1 citations · 1 across the 6 of their papers we have counts for
4 papers · 1 filter
Statistical Gains from Looped Estimation under Parameter Budgets
Xinyu Tian, Xiaotong Shen
Memory constraints in artificial intelligence motivate accurate function approximation with fewer parameters. We study looping, which repeatedly composes one update function with s…
Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data
Yuefei Shen, Xiaotong Shen
Mixed continuous--categorical data pose a representation problem for continuous generative models. Flow Matching and Gaussian diffusion operate in Euclidean spaces, whereas categor…
Generative Score Inference for Multimodal Data
Xinyu Tian, Xiaotong Shen
Accurate uncertainty quantification is crucial for making reliable decisions in various supervised learning scenarios, particularly when dealing with complex, multimodal data such…
Manifold-Aligned Generative Transport
Xinyu Tian, Xiaotong Shen
Many high-dimensional datasets concentrate near a low-dimensional structure embedded in the ambient space. Generative models for such data must control off-support mass while remai…