Xidian University

4 related articles

researchsquare.com Oct 22, 2026
Single-cell 3D genome boundaries survive sparse data: cross-cell alignment lets boundary strength split an embryo subpopulation RNA could not
Single-cell 3D genome data are so sparse that domain boundaries are hard to call reliably, and positional disagreement across cells blocks comparison of boundary frequency and strength. CellRoB couples single-cell boundary detection with cross-cell alignment that minimizes an insulation-score loss, improving boundary accuracy and robustness to contact dropout on mouse brain Dip-C and human GM12878 scMicro-C data from 40 kb down to 5 kb. On multimodal mouse embryo data, boundary-strength profiles split the EPI cells that the RNA embedding left as one group.
Single-cell 3D genome data are so sparse that domain boundaries are hard to call reliably, and positional disagreement across cells blocks comparison of boundary frequency and strength. CellRoB couples single-cell boundary detection with cross-cell alignment that minimizes an insulation-score loss, improving boundary accuracy and robustness to contact dropout on mouse brain Dip-C and human GM12878 scMicro-C data from 40 kb down to 5 kb. On multimodal mouse embryo data, boundary-strength profiles split the EPI cells that the RNA embedding left as one group.
Xidian University Shiji Liu Lin Gao Yusen Ye
Single-Cell 3D Genome Domain Boundary Rare and Conserved Boundary Classification CellRoB Single-Cell Domain Boundary Detection
researchsquare.com Oct 22, 2026
Co-frequency signal separation at 235K parameters: complex attention cuts collapse and keeps phase
Single-channel blind separation of co-frequency communication signals has relied on real-valued networks or attention modules blind to complex structure, which cannot exploit the phase coupling between the I and Q rails. ComplexLightweightSepNet embeds a complex squeeze-and-excitation block in a complex convolutional encoder-decoder, scaling complex features with a real-valued channel weight that preserves phase, at 235,525 parameters. On 5 Hz co-frequency synthetic mixtures across four modulations it reaches a five-seed mean SDR of 2.31 dB with 0.62 dB standard deviation; paired Wilcoxon tests do not reach alpha = 0.05, so the result is positioned as a working point at the 235K scale, not an inferred advantage.
Single-channel blind separation of co-frequency communication signals has relied on real-valued networks or attention modules blind to complex structure, which cannot exploit the phase coupling between the I and Q rails. ComplexLightweightSepNet embeds a complex squeeze-and-excitation block in a complex convolutional encoder-decoder, scaling complex features with a real-valued channel weight that preserves phase, at 235,525 parameters. On 5 Hz co-frequency synthetic mixtures across four modulations it reaches a five-seed mean SDR of 2.31 dB with 0.62 dB standard deviation; paired Wilcoxon tests do not reach alpha = 0.05, so the result is positioned as a working point at the 235K scale, not an inferred advantage.
University of Shanghai for Science and Technology Tianfu College of SWUFE Xidian University 付卫红 Bin Nong Zuo Jiang
Complex Squeeze-and-Excitation Attention Convolutional Neural Network Blind Source Separation Complex-Valued Neural Network
arXiv Sep 25, 2026
VA-Adapter lets an ultrasound foundation model guide the echo probe, cutting trained parameters about 33-fold while lowering guidance error below strong baselines
The work proposes a Vision-Action Adapter (VA-Adapter) inserted into the deep layers of a frozen ultrasound foundation model image encoder (EchoCLIP, USFM, BiomedCLIP) to online-inject understanding of individual 3D cardiac structure by encoding historical vision-action sequences; on a dataset of 178 adults, 356 expert scans and 1.31M image-action pairs, it reaches lower translation and rotation mean absolute error than strong probe-guidance baselines with roughly 2.61M-3.97M trainable parameters.
The work proposes a Vision-Action Adapter (VA-Adapter) inserted into the deep layers of a frozen ultrasound foundation model image encoder (EchoCLIP, USFM, BiomedCLIP) to online-inject understanding of individual 3D cardiac structure by encoding historical vision-action sequences; on a dataset of 178 adults, 356 expert scans and 1.31M image-action pairs, it reaches lower translation and rotation mean absolute error than strong probe-guidance baselines with roughly 2.61M-3.97M trainable parameters.
Beijing Academy of Artificial Intelligence Tsinghua University Chinese PLA General Hospital Xidian University Zhenguo Sun Gao Ming Huang Shiji Song Haojun Jiang Teng Wang Yuxuan Wang
Cardiac Valve Diseases and Treatments Cardiovascular Function and Risk Factors Ultrasound in Clinical Applications
Bioinformatics Sep 18, 2026
Regulatory-prior-guided attention preserves biological structure during unpaired single-cell RNA-ATAC integration
The work presents scHPGT, a single-cell Heterogeneous Prior-Guided Transformer that integrates unpaired RNA and chromatin accessibility profiles in a shared latent space using modality-specific encoders, a prior-guided cross-modal Transformer that constrains gene-peak attention with regulatory links, and a domain-adversarial objective, improving clustering agreement, label transfer and biological structure preservation across PBMC3k, mouse spleen, CITE-seq/ASAP-seq PBMC and PBMC10k benchmarks while avoiding forced correspondence of unmatched or condition-specific states in partial-overlap and condition-shift settings, with attention-derived links recovering regulatory relationships, marker-gene regulatory regions, transcription factor programs and regulatory activity profiles.
The work presents scHPGT, a single-cell Heterogeneous Prior-Guided Transformer that integrates unpaired RNA and chromatin accessibility profiles in a shared latent space using modality-specific encoders, a prior-guided cross-modal Transformer that constrains gene-peak attention with regulatory links, and a domain-adversarial objective, improving clustering agreement, label transfer and biological structure preservation across PBMC3k, mouse spleen, CITE-seq/ASAP-seq PBMC and PBMC10k benchmarks while avoiding forced correspondence of unmatched or condition-specific states in partial-overlap and condition-shift settings, with attention-derived links recovering regulatory relationships, marker-gene regulatory regions, transcription factor programs and regulatory activity profiles.
Baylor College of Medicine Children's Cancer Center Texas Children's Hospital Xidian University Zhenglong Cheng Jiao Zhang Shixiong Zhang

You’re all caught up

Single-cell 3D genome boundaries survive sparse data: cross-cell alignment lets boundary strength split an embryo subpopulation RNA could not

Co-frequency signal separation at 235K parameters: complex attention cuts collapse and keeps phase

VA-Adapter lets an ultrasound foundation model guide the echo probe, cutting trained parameters about 33-fold while lowering guidance error below strong baselines

Regulatory-prior-guided attention preserves biological structure during unpaired single-cell RNA-ATAC integration