EECE 576L: Advanced Topics in Deep Learning
Overview
EECE 576L examines geometric and probabilistic deep learning and deep reinforcement learning through lectures, student paper presentations, and a research project.
Course Information
| Instructor | Renjie Liao |
|---|---|
| Term | 2026/27 Winter Session, Term 1 (Fall 2026) |
| TA | Yuanpei Gao · yuanpeig@student.ubc.ca |
| Class | Tuesday, 4:00 p.m. – 7:00 p.m. · UBCV · MCLD 2012 (Hector J. MacLeod Building, Floor 2) |
| Piazza | Course forum |
| Office hour | Tuesday, 1:00 p.m. – 2:00 p.m. · KAIS 3047 (Ohm) |
| renjie.liao@ubc.ca |
Use Piazza for questions and Canvas for submissions, grades, deadlines, and changes.
Announcements: First class: Sep. 15. No class Sep. 8 (the classroom may be used for Imagine UBC orientation activities) or Nov. 10 (midterm break).
Detailed overview · Course project · Course policies · Resources
Schedule
Tuesdays, 4:00 p.m. – 7:00 p.m., MCLD 2012. Dates follow the UBC Vancouver calendar; classes do not meet on UBC holidays or during the midterm break. There is no class on Sep. 8 or Nov. 10; the first meeting is Sep. 15 and the last is Dec. 1.
The schedule is tentative. Reference slides are from the previous offering until replaced; paper selections may change. See the presentation guideline.
| Meeting | Date (Tuesday) | Topic and papers | Reference slides | Suggested readings |
|---|---|---|---|---|
| — | Sep. 8 | No class — classroom may be used for Imagine UBC activities | — | — |
| 1 | Sep. 15 | Introduction; invariance, equivariance, sets and sequences | slides slides |
Chapter 13, 14 of PML1 book & DL book DeepSets & Transformers & PreNorm & VisionTransformers & SwinTransformers & Chapter 15 of PML1 book |
| 2 | Sep. 22 | Graph neural networks: message passing and graph convolutions | slides I slides II |
Part II of GRL book & Chapter 23 of PML1 book & Chapter 4 of GNN book & GNNs & GGNNs & GAT & Graphormer & GPS & GCNs & ChebyNet & LanczosNet & SignNet & Specformer |
| 3 | Sep. 29 | Group-equivariant deep learning | slides I slides II slides III slides IV |
lecture note I lecture note II lecture note III lecture note IV UvAGEDL |
| 4 | Oct. 6 | Paper presentations 3–6 3. Mamba 4. xLSTM 5. ViT Registers 6. G-CNNs |
slides 3 slides 4 slides 5 slides 6 |
— |
| 5 | Oct. 13 | Paper presentations 7–10 7. Tensor-Field Networks 8. SE(3)-Transformers 9. EGNNs 10. LieTransformers |
slides 7 slides 8 slides 9 slides 10 |
— |
| 6 | Oct. 20 | Autoregressive models, LLMs and policy gradients; paper presentations 11–12 11. TIT 12. GRPO |
slides slides 11 slides 12 |
BERT & GPT3 & T5 & Scaling Laws & LoRA |
| 7 | Oct. 27 | Paper presentations 13–16 13. DPO 14. Learning Dynamics of DPO 15. KTO 16. RLVR I |
slides 13 slides 14 slides 15 slides 16 |
— |
| 8 | Nov. 3 | Diffusion and flow models | slides slides |
Score-based Models & ScoreSDE & DDPM & DDIM & DPM++ Flow Matching & Rectified Flow & Stochastic Interpolants |
| — | Nov. 10 | No class — UBC midterm break | — | — |
| 9 | Nov. 17 | Paper presentations 17–20 17. RLVR II 18. VAR 19. Rectified Flow 20. OT-CFM |
slides 17 slides 18 slides 19 slides 20 |
— |
| 10 | Nov. 24 | Paper presentations 21–24 21. MDLM 22. MDLM Ordering 23. DMD2 24. FlowEdit |
slides 21 slides 22 slides 23 slides 24 |
— |
| 11 | Dec. 1 | Project presentations | — | — |
| — | TBA | Paper presentations 1–2 — new date to be announced 1. PointNet++ 2. Point Transformer V3 |
slides 1 slides 2 |
— |
FAQ
Can I audit or sit in?
UBC students, staff, and faculty may email the instructor to request permission to audit. Registered students receive priority if classroom space is limited.
Where can I find textbooks, paper lists, and sample projects?
See Course Resources. There is no required textbook.