Yuanzhi Zhu

Full Publications

Pre-prints

• Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky Kalogeiton.
  Diffusion Reinforcement Learning via Centered Reward Distillation, Arxiv. arxiv: 2603.14128 [paper] [arxiv] [code] [blog]

• Minh-Quan Le, Yuanzhi Zhu, Vicky Kalogeiton, Dimitris Samaras.
  What about gravity in video generation? Post-Training Newton’s Laws with Verifiable Rewards, Arxiv. arxiv: 2512.00425 [paper] [arxiv]

• Yuanzhi Zhu, Eleftherios Tsonis, Lucas Degeorge, Vicky Kalogeiton.
  One-step Diffusion Models with Bregman Density Ratio Matching, Arxiv. arxiv: 2510.16983 [paper] [arxiv] [blog]

• Yuanzhi Zhu, Hanshu Yan, Huan Yang, Kai Zhang, Junnan Li.
  Accelerating Video Diffusion Models via Distribution Matching, Arxiv. arxiv: 2412.05899 [paper] [arxiv]

Conferences

• Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky Kalogeiton.
  Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings, ICLR (2026). arxiv: 2509.22925 [paper] [arxiv] [code] [slides] [poster]

• Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky Kalogeiton.
  Di[M]O: Distilling Masked Diffusion Models into One-Step Generator, ICCV (2025). arxiv: 2503.15457 [paper] [arxiv] [code] [slides] [poster]

• Yuanzhi Zhu*, Ruiqing Wang*, Shilin Lu, Junnan Li, Hanshu Yan, Kai Zhang.
  OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs, ICLR (2026). arxiv: 2412.09465 [paper] [arxiv] [code] [slides] [poster]

• Yuqing Wang, Zhijie Lin, Yao Teng, Yuanzhi Zhu, Shuhuai Ren, Jiashi Feng, Xihui Liu.
  Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation, ICCV (2025) arxiv: 2503.1643 [paper] [arxiv]

• Shilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, Adams Wai-Kin Kong.
  Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances, ICLR (2025) arxiv: 2410.18775 [paper] [arxiv]

• Boqi Chen, Yuanzhi Zhu, Yunke Ao, Sebastiano Caprara, Reto Sutter, Gunnar Rätsch, Ender Konukoglu, Anna Susmelj.
  Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms, WACV (2025). arxiv: 2411.05223 [paper] [arxiv]

• Yuanzhi Zhu, Xingchao Liu, Qiang Liu.
  SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow, ECCV (2024). arxiv: 2407.12718 [paper] [arxiv] [code] [poster]

• Zixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang, Shuang Xu, Yulun Zhang, Kai Zhang, Deyu Meng, Radu Timofte, Luc Van Gool.
  DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion, ICCV (2023), Oral arxiv: 2303.0684 [paper] [arxiv]

• Jun Ma, Yuanzhi Zhu, Chenyu You, Bo Wang.
  Pre-trained Diffusion Models for Plug-and-Play Medical Image Enhancement, MICCAI (2023) [paper]

• Yuanzhi Zhu, Kai Zhang, Jingyun Liang, Jiezhang Cao, Bihan Wen, Radu Timofte, Luc Van Gool.
  Denoising Diffusion Models for Plug-and-Play Image Restoration, CVPRW (2023). arxiv: 2305.08995 [paper] [arxiv] [code] [slides] [poster]

Journals

• Hayato Mizuno, Hironari Isshiki, Kouta Kondou, Yuanzhi Zhu, and Yoshichika Otani.
  Influence of Planar Hall Effect on the Output Signal in a T-shaped Spin Conversion Device,

• Zhizhong Zhang*, Yuanzhi Zhu*, Yue Zhang, Weisheng Zhao, et al.
  Skyrmion-Based Ultra-Low Power Electric-Field-Controlled Reconfigurable (SUPER) Logic Gate,