I work on two axes: AI for Science and Science for AI.

AI for Science means methods, benchmarks, and open software that accelerate research. Science for AI means harnesses, orchestration, telemetry, and evaluation that make AI usable for serious work.

The publications below are application proof — evidence I can design, validate, write, and ship. Domain case work (including earlier single-cell studies) is not the identity.

Background : Direct Ph.D. track → Present
Identity : AI for Science · Science for AI
Proof channel : Peer-reviewed papers, packages, public tools
Systems work : Agent harnesses · orchestration · telemetry · QA
Stack : TypeScript/Node · Python · Shell · plugins/skills · GitHub Actions
Open to : AI scientist systems, research tooling, industry collaboration

^# Equal contribution ^* Corresponding author

Fu, Z.^#,*, Chen, C.^#, Zhang, K. (2026). Islands and bridges: Momentum contrastive coupling unifies discrete and continuous structure in single-cell omics. Biomedical Signal Processing and Control, 122, 110376.

Fu, Z.^#,*, Liu, Y.^#, Wang, J., Wang, S. (2026). CCVGAE: A centroid-coupled variational graph attention autoencoder for stable and interpretable single-cell representation learning. Array, 30, 100808.

Fu, Z.^#,*, Liu, Y.^#, Wang, J., Wang, S. (2026). CLOP-DiT: Structured-metadata-conditioned single-cell latent generation via contrastive language-omics pretraining and Diffusion Transformers. Array, 100934 (in press).

Fu, Z.^#,*, Fu, J.^#, Wang, X.^#, Liu, Y.^*, Ran, T.^* (2026). GAHIB: Graph Attention VAE with a Hyperbolic Information Bottleneck for Biologically Structured Single-Cell Representations. Frontiers in Genetics.

Fu, Z.^#, Fu, J.^#, Chen, C.^#, Zhang, K., Wang, J.^*, Ran, T.^*, Wang, S.^* (2026). scCCVGBen for Benchmarking of Single-Cell Representation Learning Anchored on a Centroid-Coupled Variational Graph Attention Autoencoder across scRNA-seq and scATAC-seq. Frontiers in Genetics.

Fu, Z.^#,*, Fu, J.^#, Zhang, K., Ran, T.^*, Chen, C.^* (2026). LAIOR: A Hyperbolic Neural ODE Variational Framework for Interpretable Single-Cell Manifold Learning and Trajectory Inference. Frontiers in Genetics.

Fu, Z.^#,*, Chen, C.^#, Wang, S. et al. (2025). iVAE: An Interpretable Representation Learning Framework Enhancing Clustering Performance for Single-Cell Data. BMC Biology, 23, 213.

Fu, Z.^#,*, Chen, C.^#, Wang, S. et al. (2026). iAODE for Benchmarking and Continuum Modeling of Single-Cell Chromatin Accessibility. Communications Biology.

Fu, Z.^#,*, Chen, C.^# (2025). Correlated Latent Space Learning for Structural Differentiation Modeling in Single Cell RNA Data. Computers in Biology and Medicine, 198(A), 111115.

Fu, Z.^#,*, Chen, C.^#, Wang, S. et al. (2025). GNODEVAE: A Graph-Based ODE-VAE Enhances Clustering for Single-Cell Data. BMC Genomics, 26, 767.

Chen, C.^#, Fu, Z.^#,*, Yang, J. et al. (2025). scFocus: Detecting Branching Probabilities in Single-cell Data with SAC. Computational and Structural Biotechnology Journal, 27, 2243--2263.

Fu, Z.^#,*, Fu, J.^#, Chen, C.^# et al. (2026). Lorentz-Regularized Interpretable VAE for Multi-Scale Single-Cell Transcriptomic and Epigenomic Embeddings. Frontiers in Genetics, 16, 1713727.

Fu, Z.^#, Chen, C.^#, Wang, S. et al. (2025). scRL: Utilizing Reinforcement Learning to Evaluate Fate Decisions in Single-Cell Data. Biology, 14(6), 679.