[Youtube]
The always learning machine. CUHK Multi-Modal and World Model Symposium 2026. Hong Kong. 2026/08/16. [slides]
The always learning machine. Mila. Montréal. 2026/07/23. [slides]
The always learning machine. Seoul National University. Seoul. 2026/07/09. [slides]
The always learning machine. Global AI Frontiers Symposium. Seoul. 2026/07/03. [slides] [video]
Does your LLM agent have a self? ICLR 2026 MemAgents Workshop. Rio de Janeiro. 2026/04/27. [slides] [video]
The always learning machine. Columbia University. New York. 2026/04/09. [slides]
Lifelong concept learning. New York University CDS Seminar. New York. 2026/02/13. [slides]
Lifelong concept learning. Korea Advanced Institute of Science and Technology (KAIST). Seoul. 2025/10/31. [slides]
Lifelong concept learning. Seoul National University. Seoul. 2025/10/30. [slides]
Lifelong concept learning. Global AI Frontiers Symposium. Seoul. 2025/10/27. [slides] [video]
Lifelong concept learning. University of Calgary. Department of Electrical and Software Engineering. Calgary. 2025/06/16. [slides]
Lifelong concept learning. IITP AI Education Program. New York. 2025/06/02. [slides]
Lifelong concept learning for machines. New York University. Department of Psychology ConCats Seminar. New York. 2025/04/04. [slides]
Lifelong and human-like learning in foundation models. Seoul National University. Guest Lecture at SNU AI Seminar. Seoul. 2024/12/05. [slides]
Lifelong and human-like learning in foundation models. Columbia University. NSF AI Institute for Artificial and Natural Intelligence. New York. 2024/09/13. [slides]
Computer Vision and Deep Learning: A Primer. NYU AI Summer School. New York University. New York. 2024/06/04. [slides]
Lifelong and human-like learning in foundation models. Machine Learning Seminar. Flatiron Institute. New York. 2024/04/30. [slides]
Lifelong and human-like learning in foundation models. Smart Minds meet Smart Machines: AI for Science and Public Good. German Consulate General in New York. New York. 2024/04/08. [slides]
Lifelong learning in structured environments. American Statistical Association, Statistical Learning and Data Science Webinar. Virtual. 2023/10. [slides] [video]
Scaling forward gradient with local losses. Baylor College of Medicine, Journal Club Invited Talk. Houston. 2023/06. [slides]
Biologically plausible learning using local activity perturbation. University of British Columbia. Invited Talk. Vancouver. 2023/06. [slides]
Meta-learning within a lifetime. NeurIPS 2022 MetaLearn Workshop, Invited Talk. New Orleans. 2022/12. [slides] [video]
Biologically plausible learning using local activity perturbation. NYU CDS Lunch Seminar. New York. 2022/10. [slides] [video]
Visual learning in the open world. 19th Conference on Vision and Robotics (CRV), Invited Symposium. Toronto. 2022/06. [slides]
Visual learning in the open world. University of Oxford. Oxford. 2021/11. [slides]
Visual learning in the open world. Google Brain. Toronto. 2021/11. [slides]
Visual learning in the open world. Stanford University. Stanford. 2021/10. [slides]
Steps towards making machine learning more natural. Job talk. 2021/02. [slides]
A tutorial on few-shot learning and unsupervised representation learning. Vector Institute. Toronto. 2021/01. [slides]
How can we apply few-shot learning? Vector Institute. Toronto. 2020/10. [slides]
Towards continual and compositional few-shot learning. Stanford University. Stanford. 2020/10. [slides]
Towards continual and compositional few-shot learning. Brown University. Providence. 2020/09. [slides]
Towards continual and compositional few-shot learning. MIT. Cambridge. 2020/09. [slides] [video]
Towards continual and compositional few-shot learning. Mila. Montréal. 2020/08. [slides]
Towards continual and compositional few-shot learning. Uber ATG. Toronto. 2020/08. [slides]
Wandering within a world: Online contextualized few-shot learning. Google Brain. Montréal. 2020/08. [slides]
Wandering within a world: Online contextualized few-shot learning. ICML 2020 Lifelong Learning Workshop. 2020/07. [slides]
Wandering within a world: Online contextualized few-shot learning. ICML 2020 Continual Learning Workshop. 2020/07. [slides]
Jointly learnable behavior and trajectory planner for autonomous driving. IROS 2019. Macau. 2019/11. [slides]
Meta-learning for more human-like learning algorithms. Columbia University. New York. 2019/10. [slides]
Learning to reweight examples for robust deep learning. CIFAR deep learning and reinforcement learning summer school. Toronto. 2018/08. [slides]
Learning to reweight examples for robust deep learning. ICML 2018. Stockholm. 2018/07. [slides]
Meta-learning for weakly supervised learning. INRIA Grenoble - Rhône-Alpes. Grenoble. 2018/07. [slides]
Meta-learning for weakly supervised learning. NEC Laboratories America. Princeton. 2018/07. [slides]
Meta-learning and learning to reweight examples. Max Planck Institute for Intelligent Systems. Tübingen. 2018/06. [slides]
SBNet: Sparse blocks network for fast inference. CVPR 2018. Salt Lake City. 2018/06. [slides]
SBNet: Sparse blocks network for fast inference. Borealis AI Lab (RBC Research). Toronto. 2018/02. [slides]
Meta-learning for semi-supervised few-shot classification. Vector Institute. Toronto. 2017/11. [slides]
End-to-end instance segmentation with recurrent attention. CVPR 2017. Honolulu. 2017/07. [slides] [video]
Sequence-to-sequence deep learning with recurrent attention. Queen’s University. Kingston. 2017/05. [slides]
Recurrent neural networks. CSC 2541: Sport Analytics Guest Lecture. University of Toronto. Toronto. 2017/01. [slides]
Deep dashboard tutorial. University of Guelph. Guelph. 2016/03. [slides]
Deep dashboard tutorial. University of Toronto. Toronto. 2016/02. [slides]