Weijiang Yu

TL;DR: A novel music-to-dance framework with a choreographic memory that learns to summarize meaningful dancing units from 3D pose sequence to a quantized codebook, and an actor-critic Generative Pre-trained Transformer (GPT) that composes these units to a fluent dance coherent to the music.

TL;DR: Wang et al. as mentioned in this paper proposed a hierarchical layout-graph reasoning model to detect ambiguous and structure-inconsistent landmarks of multiple overlapped clothes in one person by enforcing structural layout relationships among landmarks on the intermediate representations via multiple stacked layoutgraph reasoning layers.

TL;DR: In this paper , the authors proposed a novel method ConGI to accurately exploit spatial domains by adapting gene expression with histopathological images through contrastive learning, which can be used to cluster the spatial domains on both tumor and normal spatial transcriptomics datasets.

TL;DR: GraphBepi as mentioned in this paper is a graph-based model for B-cell epitope prediction, which first generates the effective information sequence representations and protein structures from antigen sequences through the pretrained language model and AlphaFold2, respectively.