Publications (17)
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
Runze Ma, Shunbo Jia, Haonan Lyu +2
The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VLMs of 2--4B parameters can run…
VCWorld: A Biological World Model for Virtual Cell Simulation
Zhijian Wei, Runze Ma, Zichen Wang +3
Virtual cell modeling aims to predict cellular responses to perturbations. Existing virtual cell models rely heavily on large-scale single-cell datasets, learning explicit mappings…
NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction
Zhongmin Li, Runze Ma, Jiahao Tan +2
Nucleotide sequence variation can induce significant shifts in functional fitness. Recent nucleotide foundation models promise to predict such fitness effects directly from sequenc…
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
Xiaoliang Shi, Zichen Wang, Runze Ma +2
Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progres…
BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Classification
Runze Ma, Caizhi Liao
Although deep learning has advanced automated electrocardiogram (ECG) diagnosis, prevalent supervised methods typically treat recordings as undifferentiated one-dimensional (1D) si…
Direct evidences of pentagonal silicon chains and magic clusters
Shaoxiang Sheng, Runze Ma, Jiangbin Wu +11
Pentagon is one of the most beautiful geometric structures in nature, but it is rarely seen simply because five-fold symmetry is mathematically forbidden in a 2D or 3D periodic lat…
REALM: Retrospective Encoder Alignment for LFP Modeling
Peicheng Wu, Zhenyu Bu, Runze Ma +1
Spike activity has been the dominant neural signal for behavior decoding due to its high spatial and temporal resolution. However, as brain-computer interfaces (BCIs) move toward h…
An Energy-Adaptive Elastic Equivariant Transformer Framework for Protein Structure Representation
Zhongyue Zhang, Runze Ma, Yanjie Huang +1
Structure-informed protein representation learning is essential for effective protein function annotation and \textit{de novo} design. However, the presence of inherent noise in bo…
CGGM: A conditional graph generation model with adaptive sparsity for node anomaly detection in IoT networks
Munan Li, Xianshi Su, Runze Ma +3
Dynamic graphs are extensively employed for detecting anomalous behavior in nodes within the Internet of Things (IoT). Graph generative models are often used to address the issue o…
TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance
Yue Tao, Zhiwei Jia, Runze Ma +1
Scene text recognition (STR) is an important bridge between images and text, attracting abundant research attention. While convolutional neural networks (CNNS) have achieved remark…
RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching
Runze Ma, Zhongyue Zhang, Zichen Wang +4
Ribonucleic acid (RNA) binds to molecules to achieve specific biological functions. While generative models are advancing biomolecule design, existing methods for designing RNA tha…
Exploration of Methods to Remove Implanted Pb and Po Contamination from Silicon Surfaces
Isaac J. Arnquist, Raymond Bunker, Zdenek Dohnalek +2
Radioactive contaminants on the surfaces of detector components can be a problematic source of background events for physics experiments searching for rare processes. Exposure to r…
Submolecular-resolution non-invasive imaging of interfacial water with atomic force microscopy
Jinbo Peng, Jing Guo, Prokop Hapala +8
Scanning probe microscopy (SPM) has been extensively applied to probe interfacial water in many interdisciplinary fields but the disturbance of the probes on the hydrogen-bonding s…
Stacking-Enhanced Bagging Ensemble Learning for Breast Cancer Classification with CNN
Peihceng Wu, Runze Ma, Teoh Teik Toe
This paper proposes a CNN classification network based on Bagging and stacking ensemble learning methods for breast cancer classification. The model was trained and tested on the p…
Fitness aligned structural modeling enables scalable virtual screening with AuroBind
Zhongyue Zhang, Jiahua Rao, Jie Zhong +22
Most human proteins remain undrugged, over 96% of human proteins remain unexploited by approved therapeutics. While structure-based virtual screening promises to expand the druggab…
SCOP: A Sequence-Structure Contrast-Aware Framework for Protein Function Prediction
Runze Ma, Chengxin He, Huiru Zheng +4
Improving the ability to predict protein function can potentially facilitate research in the fields of drug discovery and precision medicine. Technically, the properties of protein…
ODesign: A World Model for Biomolecular Interaction Design
Odin Zhang, Xujun Zhang, Haitao Lin +34
Biomolecular interactions underpin almost all biological processes, and their rational design is central to programming new biological functions. Generative AI models have emerged…