Cheng Wan

myprofile.png

Hi there! I’m an ECE Ph.D. student at Cornell University, and I’m honored to be advised by Mert Sabuncu and Qingyu Zhao. In Summer 2026, I was a research intern on the Adobe Firefly foundation model team, working on large-scale pre-training and post-training of generative models. Previously, I worked on computer vision at CMU and on AI for healthcare at Georgia Tech and Emory.

Research Interests: Generative modeling (diffusion / flow matching, image & video generation), multimodal reasoning, and foundation-model pre-/post-training (on-policy distillation, RL), with applications to medical imaging.

Experience

Adobe – Firefly Foundational Models Team May 2026 – Aug 2026
Research Intern
Large-scale pre-training of generative foundation models; post-training with on-policy distillation (OPD) and RL.

Publications

  1. ropsd.png
    R-OPSD: Realizable On-Policy Self-Distillation for Diffusion Models
    Cheng Wan, Xiaoyan Cong, Zhiqi Li, Zhexiao Xiong, Yiyang Fan, Ajinkya Kale, Qingyu Zhao, and Huijuan Huang
    Under review, 2026
  2. adaopd.png
    AdaOPD: Mitigating Language-Style Gap in On-Policy Distillation for Medical VLM Post-Training
    Cheng Wan, Chenjun Li, Haomiao Chen, Rachit Saluja, Fengbei Liu, Johannes C. Paetzold, and Qingyu Zhao
    Under review, 2026
  3. prism_bench.png
    Cheng Wan, Yusu Qian, and Qingyu Zhao
    NeurIPS 2026
  4. ag_ldm.png
    Cheng Wan, Bahram Jafrasteh, Ehsan Adeli, Miaomiao Zhang, and Qingyu Zhao
    IEEE Trans. on Medical Imaging (TMI)
  5. flowmap_opd.png
    FlowMap-OPD: Decoupling Rollout and Supervision for Few-Step Flow-Map Generators
    Zhiqi Li, Cheng Wan, and Bo Zhu
    Under review, 2026
  6. unpair.png
    Cheng Wan, Chenjun Li, and Qingyu Zhao
    Under review, 2026

Academic Service

Reviewer: NeurIPS (2024–2026), ICLR (2025–2026), ICML (2025), AISTATS (2025–2026)
Workshop Reviewer: NeurIPS AI4Science (2025–2026), NeurIPS SPIGM (2025–2026), ICML AI4Science (2024)

Teaching

  • Teaching Assistant (Co-lecturer), ECE 5200/3200: Foundations of Machine Learning, Cornell University Spring 2025