Skip to main content
Search

Central South University

11 related articles

Subscribe to updates
  1. bioRxiv

    Paired transcriptome and 3D genome from one cell: scHiR fuses two sparse modalities into a single cell embedding

    Technologies that simultaneously sequence single-cell transcriptome and 3D genome already yield paired measurements from the same cell, but the two modalities differ sharply in noise, scale and biological meaning, and were previously analyzed separately with latent spaces that need not align. scHiR maps gene expression and chromatin contact matrices into one hyperspherical latent space through modality-specific encoders and reconstructs both signals. On paired data from HiRES, GAGE-seq and LiMCA, the joint embedding matched or exceeded single-omics methods in clustering, and on mouse main olfactory epithelium it raised the Spearman correlation between pseudotime and developmental stage from 0.357 and 0.205 for single-omics embeddings to 0.517.

  2. medRxiv

    Fetal ultrasound screening learns from scarce labels: RadarMAE's radar-style masking holds cross-hospital metric drops to 0.04

    First-trimester ultrasound images for Down syndrome screening are low-resolution and structurally variable, and confirmed rare cases are scarce, so standard self-supervised pretraining struggles. RadarMAE instead masks alternating concentric rings and angular sectors, a radar-like pattern that forces the network to learn the continuous curvature and elongated shapes of craniofacial structures, reaching AUC 0.99 and 97% accuracy on an internal cohort. With domain-adversarial adaptation, the model calibrates on unlabeled images from four external hospitals and limits the drop in key metrics to 0.04 or less.

  3. Skin microbiome catalog fills a reference-genome gap: 452,000 genomes, most species previously unrepresented

    Reference genomes for the human skin microbiome have been scarce, especially outside bacteria and across global strain variation. The Global Skin Metagenomic Data resource combined 12,409 newly sequenced and 4,396 public skin metagenomes with 3,077 isolate genomes to reconstruct 452,397 metagenome-assembled genomes and add 42,758 previously uncharacterized taxa. From 1.71 billion predicted protein sequences it consolidated 1,272,886 protein families, 79,434 of which had no homology hit in Pfam or RefSeq.

  4. arXiv

    Mixed-variable experiments stop leaning on structure alone: LLM ranking priors plus structural smoothing reach near-optimal candidates faster on six chemistry and materials tasks

    TagBO treats candidate rankings produced by a large language model as coarse task-aware priors and fuses them with local structural smoothing into a similarity graph, reaching high-quality candidates in fewer evaluations under a fixed budget on six mixed-variable chemistry and materials optimization tasks.

  5. arXiv

    Robots stop swallowing every experience whole: keeping only human-controlled segments of successful interventions lifts precision insertion success to 88.24%

    Evo-RL filters deployment experience by estimated advantage before policy fine-tuning, raising attempt success rate on a real PiperX high-precision screw-insertion task from RECAP's 57.78% to 88.24%.

  6. arXiv

    Skeleton action recognition gets a quantization plug-in: white-box attack success drops from near 100% to single digits, accuracy stays comparable

    Mainstream contrastive models for self-supervised skeleton-based action recognition had almost no defense against adversarial attacks, where tiny perturbations to skeleton data could sharply degrade recognition. QCLR adds quantization as a plug-in module at two levels of the encoding pipeline, mapping continuous inputs and features to discrete codebooks so small perturbations are absorbed and gradient propagation is broken; integrated into SkeletonCLR, AimCLR and ActCLR on NTU-60, NTU-120 and PKU-MMD, it cuts PGD and SMART attack success rates to single digits while keeping classification accuracy comparable to the original models.

  7. FedFit cuts federated LoRA fine-tuning communication by up to 100x while matching standard federated LoRA perplexity via dual vector-bank parameterization and quantization

    FedFit targets the large communication overhead of federated fine-tuning of large language models and the LoRA aggregation dilemma between accurate Sum-of-Products (SoP) and communication-efficient Product-of-Sums (PoS); it reconstructs high-dimensional adapter matrices from two compact, disjoint global vector banks, alternates between decoupled single-bank updates and joint updates corrected by a Residual Spectral Aggregation mechanism, and adds blockwise quantization with client-side error feedback, achieving perplexity comparable to standard federated LoRA on Qwen2.5 models with compression ratios up to 100x higher, alongside theoretical convergence guarantees.

  8. arXiv

    ZJU team releases EMem-Bench: across 2,554 long-horizon embodied episodes the strongest model Gemini-3-Flash reaches only 64.2% average success, while its EMem memory system lifts GPT-5.4-mini by 23.6 points

    The OmniAI Group of ZJU ACES Lab introduces EMem-Bench, a long-horizon embodied memory benchmark of 2,554 executable episodes spanning Passive Observation, Dynamic Tracking, Interaction Failure, and Experience Generalization, together with an external memory system EMem and an 8B policy EMem-8B; evaluating 16 open-source and proprietary MLLMs plus representative multimodal memory systems shows the strongest proprietary model Gemini-3-Flash reaches only 64.2% average success rate and most open-source models fall below 45%, while EMem achieves the best overall performance among matched backbones, improving Mistral-Small-3.1-24B by 16.4 points and GPT-5.4-mini by 23.6 points, with EMem-8B improving over Qwen3-VL-8B by 20.6 points.

  9. Random Forest and SVM-RBF target gold at Wadi Umm Eish El-Zarqa, Egypt using EnMAP hyperspectral data, with RF achieving perfect precision and 37% more high-confidence targets

    In the Wadi Umm Eish El-Zarqa area of Egypt, this study for the first time combines machine learning with EnMAP hyperspectral data, training Random Forest (RF) and Support Vector Machine with Radial Basis Function (SVM-RBF) models on pixel spectra from three known gold mining sites and expanding the training set with a 0.05 spectral probability tolerance, while using ALOS-PALSAR DEM to extract drainage networks linking upstream bedrock sources to downstream placers; ground-truth validation showed SVM-RBF had slightly higher overall accuracy (91.8% vs 89.

  10. Biparametric MRI Radiomics Combined with Serum Bone Turnover Biomarkers for Predicting Postoperative Bone Metastasis in Prostate Cancer: Precision Selection for Targeted Radionuclide Therapy

    In a prospective single-center cohort of 143 patients with clinically localized prostate cancer (cT1-2N0M0) undergoing laparoscopic radical prostatectomy, the study measured preoperative serum bone metabolism indicators such as osteocalcin N-terminal mid-fragment and alkaline phosphatase, extracted biparametric MRI radiomics variables including apparent diffusion coefficient mean and K trans mean, and integrated serum and imaging biomarkers with a multivariate logistic regression model; the integrated model reached an area under the ROC curve of 0.984, significantly outperforming individual biomarkers and imaging features (all p < 0.001), showed clinical net benefit with strong calibration (Hosmer-Lemeshow test p = 0.