3 papers
cs.LG2025
Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
Ruiyao Miao, Junren Xiao, Shiya Tsang +2
Existing Bayesian Optimization (BO) methods typically balance exploration and exploitation to optimize costly objective functions. However, these methods often suffer from a signif…
cs.HC2025
AnimAlte:Designing AI-Infused Cartoon Videos to Improve Preschoolers' Language Learning with Family Engagement at Home
Shiya Tsang, Ruiyao Miao, Junren Xiao +1
Cartoon videos have proven to be effective in learning vocabulary to preschool children.However, we have little knowledge about integrating AI into cartoon videos to provide system…
cs.LG2024
"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihood
Peiyu Yu, Dinghuai Zhang, Hengzhi He +10
Noise Contrastive Estimation (NCE) has fueled major breakthroughs in representation learning and generative modeling. Yet a long-standing challenge remains: accurately estimating r…