The following schedule is a work in progress. Once we have the full seminar details including title, abstract and speaker bio, we will publish these talks under upcoming seminars.

Date Speaker Title Abstract
2025-01-16 11:00 Ruikai Cui From Completion to Generation: Learning Representation for 3D Content Enhancement and Creation Enhancing the quality of existing 3D content and synthesizing novel content is crucial for many 3D understanding tasks and applications. Despite significant research in this area, current methods still face limitations such as reliance on hard-to-obtain labelled data and unsatisfactory 3D content quality and diversity. To address these challenges, in this seminar I will present four key contributions from my PhD research: 1) An unsupervised point cloud completion framework that enables effective 3D content enhancement using unlabelled 3D data. 2) A self-supervised point cloud completion method that learns to improve 3D content quality using only partial observations of 3D objects. 3) A generative model that integrates 3D shape completion, reconstruction, and generation into a single unified framework. 4) A 3D reconstruction model that facilitates large-scale 3D content creation from single-view image references. Both theoretical and experimental analyses validate the effectiveness of these techniques in advancing 3D content enhancement and creation.
2025-01-23 11:00
2025-01-30 11:00
2025-02-06 11:00 Xiaodi Zhang Counter-Example Based Planning I will introduce advancements in solving conformant planning (CP) and probabilistic conformant planning (PCP) through counter-example-based approaches. For CP, I enhance the CPCES algorithm by introducing certain-facts to optimize classical planning reductions, implementing a warm-start strategy to improve initialization, and integrating an incremental SAS+ representation for better compatibility with the FD planner. For PCP, I propose p-CPCES, which uses counter-tags, a probabilistic abstraction of counter-examples, to reduce search complexity, using d-DNNF representations for efficient probability computation. To address the limitations of single-threaded computation in p-CPCES, I propose parallel-CPCES, a parallelized system utilizing multi-core CPUs. By introducing specialized modules to manage counter-tags, hitting sets, and candidate plans, parallel-CPCES enables concurrent computations at each depth, significantly reducing planning time.
2025-02-13 11:00
2025-02-20 11:00
2025-02-27 11:00
2025-03-06 11:00
2025-03-13 11:00 Joshua Krook Human Autonomy in the Age of A.I. Recommender systems form the backbone of modern e-commerce, suggesting items to users based on the collection of algorithmic data of a user's preferences. Companies that use recommender systems claim that they can give users what they want, or more precisely, what they desire. Netflix, for example, gives users recommended movies based on the user's behaviour on the platform, thereby listing new movies that the user may want to watch. This article explores whether there is a difference between what engages us, on the one hand, and what we truly want to want, on the other. This builds on the hierarchical structure of desires, as posed by Harry Frankfurt and Gerald Dworkin. Recommender systems, to use Frankfurt's terminology, may not allow for the formation of second-order desires, or for users to consider what they want to want. Indeed, recommender systems may rely on a narrow form of human engagement, a voyeuristic mode, rather than an active wanting. In bypassing second-order desires, there is a risk that recommender systems can start to control the user, rather than the user controlling the algorithm. This raises important questions concerning human autonomy, trustworthiness, and Byung-Chul Han's conception of an information regime, where the owners of the data make decisions about what users consume online, and ultimately, how they live their lives.
2025-03-20 11:00
2025-03-27 11:00
2025-04-03 11:00
2025-04-10 11:00
2025-04-17 11:00
2025-04-24 11:00
2025-05-01 11:00
2025-05-08 11:00
2025-05-15 11:00
2025-05-22 11:00
2025-05-29 11:00
2025-06-05 11:00
2025-06-12 11:00
2025-06-19 11:00
2025-06-26 11:00
2025-07-03 11:00
2025-07-10 11:00
2025-07-17 11:00
2025-07-24 11:00
2025-07-31 11:00
2025-08-07 11:00
2025-08-14 11:00
2025-08-21 11:00
2025-08-28 11:00
2025-09-04 11:00
2025-09-11 11:00
2025-09-18 11:00
2025-09-25 11:00
2025-10-02 11:00
2025-10-09 11:00
2025-10-16 11:00
2025-10-23 11:00
2025-10-30 11:00
2025-11-06 11:00
2025-11-13 11:00
2025-11-20 11:00
2025-11-27 11:00
2025-12-04 11:00
bars search times arrow-up