In continuous optimisation, surrogate models (SMs) are used when tackling real-world problems whose candidate solutions are expensive to evaluate. In previous work, we showed that...
Hierarchical culling is a key acceleration technique used to efficiently handle massive models for ray tracing, collision detection, etc. To support such hierarchical culling, bo...
Tae-Joon Kim, Yongyoung Byun, Yongjin Kim, Bochang...
Compositional Modelling (CM) has been applied to synthesize automatically plausible scenarios in many problem domains with promising results. However, it is assumed that the generi...
State-of-the-art solvers for Quantified Boolean Formulas (QBF) have employed many techniques from the field of Boolean Satisfiability (SAT) including the use of Conjunctive Norm...
Alexandra Goultiaeva, Vicki Iverson, Fahiem Bacchu...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...