Buhua Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Buhua Liu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Bao Li
Chinese Academy of Sciences Institute of Automation
1 shared publication - Haoyi Xiong
Baidu Inc., Beijing, China
1 shared publication - James Tin-Yau Kwok
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China
1 shared publication - Lichen Bai
The Hong Kong University of Science and Technology - Guangzhou Campus
1 shared publication - Mengke Li
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
1 shared publication - Qing Xu
Institute For Infocomm Research, Agency for Science, Technology and Research (ASTAR), Singapore
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 10 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (9) , 1-37
Alignment of Diffusion Models: Fundamentals, Challenges, and Future
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions and generate results with undesired properties or even harmful content. Inspired by the success and popularity of alignment in tuning large language models, recent studies have investigated aligning diffusion models with human expectations and preferences. This work mainly reviews alignment of diffusion models, covering advancements in fundamentals of alignment, alignment techniques of diffusion models, preference benchmarks, and evaluation for diffusion models. Moreover, we discuss key perspectives on current challenges and promising future directions on solving the remaining challenges in alignment of diffusion models. To the best of our knowledge, our work is the first comprehensive review paper for researchers and engineers to comprehend, practice, and research alignment of diffusion models.
- 10 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (9) , 1-37
Top Cited PapersOpen AccessAlignment of Diffusion Models: Fundamentals, Challenges, and Future
Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions and generate results with undesired properties or even harmful content. Inspired by the success and popularity of alignment in tuning large language models, recent studies have investigated aligning diffusion models with human expectations and preferences. This work mainly reviews alignment of diffusion models, covering advancements in fundamentals of alignment, alignment techniques of diffusion models, preference benchmarks, and evaluation for diffusion models. Moreover, we discuss key perspectives on current challenges and promising future directions on solving the remaining challenges in alignment of diffusion models. To the best of our knowledge, our work is the first comprehensive review paper for researchers and engineers to comprehend, practice, and research alignment of diffusion models.
- Open Access
- 11 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1377-1388
Improve Knowledge Distillation via Label Revision and Data Selection
Knowledge distillation (KD) transferring knowledge from a large teacher model to a lightweight student one has received great attention in deep model compression. In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model. Based on vanilla KD, various approaches have been developed to further improve the performance of the student model. However, few of these previous methods have considered the reliability of the supervision from teacher models. Supervision from erroneous predictions may mislead the training of the student model. This paper therefore proposes to tackle this problem from two aspects: Label Revision to rectify the incorrect supervision and Data Selection to select appropriate samples for distillation to reduce the impact of erroneous supervision. In the former, we propose to rectify the teacher’s inaccurate predictions using the ground truth. In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher, thereby reducing the impact of incorrect predictions to some extent. Experiment results demonstrate the effectiveness of the proposed method, which can be further combined with other distillation approaches to enhance their performance.
- 11 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 17 (6) , 1377-1388
Open AccessImprove Knowledge Distillation via Label Revision and Data Selection
Knowledge distillation (KD) transferring knowledge from a large teacher model to a lightweight student one has received great attention in deep model compression. In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model. Based on vanilla KD, various approaches have been developed to further improve the performance of the student model. However, few of these previous methods have considered the reliability of the supervision from teacher models. Supervision from erroneous predictions may mislead the training of the student model. This paper therefore proposes to tackle this problem from two aspects: Label Revision to rectify the incorrect supervision and Data Selection to select appropriate samples for distillation to reduce the impact of erroneous supervision. In the former, we propose to rectify the teacher’s inaccurate predictions using the ground truth. In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher, thereby reducing the impact of incorrect predictions to some extent. Experiment results demonstrate the effectiveness of the proposed method, which can be further combined with other distillation approaches to enhance their performance.