Shuchen Xue

scxue.jpg

I am a final-year Ph.D. student in Statistics at the University of Chinese Academy of Sciences (UCAS) and Academy of Mathematics and Systems Science (AMSS), CAS, advised by Prof. Zhi-Ming Ma. My work aims to bridge the theory and practice of scalable generative models, with a focus on efficient training and inference algorithms. I’m currently working on post-training of diffusion models.

Currently, I am a research intern at ByteDance Seed Vision & Seed Edge. I was previously a research intern at Adobe Research, supervised by Chongjian Ge, a visiting student at Columbia University, and a research intern at the AI Theory Group in Noah’s Ark Lab, where I worked closely with Mingyang Yi, Tianyang Hu, Zhaoqiang Liu, Enze Xie. I received my B.S. degree in Mathematics from the University of Chinese Academy of Sciences (UCAS).

I will be graduating in Summer 2026 and am actively seeking full-time positions. I’m excited to connect and discuss potential opportunities.

news

Jan 26, 2026 Three papers were accepted by ICLR 2026.
Nov 10, 2025 Thrilled to begin my internship at Bytedance Seed.
Sep 29, 2025 Advantage Weighted Matching, a principled RL method for diffusion and flow models, is released. Check out our paper and code.
Jul 23, 2025 One paper was selected as Highlight by ICCV 2025.
Jul 07, 2025 One paper was selected as Oral Presentation by ICML 2025 (ES-FoMo workshop) (Top 3.42%).

selected publications

  1. arXiv
    Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
    Shuchen Xue, Chongjian Ge, Shilong Zhang, and 2 more authors
    2025
    arXiv Code
  2. ICML WorkshopOral
    Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
    Shuchen Xue, Tianyu Xie, Tianyang Hu, and 5 more authors
    ICML 2025 ES-FoMo workshop Oral Presentation (Top 3.42%) , 2025
    arXiv Code
  3. ICLR
    Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
    Chengyue Wu*, Hao Zhang*, Shuchen Xue, and 6 more authors
    2025
    arXiv Code Website
  4. ICLR
    Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
    Tianyu Xie, Shuchen Xue, Zijin Feng, and 4 more authors
    2025
    arXiv
  5. arXiv
    Graffe: Graph Representation Learning via Diffusion Probabilistic Models
    Dingshuo Chen*, Shuchen Xue*, Liuji Chen, and 5 more authors
    2025
    arXiv
  6. ICCVHighlight
    SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
    Junsong Chen*, Shuchen Xue*, Yuyang Zhao, and 6 more authors
    2025
    arXiv Code Website
  7. CVPR
    Accelerating Diffusion Sampling with Optimized Time Steps
    Shuchen Xue, Zhaoqiang Liu, Fei Chen, and 4 more authors
    2024
    arXiv Code
  8. NeurIPS
    SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
    Shuchen Xue, Mingyang Yi, Weijian Luo, and 4 more authors
    2023
    arXiv Code
 

    Total site views:  |      Site visitors: