4 papers
Generation-Powered Inference for Distribution-Valued Outcomes
Yijiao Zhang, Hongzhe Li
Modern generative models increasingly produce distribution-valued outputs, such as predicted cellular responses to genetic perturbations in single-cell genomics. While these models…
Bayesian Environment Invariant Regression
Ruqian Zhang, Juan Shen, Yijiao Zhang
The availability of data from multiple heterogeneous environments has motivated methods that remain reliable under distributional shifts. When the joint distribution of response an…
Gradient-Informed Training for Low-Resource Multilingual Speech Translation
Ruiyan Sun, Satoshi Nakamura
In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This…
Syntax-Guided Diffusion Language Models with User-Integrated Personalization
Ruqian Zhang, Yijiao Zhang, Juan Shen +2
Large language models have made revolutionary progress in generating human-like text, yet their outputs often tend to be generic, exhibiting insufficient structural diversity, whic…