Chaotian Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chaotian Song has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Boxi Wu
Zhejiang University
2 shared publications - Deng Cai
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
2 shared publications - Chenghao Chen
Rajax Network Technology, Taobao Shangou of Alibaba, Hangzhou, China
1 shared publication - Dehai Zhao
Zhejiang University, Hangzhou, China
1 shared publication - Guodong Cao
Rajax Network Technology, Taobao Shangou of Alibaba, Beijing, China
1 shared publication - Hengjia Li
State Key Laboratory of CADCG, Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7957-7966
DeGRe: Dense-supervised Generative Reranking for Recommendation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7957-7966
Open AccessDeGRe: Dense-supervised Generative Reranking for Recommendation
- Top Cited Papers
- 20 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 8145-8158
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fusion matrix of multiple Low-Rank Adaptations (LoRAs) to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, where the model struggles to preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through concept injection constraints, enhancing visibility via an expanded cross-attention mechanism. To combat concept confusion, concept isolation constraints are introduced, refining the self-attention computation. Furthermore, we propose two inference techniques to accelerate inference speed without performance degradation and enhance the accuracy of the generated region, respectively. Extensive experiments demonstrate that LoRA-Composer significantly outperforms standard baselines, especially in scenarios without image-based conditions such as canny edge or pose estimation.
- 20 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 8145-8158
Top Cited PapersLoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fusion matrix of multiple Low-Rank Adaptations (LoRAs) to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, where the model struggles to preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through concept injection constraints, enhancing visibility via an expanded cross-attention mechanism. To combat concept confusion, concept isolation constraints are introduced, refining the self-attention computation. Furthermore, we propose two inference techniques to accelerate inference speed without performance degradation and enhance the accuracy of the generated region, respectively. Extensive experiments demonstrate that LoRA-Composer significantly outperforms standard baselines, especially in scenarios without image-based conditions such as canny edge or pose estimation.