adaptation
PDF
Scaling Laws, In-Context Learning & Prompting
CMU Ref: Lecture 7 (Scaling Laws & ICL)
Stanford Ref: Week 5 Tue (Efficient Adaptation)
S10 • Adaptation
PDF
Fine-Tuning, Parameter-Efficient Adaptation & LoRA
CMU Ref: Lecture 8 (Fine-tuning & Distillation)
Stanford Ref: Week 9 Thu (Tinker & LoRA)
S11 • Alignment
PDF
Reinforcement Learning Fundamentals in NLP
CMU Ref: Lecture 16 (RL Fundamentals)
S12 • Alignment
PDF
Post-Training with Human Preferences: RLHF & DPO
CMU Ref: Lecture 17 (RL Applications)
Stanford Ref: Week 4 Thu (Post-training)
S13 • Systems
PDF
Model Quantization & Distributed Training Systems
CMU Ref: Lecture 19 (Quantization) + 20 (Parallelism)
S14 • Architectures
PDF
Mixture of Experts (MoE) & Long-Context Scaling
CMU Ref: Lecture 21 (MoE) + 22 (Sequence Length)
S15 • Reasoning
PDF
Decoding Algorithms, Chain-of-Thought & Test-Time Scaling
CMU Ref: Lecture 9 (Decoding) + 23 (Test-Time Scaling)
Stanford Ref: Week 6 Thu & Week 7 Tue (Reasoning)
S16 • RAG & Agents
PDF
Retrieval-Augmented Generation (RAG)
CMU Ref: Lecture 10 (Retrieval & RAG)
Stanford Ref: Week 5 Thu (RAG Part 1)
S17 • RAG & Agents
PDF
Language Model-Based Agents & Tool Use
CMU Ref: Lecture 18 (LM Agents)
Stanford Ref: Week 5 Thu (Agents Part 2)
S18 • Evaluation
PDF
Evaluation Techniques, Benchmarking & Leaderboards
CMU Ref: Lecture 13 (Evaluation)
Stanford Ref: Week 6 Tue (Benchmarking)
S19 • Ethics & Safety
PDF
Interpretability, Safety, Bias & Privacy in LLMs
Stanford Ref: Week 8 Tue (Interpretability) + Thu (Risks)
S20 • Multimodal
PDF
Multimodal LLMs: Vision-Language Models (VLM)
CMU Ref: Lecture 11 & 12 (Multimodal I & II)
Stanford Ref: Week 9 Tue (Multimodality)
S21 • Generative
PDF
Diffusion Models & Flow Matching for NLP
CMU Ref: Lecture 15 (Diffusion and Flows)
S22 • Advanced
PDF
Graph Neural Networks for Natural Language Processing
S23 • Research
PDF
Research Skills, Experimental Design & Future Frontiers
CMU Ref: Lecture 14 (Research Skills)
Stanford Ref: Week 10 Tue (Open Questions 2026)
RLHF
Paper
Training language models to follow instructions with human feedback
Ouyang et al. (InstructGPT, 2022)
DPO
Paper
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov et al. (2023)
RAG
Paper
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis et al. (2020)
Reasoning
Paper
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei et al. (2022)
MoE
Paper
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Shazeer et al. (2017)
GNN
Paper
Graph Neural Networks for Natural Language Processing: A Survey
Wu et al. (2021)
Foundations
Colab / PyTorch
Lab 1: Implementing Word2Vec & CBOW from Scratch (PyTorch)
Hands-on coding tutorial with PyTorch and Hugging Face Transformers.
Transformers
Colab / PyTorch
Lab 2: Scaled Dot-Product & Multi-Head Self-Attention Transformer
Hands-on coding tutorial with PyTorch and Hugging Face Transformers.
Fine-Tuning
Colab / PyTorch
Lab 3: Parameter-Efficient Fine-Tuning with LoRA & QLoRA
Hands-on coding tutorial with PyTorch and Hugging Face Transformers.
RAG & Agents
Colab / PyTorch
Lab 4: Building an Agentic Dense-Retrieval RAG Pipeline with LangChain
Hands-on coding tutorial with PyTorch and Hugging Face Transformers.
Alignment
Colab / PyTorch
Lab 5: Post-Training Alignment with DPO (Direct Preference Optimization)
Hands-on coding tutorial with PyTorch and Hugging Face Transformers.
Benchmark / Dataset
PersianNLP Benchmark Suite (PQuAD, Digikala Reviews, ParsNLU)
Standard datasets for Persian reading comprehension, sentiment, and NLI.
Benchmark / Dataset
MMLU & MMLU-Pro
Massive Multitask Language Understanding benchmark for reasoning and knowledge evaluation.
Benchmark / Dataset
GSM8K & MATH
Grade school math and competitive reasoning datasets for chain-of-thought evaluation.
Benchmark / Dataset
Alpaca & UltraFeedback
High-quality instruction tuning and human preference preference datasets.