1. Course Information

• Instructor: Hanjie Chen

• Semester: Fall 2026

• Time: Thursday 4:00PM - 5:15PM

• Location: OES 132

• Email: hanjie@rice.edu

• Office Hour: Friday 4:30PM - 5:00PM, DH 2081

2. Course Description

This graduate seminar explores recent advances in large language models (LLMs), with an emphasis on their underlying mechanisms, capabilities, limitations, and emerging research directions. The course will cover core topics in LLM development, including pretraining, post-training, and test-time scaling, as well as recent advances in reasoning, agents, multimodal models, interpretability, controllability, alignment, and safety.

The course is research-oriented and primarily based on recent papers from leading machine learning (ML) and natural language processing (NLP) conferences. Students will study current approaches, identify open research questions, and discuss the broader implications of increasingly capable language models.

3. Course Format

• Introduction Session. The instructor and her PhD students will lead the first few lectures, providing overviews of advanced topics in large language models and introducing key concepts, methods, and recent research developments in each area.

• Paper Reading, Presentation, and Discussion. Starting from the weeks of student presentations, three students will present three research papers related to the weekly topic. All other students are expected to read these papers before class and submit one discussion question for each paper to Canvas prior to class. Each paper presentation will be approximately 15 minutes, followed by a 10-minute discussion session on the paper and the broader topic. Students are expected to actively participate in the discussion by asking questions or providing comments. Depending on the number of students enrolled, each student will be responsible for presenting 1-2 papers throughout the semester.

• Final Project Presentation (3-credit option). We will hold the final lecture for project presentations. All students, including those enrolled in the 1-credit option, are welcome to attend. Students enrolled in the 3-credit option will record a 10-minute final presentation on their projects and upload the recording to Canvas.

4. Assignments and Evaluation

Please review the Reading List and sign up for paper presentations by the end of October 9th.

• 1-Credit Option

  1. Paper reading and discussion questions: 6 * 5% = 30%

  2. Paper presentation: 46%

  3. Attendance and active participation in paper discussions: 6 * 4% = 24%

• 3-Credit Option

  1. Paper reading and discussion questions: 6 * 3% = 18%

  2. Paper presentation: 46%

  3. Attendance and active participation in paper discussions: 6 * 2% = 12%

  4. Final project: 24%

• Rubrics

1. Paper reading and discussion questions. Read the 3 assigned papers each week and submit 1 discussion question for each paper to Canvas before class.

2. Paper presentation. Each paper presentation should include an introduction/background, research problem/motivation, method, experimental results, and conclusion/takeaway. Presentations will be evaluated based on clarity, understanding of the paper, and the ability to engage the class in discussion.

3. Attendance and active participation in paper discussions. Students are expected to attend the class and ask at least one question or make one comment for each paper presentation.

4. Final project. For students enrolled in the 3-credit hour option, completing a research-oriented course project is required. The project should investigate a research problem related to large language models and may involve developing new methods, conducting empirical studies, or analyzing existing approaches. Projects will be evaluated based on the quality of the research question, technical approach, experimental design and analysis, and final presentation. Students are encouraged to discuss their project ideas with the instructor early in the semester and to meet regularly with the instructor or attend office hours to receive feedback and provide updates on their progress. 

Final project presentation (24'):

• Introduction (3'): background/motivation, research problem

• Models and datasets (4')

• Methodology (8'): a description of the method

• Experiments (8'): setup, experimental results

• Conclusion (1')

          No final report.

• Grading

The letter grade will be assigned based on the points accumulated:
A+ (98-100), A (94-97), A- (90-93), B+ (87-89), B (84-86), B- (80-83), C+ (77-79), C (74-76), C- (70-73), D+ (67-69), D (64-66), D- (60-63), F (<60)

5. Prerequisites

Students are expected to have completed at least one machine learning course and possess basic knowledge of NLP and LLMs, including fundamental concepts and common tasks (such as question answering). For students opting for the 3-credit hour option, which includes a hands-on research project, programming experience, preferably in Python, and familiarity with libraries and frameworks such as NumPy, pandas, scikit-learn, PyTorch, and Hugging Face Transformers are required.

6. Honor Code

All students are expected to adhere to the standards of the Rice Honor Code, which you agreed to uphold upon matriculation. For detailed information on the Honor Code, including its administration and the procedures for addressing alleged violations, please refer to the Honor System Handbook available at http://honor.rice.edu/honor-system-handbook/. This handbook outlines the University’s expectations for academic integrity, the procedures for resolving any alleged violations, and the rights and responsibilities of students and faculty throughout the process.

Note that students should use AI tools carefully in their assignments. Please follow the university's AI Usage Guidelines.