publications

Jieke (Jack) Wu's publications — papers on generative models, training-free methods, and AI for science.

2026

  1. Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
    Hantao Zhang, Jieke Wu, Mingda Xu, and 3 more authors
    arXiv preprint arXiv:2603.06615, 2026
  2. D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob’s h-Transform
    Jieke Wu, Qijie Zhu, Weimin Wu, and 3 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
  3. AnchorGen: Anchored Optimization for Customizable Generative 3D Design
    Hantao Zhang, Oliver Heinimann, Jieke Wu, and 3 more authors
    arXiv preprint arXiv:2610.06135, 2026

2025

  1. GenomeOcean: Efficient Foundation Model for Genome Generation
    Zhihan Zhou, Weimin Wu, Jieke Wu, and 3 more authors
    arXiv preprint, 2025

2024

  1. Training-free Design of Augmentations with Data-centric Principles
    Jieke Wu, Wei Huang, Mingyuan Bai, and 3 more authors
    In ICML 2024 AI for Science Workshop, 2024
  2. Training-free Design of Deep Networks as Ensembles of Clinical Experts
    Tinghui Wu, Jieke Wu, Zijun Zhang, and 1 more author
    medRxiv, 2024