Peer-curated academic archive from University of Alberta (Amii), comprising 7 recorded lectures in AI & Machine Learning, Algorithms & Theoretical CS, Computer Systems & Software.
Self-contained research seminars, public lectures, and invited colloquia.
Exploring techniques for machine learning to automate formal verification, focusing on mining reusable custom tactics and the challenges in applying abstractions to real-world projects.
Introducing Endpoint Replay, an algorithm that significantly compresses recency buffers in deep reinforcement learning by pairing a recency buffer with a coreset of chained n-step transitions.
A deep dive into methods for optimizing the Conditional Value-at-Risk (CVaR) in Markov Decision Processes, introducing the Dynamically Augmented CVaR for robust decision-making.
Outlines a roadmap for continual, agent-centric intelligence built from online temporal-difference prediction, meta-step-size adaptation, and learned predictive world models.
An examination of how large language models bridge lexical and sentence semantics through concepts, presenting recent findings and highlighting limitations in reasoning and multilingual contexts.
This seminar presents research on actionable interpretability, translating insights into language model reasoning, learning, and failure modes into concrete improvements in training and inference. Topics include parameter-efficient adaptation via localized computation, distillation dynamics, and gradient-based analysis for reward hacking suppression.
Professors, researchers, and invited lecturers recorded at University of Alberta (Amii).
Browse, filter, and sort every lecture from University of Alberta (Amii).
