Paper Presentation
In a group of 2 people
60 minutes presentation + 15 minutes discussion. Cover 4-5 papers.
Template:
Clear statement of the topic.
Backgrounds and previous literature;
Each Paper: Studied problem, technical ideas, experiments, brief summarization;
Open research questions, future work, potential applications
Slides are expected to be mostly visual (figures, animations, videos). Students are encouraged to search for relevant material, e.g., from the authors' webpage, project pages, etc. It's fine to use slides from the authors, but each slide that is not your own must be clearly cited.
Due dates: Send slides to instructor two days before your presentation to receive feedback.
Paper Review
At most one page PDF. The selected papers should be related to either: your paper presentation, or, final project. It should include the following contents:
Studied problem, technical ideas, experiments;
Strengths and weaknesses in your understanding;
(Optional) Future work, open research questions, unclear points, potential applications;
Ethics: According to university policy, using materials generated by AI (e.g., ChatGPT) without attribution is considered plagiarism.
Assignment
For each assignment, you need to fill in all the missing lines of codes, and succesfully run codes to get satiesfying running results. Keep the running results in *.ipynb and submit it to canvas.
Deadline: See course schedule for deadline of each assignment. You will be allowed a total of five late days per course. Each additional late day will incur a 10% penalty.
Ethics: Please do assignments individually. You can search the Internet resources to help you write, debug, and run the codes.
Points: You will get 6/6 points if your submission shows good running results. Otherwise, you will get fewer points depending on your written codes and running results.
Final Project
In a group of 1 - 2 people (2 is preferred, but higher workload for the project is expected)
Submit a project paper (4 pages), a blogpost, and presentation slides (in pdf) to canvas.
Give a presentation of 10-15 minutes at the end of the semester
Topics are flexible, but should be related to this course, such as:
Proposing and addressing a new task/application;
Design and evaluation of a novel approach;
An extension of an approach studied in class;
In-depth analysis of an existing technique;
In-depth comparison of two related existing techniques.
Proposal presentation (5 points): A 5-minute presentation describing: (1) Problem statement: describe the problem; (2) Related work: briefly describe related papers, and, what will be unique about your project that previous work has not done? (3) Approach: briefly describe the algorithm(s) you will employ; (4) Experiments: Describe the designed experiments to evaluate your approach. (5) Others: Summarize any preliminary results.
Final project presentation (15 points): A 10-minute presentation describing: (1) Problem statement: describe the problem; (2) Related work: provide a detailed description of related papers. If you're proposing a new idea or extending an existing approach, what will be unique about your project that previous work has not done? If you're analyzing one or two related techniques, describe how they relate to other relevant work; (3) Approach: Describe in detail the algorithm(s) you employed. Clearly state the method's input and output, and any assumptions or design choices; (4) Experiments: describe the experiments you conducted to evaluate the approach. For each experiment, describe what you did, what was the main purpose of the experiment, and what you learned from the results. Provide figures, tables, and qualitative examples, as appropriate. (5) Conclusions: briefly summarize the main idea and results, discuss limitations and possible future work.
Final project blog post (20 points): The final report is in the form of a blog post. It should be written in a way that is accessible to a general audience, introductory and educative, and include all contents as above. Example blogs:
Generative Modeling by Estimating Gradients of the Data Distribution, by Yang Song
Perspectives on diffusion, by Sander Dieleman
Diffusion Models for Video Generation, by Lilian Weng
The AI Revolution: The Road to Superintelligence, by Maarten Steinbuch
Understanding LSTM Networks, by Christopher Olah
The Unreasonable Effectiveness of Recurrent Neural Networks, by Andrej Karpathy