Scholar
Dongyang Liu
Google Scholar ID: VxQGEOcAAAAJ
MMLab CUHK
Citations & Impact
Citations
1,830
H-index
10
i10-index
11
Publications
18
Co-authors
4
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT
- - Lumina-mGPT: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining
- - Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
- - Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
- - SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
- - SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
- - LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
- - A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
- - Function-Consistent Feature Distillation
Research Experience
- - Currently a Ph.D. student at MMLab, involved in multiple research projects including Lumina-Video, Lumina-mGPT, Lumina-Next, etc.
- - During the time at VIPL lab, participated in various research works.
Education
- - 2024.09 - Present: MMLab, The Chinese University of Hong Kong (Ph.D.), Supervisor: Prof. Hongsheng Li
- - 2021.09 - 2024.06: VIPL Lab, Institute of Computing Technology, Chinese Academy of Sciences (Master), Supervisors: Prof. Shiguang Shan and Prof. Meina Kan
- - 2017.09 - 2021.06: School of Software Engineering, Tongji University (Bachelor)
Background
- - Research Interests: Multimodal understanding and generation
- - Background: Currently a first-year Ph.D. student at MMLab, CUHK, supervised by Prof. Hongsheng Li. Before that, obtained a master’s degree from VIPL, supervised by Prof. Shiguang Shan and Prof. Meina Kan.
