LLM Chronicles
A fast-paced whiteboard animation series unraveling Deep Learning and Large Language Models. Dive into core concepts, from Neural Networks basics to t...
Academic Course Syllabus
Summary
A comprehensive Stanford University course syllabus covering the technical evolution of Transformers and Large Language Models. The curriculum spans from foundational NLP concepts to advanced topics like agentic workflows, reasoning, and evaluation methodologies.
Highlights
- Covers foundational Transformer architectures and advanced attention mechanisms like MQA and GQA
- Detailed instruction on LLM training, including pretraining, quantization, and LoRA
- Explores advanced tuning and reasoning methods such as RLHF, DPO, and GRPO
- Includes practical modules on RAG, agentic frameworks (ReAct), and LLM-as-a-judge evaluation
auto-generated
Context
Audience
Machine Learning Engineers, AI Researchers, and Computer Science Students
DomainMachine Learning
FormatAcademic course lectures and video recordings
AccessFree online
Source Overview
CME 295 syllabus lists nine lectures from September 26 to December 5, 2025, covering Transformer architecture, LLMs, training methods like pretraining and LoRA, tuning via RLHF and DPO, reasoning, agents, RAG, and evaluation.
Each lecture includes slides, Panopto recordings around 1:45-1:50 hours, and YouTube videos from a playlist. Resources also feature a midterm on October 24 with exam and solutions, plus a final on December 10.
Topics
Related
Natural Language ProcessingReinforcement LearningRetrieval-Augmented GenerationParameter-Efficient Fine-Tuning
