Gongye Liu

Preprint

Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling

Gongye Liu, Bo Yang, Yida Zhi, Zhizhou Zhong, Lei Ke, Didan Deng, Han Gao, Yongxiang Huang, Kaihao Zhang, Hongbo Fu, Wenhan Luo

Preprint, 2026

arXiv / Code

Diffusion-native reward modeling, improving efficiency while retaining performance.

NeurIPS 2025 Teaser

Flow-GRPO: Training Flow Matching Models via Online RL

Jie Liu*, Gongye Liu*, Jiajun Liang, Yangguang Li, Jiaheng Liu, Xintao Wang, Pengfei Wan, Di Zhang, Wanli Ouyang

NeurIPS, 2025

arXiv / Visualization / Code

GRPO on Flow Matching models. Achieving 0.95 on GenEval Benchmark.

NeurIPS 2025 Teaser

Improving Video Generation with Human Feedback

Jie Liu*, Gongye Liu*, Jiajun Liang, Ziyang Yuan, Xiaokun Liu, Mingwu Zheng, Xiele Wu, Qiulin Wang, Wenyu Qin, Menghan Xia, Xintao Wang, Xiaohong Liu, Fei Yang, Pengfei Wan, Di Zhang, Kun Gai, Yujiu Yang, Wanli Ouyang

NeurIPS, 2025

arXiv / Project Page / Dataset / Code

A systematic pipeline that leverages human feedback to improve the flow-based VDMs.

Preprint

Alignment of Diffusion and Flow-Matching Models for Visual Generation: A Survey

Gongye Liu, Bo Yang, Jie Liu, Yida Zhi, Kaihao Zhang, Wenhan Luo

Preprint, 2026

Paper / Paper List

A comprehensive survey on the recent development of alignment methods in diffusion and flow-matching models.

CVPR 2026

GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping

Jing Wang, Jiajun Liang, Jie Liu, Henglin Liu, Gongye Liu, Jun Zheng, Wanyuan Pang, Ao Ma, Zhenyu Xie, Xintao Wang, Meng Wang, Pengfei Wan, Xiaodan Liang

CVPR, 2026

arXiv / Project Page / Code

Mitigates implicit over-optimization in Flow-GRPO via regulated clipping.

CVPR 2026

FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories

Lei Ke, Hubery Yin, Gongye Liu, Zhengyao Lv, Jingcai Guo, Chen Li, Wenhan Luo, Yujiu Yang, Jing Lyu

CVPR, 2026

arXiv

Improves few-step rectified-flow distillation via online trajectory sampling.

ICLR 2026

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes

Yu Li, Menghan Xia, Gongye Liu, Jianhong Bai, Xintao Wang, Conglang Zhang, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Yujiu Yang

ICLR, 2026

arXiv / Project Page

Adapts video diffusion priors for viewpoint planning in 4D scenes.

TMLR 2025

Autoregressive Models in Vision: A Survey

Jing Xiong*, Gongye Liu*, Lun Huang, Chengyue Wu, Taiqiang Wu, Yao Mu, Yuan Yao, Hui Shen, Zhongwei Wan, Jinfa Huang, Chaofan Tao, Shen Yan, Huaxiu Yao, Lingpeng Kong, Hongxia Yang, Mi Zhang, Guillermo Sapiro, Jiebo Luo, Ping Luo, Ngai Wong

TMLR, 2025

arXiv / Paper List

A comprehensive survey on the recent development of visual autoregressive models.

ICLR 2025

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation

Chufan Shi, Cheng Yang, Yaxin Liu, Bo Shui, Junjie Wang, Mohan Jing, Linran Xu, Xinyu Zhu, Siheng Li, Yuxiang Zhang, Gongye Liu, Xiaomei Nie, Deng Cai, Yujiu Yang

ICLR, 2025

arXiv / Project / Code

A comprehensive benchmark for evaluating LMM's cross-modal reasoning capability via chart-to-code generation.

TOG 2024

StyleCrafter: Taming Stylized Video Diffusion with Reference-Augmented Adapter Learning

Gongye Liu, Menghan Xia, Yong Zhang, Haoxin Chen, Jinbo Xing, Yibo Wang, Xintao Wang, Ying Shan, Yujiu Yang

SIGGRAPH Asia (Journal Track), 2024

arXiv / Paper / Project Page / Code

Reference based Stylized Text-to-Image/Video Generation with Limited Stylized Data.

ECCV 2024

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, Tien-Tsin Wong

ECCV (Oral Presentation), 2024

arXiv / Project Page / Code

An Open-Domain High-Quality Image-to-Video Foundation Model.

IJCAI 2024 Cover

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

Gongye Liu, Haoze Sun, Jiayi Li, Fei Yin, Yujiu Yang

IJCAI, 2024

arXiv / Paper / Code / Poster

Zero-shot Image Restoration based on Diffusion.

Preprint 2024 Cover

LayoutDiT: exploring content-graphic balance in layout generation with diffusion transformer

Yu Li, Yifan Chen, Gongye Liu, Fei Yin, Qingyan Bai, Jie Wu, Hongfa Wang, Ruihang Chu, Yujiu Yang

Preprint, 2024