Seminar
CVL Talk: Biologically Plausible Learning Using Local Activity Perturbation - Mengye Ren, NYU
CVL Talk: Biologically Plausible Learning Using Local Activity Perturbation - Mengye Ren, NYU
Abstract: Backprop is usually considered biologically implausible due to the issues of weight transport and global synchronization. Perturbation learning is potentially a good candidate for a biologically plausible alternative, since it...
AI & Fundamentals
Multimodal AI in the Era of Gigantic Pretrained Language Models: Challenges and (Some) Remedies - Boyang Albert Li, Associate Professor, Nanyang Technological University
Multimodal AI in the Era of Gigantic Pretrained Language Models: Challenges and (Some) Remedies - Boyang Albert Li, Associate Professor, Nanyang Technological University
Please register for this event here. Abstract: Large pretrained language models brought a series of capabilities, such as in-context learning, chain-of-thought reasoning, and many other prompting tricks, that surprised man...
Seminar
CVL Talk: From Video to Unsupervised Semantic 4D Reconstruction - James Tompkin, Browns
CVL Talk: From Video to Unsupervised Semantic 4D Reconstruction - James Tompkin, Browns
Abstract: Pose estimation and tracking are among the fundamental problems in computer vision and crucial tasks in many vision applications ranging from sports to human-computer interaction to the study of collective behaviour. Within ou...
Seminar
CVL Talk: Multi-Object Tracking and Pose Estimation for Animals - Urs Waldmann, University of Konstanz
CVL Talk: Multi-Object Tracking and Pose Estimation for Animals - Urs Waldmann, University of Konstanz
Abstract: Pose estimation and tracking are among the fundamental problems in computer vision and crucial tasks in many vision applications ranging from sports to human-computer interaction to the study of collective behaviour. Within ou...
AI & Fundamentals
Reconstructing Training Data from Model Gradient, Provably - Qi Lei, Assistant Professor, NYU
Reconstructing Training Data from Model Gradient, Provably - Qi Lei, Assistant Professor, NYU
Abstract: Understanding when and how much a model gradient leaks information about the training sample is an important question in privacy. In this talk, we present a surprising result: even without training or memorizing the da...
AI & Fundamentals
Diffusion Models: From Foundations to Image, Video and 3D Content Creation - Karsten Kreis, Senior Research Scientists, NVIDIA’s Toronto AI Lab
Diffusion Models: From Foundations to Image, Video and 3D Content Creation - Karsten Kreis, Senior Research Scientists, NVIDIA’s Toronto AI Lab
Abstract: Denoising diffusion-based generative models have led to multiple breakthroughs in deep generative learning. In this talk, I will provide an overview over recent works by the NVIDIA Toronto AI Lab on diffusion models and their ...
General Event
CAIDA Faculty Lunch - October 2023
CAIDA Faculty Lunch - October 2023
Our monthly faculty lunch allows our members to connect and encourages future interdisciplinary collaborations. This event is for CAIDA Faculty Members only and requires registration. If you are a UBC faculty member working i...
AI & Applications
Gore Robots: From Blood and Guts to Bits and Bytes - Juan Wachs, Professor, Purdue University
Gore Robots: From Blood and Guts to Bits and Bytes - Juan Wachs, Professor, Purdue University
Abstract: Robots can already solve sophisticated problems ranging from playing games, autonomous driving, and dancing—given enough observational of data for training. The core of such success resides in efficient algorithms, com...
General Event
Imaging the Future
Imaging the Future
Register Here INOVAIT, UBC School of Biomedical Engineering, UBC Biomedical Imaging and AI Cluster, and CAIDA: UBC ICICS Centre for Artificial Intelligence Decision-making and Action invites clinicians, ...
General Event
Querying AI: Social Science and Humanities Perspectives on AI in Research and Politics
Querying AI: Social Science and Humanities Perspectives on AI in Research and Politics
REGISTER HERE Pre-Workshop Training Working with AI for Humanities and Social Science Research: Python and R for Word Embeddings and Language Models Time: 11:00AM - 12:45PM Venue: ANSO 134 This hands-on workshop will walk p...