CS 769 NLP | Schedule

Date	Lecture	Readings	Logistics
Module 1: Introduction to Natural Language Processing
9/3	Lecture #1 : Introduction of NLP [ slides \| video ]	SLP3 ch2
9/8	Lecture #2 : Word Representations [ slides \| video ]	SLP3 ch 6 E ch 14
9/10	Lecture #3 : Language Models [ slides \| video ]	SLP3 ch 3 Chen & Goodman
9/15	Lecture #4 : Recurrent Networks [ slides \| video ]	Blog Karpathy et al. 2015 Hochreiter et al. 1997
9/17	Lecture #5 : Attention and Transformer [ slides \| video ]	Bahdanau et. al 2014 Vaswani et. al 2017
Module 2: Large Language Models
9/22	Lecture #6 : Pre-training LLMs [ slides \| video ]	Devlin et al. 2019 Yang et al. 2019 Survey Lewis et al. 2020	HW 1 due & Project survey due (11:59pm 9/17)
9/24	Lecture #7 : Parameter-efficient Fine-tuning [ slides \| video ]	He et al. 2021 Dettmers et al. 2023 Hu et al. 2021
9/29	Lecture #8 : Instruction Tuning and Multitask Learning [ slides \| video ]	Understanding Dataset shift Caruana 1997 Neubig and Hu, 2018 Chu et al. 2017 Johnson et al. 2017 Conneau et al. 2020 Ganin et al. 2015
10/1	Lecture #9 : Prompting and Zero-/Few-shot Learning [ slides \| video ]	Liu et al. 2021
10/6	Lecture #10 : Preference Learning from Feedback [ slides \| video ]	Survey, Fernandes et al. 2023 DPO, Rafailov et al. 2023 PPO, Schulman et al. 2017 Policy Gradient, William 1992
10/8	Project Proposal Presentation, HW 2 due (11:59pm 10/8)
Module 3: Scaling up LLMs
10/13	Lecture #11 : Long-Context Language Models [ slides \| video ]	Dai et al. 2019 Child et al. 2019 Kitaev et al. 2020 Wang et al. 2021 Xiong et al. 2021
10/15	Lecture #12 : Decoding and Test-time Scaling [ slides ]	Survey, Welleck et al. 2024 Deepmind's Test-time Compute, Snell et al. 2024
10/20	Lecture #13 : KV Cache Optimization [ slides ]	Survey, Li et al. 2025
10/22	Lecture #14 : Mixture of Experts in LLMs [ slides \| video ]	Survey, Cai et al. 2025 ICML 2024 Tutorial	HW 3 due (11:59pm 10/22)
10/27	Lecture #15 : Retrieval-Augmented Generation of LLMs [ slides ]	Akari's slides ACL 2023 Tutorial
Module 4: Expanding LLMs beyond One Language
10/29	Lecture #16 : Multilingual LLMs: Languages and Cultures [ slides \| video ]	IBM Model Moses Johnson et al. 2016 Koehn et al. 2017 Arivazhagan et al. 2019 SLP3 ch10
11/3	Lecture #17 : Multimodal Learning: Vision and Language [ slides \| video ]	Baltrusaitis et al. 2017 Radford et al. 2021 Ramesh et al. 2021
11/5	Lecture #18 : LLMs and Knowledge-Graph [ slides \| video ]	SLP3 ch17
11/10	Project Mid-review Presentation, HW 4 due (11:59pm 11/10)
Module 5: Advanced Topics of LLMs
11/12	Lecture #19 : LLM Reasoning and Verification [ slides \| video ]	Lightman et al. 2023 Luo et al. 2024
11/17	Lecture #20 : Language Agents: Basic and Tool Use [ slides \| video ]	Wang et al. 2024 Schick et al. 2023 OpenAI 2024 Zhou et al. 2023 EMNLP 2024 Tutorial
11/19	Lecture #21 : Language Agents: Software Development and Web Browsing [ slides \| video ]	HumanEval, Chen et al. 2021 SWE-bench, Jimenez et al. 2023 OSWorld, Xie et al. 2023
11/24	Lecture #22 : Safety and Security of LLMs [ slides \| video ]	Survey in Jailbreak attack vs defense for LLM, Xu et al. 2024 Survey on backdoor attacks in LLMs, Zhao et al. 2024
11/26	Lecture #23 : Mechanistic Interpretability of LLMs [ slides \| video ]	ICML 2025 Tutorial
12/1	Project Presentation
12/3	Project Presentation
12/10	Project Report due 11:59pm 12/10