publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Preprint
    Aligning One-Step Generative Models with Reward-Weighted Transport Distillation
    Austin Wang, Ziheng Cheng, and Lexing Ying
    arXiv preprint arXiv:2609.30840, 2026
  2. Preprint
    Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
    Austin Wang, Jiaqi Han, Stefano Ermon, and 1 more author
    arXiv preprint arXiv:2605.26491, 2026
  3. ICLR 2026
    Discrete diffusion trajectory alignment via stepwise decomposition
    Jiaqi Han*, Austin Wang*, Minkai Xu, and 6 more authors
    International Conference on Learning Representations (ICLR 2026), 2026
  4. TMLR
    Blade: A derivative-free bayesian inversion method using diffusion priors
    Hongkai Zheng*, Austin Wang*, Zihui Wu, and 3 more authors
    Transactions on Machine Learning Research (TMLR), 2026

2025

  1. ICLR 2025 Spotlight
    Inversebench: Benchmarking plug-and-play diffusion models for scientific inverse problems
    Hongkai Zheng*, Wenda Chu*, Bingliang Zhang*, and 9 more authors
    International Conference on Learning Representations (ICLR 2025) Spotlight, 2025
  2. TMLR
    Ensemble kalman diffusion guidance: A derivative-free method for inverse problems
    Hongkai Zheng, Wenda Chu*, Austin Wang*, and 3 more authors
    Transactions on Machine Learning Research (TMLR), 2025
  3. ICLR 2025 FPI
    Ensemble Kalman Sampling and Diffusion Prior in Tandem: A Split Gibbs Framework
    Austin Wang, Hongkai Zheng, Zihui Wu, and 3 more authors
    ICLR 2025 Workshop: Frontiers in Probabilistic Inference: Learning meets Sampling, 2025