2 papers
cs.CV2025
TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference
Junshan Hu, Jialiang Mao, Zhikang Liu +3
Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable ineff…
stat.ME2024
A tree-based model for addressing sparsity and taxa covariance in microbiome compositional count data
Zhuoqun Wang, Jialiang Mao, Li Ma
Microbiome compositional data are often high-dimensional, sparse, and exhibit pervasive cross-sample heterogeneity. Generative modeling is a popular approach to analyze such data,…