Skip to content

Author

Xiao-Bo Sun

We have 6 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Nov 2026

Editing Large Language Models with Geometry-Aware Regularization

Knowledge editing has become a key technique for updating knowledge in large language models. However, existing methods neglect the geometric structure of the knowledge representation space, leading to two key limitations: they cannot distinguish which pre-trained knowledge should be preferentially preserved (core vs....

Bing-Qing Liu, Wei Liu, Jun Wang et al. · 0 citations
Open access Aug 2026

CoxFormer enables spatial omics inference with multimodal generative modeling

CoxFormer is presented, an approach that learns whole-transcriptome gene representations from biomedical knowledge and co-expression data, thereby enabling spatial omics to predict unmeasured genes, enhance resolution and identify disease-related tissue regions.

Yi-Yang Yang, Xu Liao, Hao-Yu Zhang et al. · 0 citations
Book Open access Aug 2026

Concord: Building Consensus Representations for Single Cells with Collaborative Random Projection

Concord is a novel single-cell FM that explicitly models relationships between gene identities and expression levels through a collaborative rotary attention (CRA) mechanism, and employs two collaborative attention modes: a gene-to-expression rotational attention that produces gene-enhanced expression representations,...

Kaichen Xu, Mianpeng Liu, Hao Wu et al. · 0 citations
Jul 2026

TCellAlign: Cross-study T-cell Populations Alignment with Nomenclature-Guided Multi-Agent Workflow

Cell type standardization plays a central role in integrating biological knowledge across single-cell studies. While standardized resources (e.g., Cell Ontology, Nomenclature Frameworks) provide unified vocabularies of cell populations, scientific publications and public datasets continue to use heterogeneous study-spe...

Peng Xie, Rongjia Zhou, Zhi-Li Ou et al. · 0 citations
Book Open access Aug 2026

DiffPro: Decoupled Generative Prior with Diffusion Models for Efficient Few-Shot Drug Synergy Prediction

DiffPro, a novel framework that integrates a Latent Diffusion Model (LDM) as a structural prior, confirms that the diffusion prior successfully regularizes the latent space, mitigating task representation collapse and enabling robust, high-precision predictions for combination therapy design.

Shu-Ting Jin, Xu Guo, An-Qi Huang et al. · 0 citations
Book Open access Aug 2026

Concord: Building Consensus Representations for Single Cells with Collaborative Random Projection

Foundation models (FMs) have recently transformed single-cell genomics by learning transferable representations from large-scale single-cell data, enabling a wide range of downstream biomedical applications. Inspired by natural language processing, existing single-cell FMs adapt transformer architectures by treating ge...

Kaichen Xu, Mianpeng Liu, Hao Wu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.