Peking UniversityI am a third-year Ph.D. candidate at Peking University (PKU), advised by Prof. Yunhai Tong. Before that, I received my B.S. degree from Beijing Institute of Technology (BIT) in 2023.
My research focuses on multimodal generation, particularly diffusion models, visual tokenization, and unified multimodal models.
Education
-
Peking UniversitySchool of Intelligence Science and Technology
Ph.D. StudentSep. 2023 - present -
Beijing Institute of TechnologyB.S. in School of Mathematics and StatisticsSep. 2019 - Jul. 2023
Experience
-
TencentQingyun Research Intern (Incoming)Aug. 2026 -
ByteDanceResearch InternDec. 2025 - Jul. 2026 -
TeleAIResearch InternMar. 2025 - Dec. 2025
Academic Service
- Conference Reviewer
CVPR, ECCV, ICCV, NeurIPS, ICML, ICLR
Honors & Awards
-
CETC The 14TH Research Institute Glarun Scholarship2024
-
Merit Student2024
-
Beijing Excellent Graduates2023
-
National Scholarship2022
-
National Scholarship2021
News
Selected Projects and Papers (view all )
RecTok: Reconstruction Distillation along Rectified Flow
Qingyu Shi, Size Wu, Jinbin Bai, Kaidong Yu, Yujing Wang, Yunhai Tong, Xiangtai Li, Xuelong Li
CVPR 2026 Poster
We introduce RecTok, a visual tokenizer trained with reconstruction distillation along rectified flow. It improves the balance between perceptual reconstruction and generation quality, enabling strong image generation with diffusion transformers.
RecTok: Reconstruction Distillation along Rectified Flow
Qingyu Shi, Size Wu, Jinbin Bai, Kaidong Yu, Yujing Wang, Yunhai Tong, Xiangtai Li, Xuelong Li
CVPR 2026 Poster
We introduce RecTok, a visual tokenizer trained with reconstruction distillation along rectified flow. It improves the balance between perceptual reconstruction and generation quality, enabling strong image generation with diffusion transformers.
Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model
Qingyu Shi, Jinbin Bai, Zhuoran Zhao, Wenhao Chai, Kaidong Yu, Jianzong Wu, Shuangyong Song, Yunhai Tong, Xiangtai Li, Xuelong Li, Shuicheng YAN
ICLR 2026 Poster
We introduce Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities. Empirical results show that Muddit achieves competitive or superior performance compared to significantly larger autoregressive models in both quality and efficiency.
Beyond Text-to-Image: Liberating Generation with a Unified Discrete Diffusion Model
Qingyu Shi, Jinbin Bai, Zhuoran Zhao, Wenhao Chai, Kaidong Yu, Jianzong Wu, Shuangyong Song, Yunhai Tong, Xiangtai Li, Xuelong Li, Shuicheng YAN
ICLR 2026 Poster
We introduce Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities. Empirical results show that Muddit achieves competitive or superior performance compared to significantly larger autoregressive models in both quality and efficiency.
Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer
Qingyu Shi, Jianzong Wu, Jinbin Bai, Jiangning Zhang, Lu Qi, Yunhai Tong, Xiangtai Li
ICCV 2025 Poster
In this paper, we propose DeT, a method that adapts DiT models to improve motion transfer ability. Our approach introduces a simple yet effective temporal kernel to smooth DiT features along the temporal dimension, facilitating the decoupling of foreground motion from background appearance.
Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer
Qingyu Shi, Jianzong Wu, Jinbin Bai, Jiangning Zhang, Lu Qi, Yunhai Tong, Xiangtai Li
ICCV 2025 Poster
In this paper, we propose DeT, a method that adapts DiT models to improve motion transfer ability. Our approach introduces a simple yet effective temporal kernel to smooth DiT features along the temporal dimension, facilitating the decoupling of foreground motion from background appearance.
DreamRelation: Bridging Customization and Relation Generation
Qingyu Shi, Lu Qi, Jianzong Wu, Jinbin Bai, Jingbo Wang, Yunhai Tong, Xiangtai Li
CVPR 2025 Oral
We introduce DreamRelation, a framework that disentangles identity and relation learning using a carefully curated dataset. Our training data consists of relation-specific images, independent object images containing identity information, and text prompts to guide relation generation. Extensive results on our proposed benchmarks demonstrate the superiority of DreamRelation in generating precise relations while preserving object identities across a diverse set of objects and relationships.
DreamRelation: Bridging Customization and Relation Generation
Qingyu Shi, Lu Qi, Jianzong Wu, Jinbin Bai, Jingbo Wang, Yunhai Tong, Xiangtai Li
CVPR 2025 Oral
We introduce DreamRelation, a framework that disentangles identity and relation learning using a carefully curated dataset. Our training data consists of relation-specific images, independent object images containing identity information, and text prompts to guide relation generation. Extensive results on our proposed benchmarks demonstrate the superiority of DreamRelation in generating precise relations while preserving object identities across a diverse set of objects and relationships.