Course Information

   Yun-Nung (Vivian) Chen
   Physical (R103) / Virtual (YT Video)
   Monday 14:20 - 17:10

Syllabus

Date Lecture Recitation Note
自學 / 先修 Introduction [ 1.1] [ 1.2] [ 1.3]
Neural Network Basics [ 2.1] [ 2.2] [ 2.3] [ 2.4]
Backpropagation [ 2.5]
HW 0
2026/09/07 Course Logistics [ 0]
Sequence Modeling [ 3.1] [ 3.2] [ 3.3] [ 3.4]
Dev Infra & Tooling
[ PyTorch] [ Debugging]
Physical
2026/09/07 Guest Lecture by Dr. Eugene Yang [form] [video] Physical
2026/09/14 Attention Mechanism
Transformer
Tokenization
BERT
NLP Lifecycle
[ Step by Step] [Colab]
Physical
HW 1
[ hw 1]
彈性補充 Word Embeddings [ Intro] [ Word2Vec] [ Training]
[ Variants] [ GloVe] [ Eval]
BERT Variants [ Pretraining] [ XLNet] [ RoBERTa] [ mBERT]
Virtual
2026/09/21 Pretraining & Prompt Learning Underlying Logics of Projects
[ Step by Step]
Physical
2026/09/28 教師節 Break
2026/10/05 Retrieval-Augmented Generation LLM Basics & MoE [ Basics]
[ Architecture] [ MoE]
Physical HW 2
2026/10/12 Post-Training
LLM Adaptation
LLM LoRA Training
[ LoRA]
Physical
HW 3
2026/10/19 NLG Decoding
NLG Evaluation
LLM Inference & Evaluation
[ Infer & Eval]
Virtual
2026/10/26 台灣光復 Break
2026/11/02 Final Project Announcement LLM Deployment
[ Deployment]
Physical
2026/11/09 Alignment: Safety, Fairness, Factuality Physical
2026/11/16 Language Agents Physical
2026/11/23 Human-AI Interaction
2026/11/30 Personalization, Reasoning Physical
2025/12/07 Knowledge, Multimodality Physical
2026/12/14 Final Project Due

Homework

The assignments should be submitted via NTU COOL.
NO LATE SUBMISSION IS ALLOWED!

  • Please make sure that you have computing resources for training deep models.
  • Please make sure that your GitHub repo for homework is private.

Teaching Team

Please send your questions to adl-ta@csie.ntu.edu.tw.
Please make sure the title of your mail starts with [ADL2026].

Role Name Work Office Hour Location
TA 施泳瑜 HW 1 R524
TA 彭紀綸 HW 2 R524
TA 陳剛詰 HW 2 R524
TA 張文毓 HW 3 R524
TA 張正穎 HW 3 R524
TA 陳妍姍 Project R524
TA 譚智睿 Project R524
TA 鄧昱辰 Project R524