Lectures

01/21/2025: Overview

01/23/2025: Prompting, Part I

Main Reference I: Lilian weng's Blog on Prompting, Main Reference II: Prof. Lianhui Qin's Slides on Chemistry Reasoning

01/28/2025: Prompting, Part II

Review of CoT, ToT, Self-Consistency, Self-Refinement, and Confidence Score

Introduction to Tool Use: Prof. Lianhui Qin's Slides (Starting from Page 18)

Introduction to LLM Agents: Lilian weng's Blog Post

01/30/2025: LLM Web Versions vs. API

02/04/2025: LLM Basics Part 1 (e.g., transformers, language modeling, pretraining, finetuning, etc)

Some Slides from Prof. Lianhui Qin

02/06/2025: LLM Basics Part 2 (decoding)

Some Slides from Prof. Lianhui Qin

02/11/2025: LLM Basics Part 3 (alignment)

Some Slides from Prof. Lianhui Qin

02/13/2025: Reinforcement Learning and Test-Time Scaling for LLM Reasoning

Large Language Monkeys

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

s1: Simple test-time scaling

02/18/2025: Engineering Benchmarks for LLMs Part 1

02/20/2025: Engineering Benchmarks for LLMs Part 2

02/25/2025: Automated Evaluations of LLMs on Engineering Benchmarks

02/27/2025: An Introduction to LLM Agents

Lilian Weng's Blog Post on LLM Agents

ICLR 2024 Workshop on LLM Agents

03/04/2025: Case Study: ControlAgent

03/06/2025: Case Study: AnalogCoder

03/11/2025: A Unified Perspective on Inference-Time Scaling law and LLM agents

03/13/2025): Multi-Agent LLM Reasoning and Engineering Tool-use

03/25/2025: Some Findings from the Benchmarking Assignments

03/27/2025: Discussion for Final Project Topics

04/01/2025: Discussion for Final Project Topics

04/03/2025: Discussion for Final Project Topics

04/08/2025: Discussion for Final Project Topics

04/10/2025: Retrieval-Augmented Generation (RAG), Part I

Adit Agarwal's slides are distributed via email.

04/15/2025: Retrieval-Augmented Generation (RAG), Part II

Adit Agarwal's slides are distributed via email.

04/17/2025: Automatic Prompt Optimization, Part I

Greedy Coordinate Gradient

Energy-based search

04/22/2025: Automatic Prompt Optimization, Part II

PGD with Entropy Projection

Amortization of LLM Prompt Optimization

04/24/2025: Reinforcement Learning for Alignment

04/29/2025: Reinforement Learning for Developing Reasoning Models

05/01/2025: Multi-Modality

05/06/2025: Review