2024 Spring UVa CS Generative AI Seminar Lectures Organized by Tags

Click on a tag to see relevant list of lectures.

• APE
• Agent
• Alignment
• BasicLLM
• Bias
• DomainAdapt
• Efficiency
• Evaluate
• Hallucination
• Interpretibility
• Mitigate
• Model Edit
• RAG
• Reasoning
• Safety

---

APE

Title	Lecture
Prompt Engineering	SlideDeck

Agent

Title	Lecture
LLM Agents	SlideDeck
MultiAgent LLMs	SlideDeck

Alignment

Title	Lecture
Survey human alignment	SlideDeck
LLM fine tuning	SlideDeck

BasicLLM

Title	Lecture
Introduction
LLM basics	SlideDeck
Survey LLMs and Multimodal FMs	SlideDeck
Open Source LLM - Mistral Data preparation	SlideDeck
Recent LLM basics	SlideDeck

Bias

Title	Lecture
FM fairness / bias issues	SlideDeck

DomainAdapt

Title	Lecture
Domain Centered FMs	SlideDeck

Efficiency

Title	Lecture
LLM Scaling law and Efficiency	SlideDeck
Recent LLM basics	SlideDeck
Advanced Transformer Architectures	SlideDeck
Bonus session on KV Cache, Tooling and WMDP	SlideDeck

Evaluate

Title	Lecture
LLM evaluating framework	SlideDeck
Survey AI Risk framework	SlideDeck
FM copyright infrigement	SlideDeck
FM privacy leakage issues	SlideDeck

Hallucination

Title	Lecture
LLM Hallucination	SlideDeck

Interpretibility

Title	Lecture
LLM interpretibility, trust and knowledge conflicts	SlideDeck

Mitigate

Title	Lecture
GenAI Guardrails	SlideDeck
Survey AI Risk framework	SlideDeck
FM copyright infrigement	SlideDeck
FM privacy leakage issues	SlideDeck

Model Edit

Title	Lecture
Model editing and Disgorgement	SlideDeck

RAG

Title	Lecture
Knowledge Augmented FMs	SlideDeck

Reasoning

Title	Lecture
Self-exam LLM and reasoning	SlideDeck

Safety

Title	Lecture
FM toxicity / harmful outputs	SlideDeck
LLM multimodal harm responses	SlideDeck
More FM risk	SlideDeck
Bonus session on KV Cache, Tooling and WMDP	SlideDeck