Dongyang Liu
7 papers · 2023–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (11) π£ Hot Topic Early Bird π₯ Mega-Team Β· Squad
π
Triple Crown
Venues
Top co-authors
Research topics
Keywords
diffusion transformer
(3)
text-to-image generation
(3)
knowledge distillation
(1)
multimodal learning
(1)
image captioning
(1)
flow matching
(1)
computational efficiency
(1)
generative model
(1)
diffusion model
(1)
loss function
(1)
multimodal large language model
(1)
visual encoder
(1)
progressive training
(1)
student network
(1)
feature distillation
(1)
token reduction
(1)
multi-exit architecture
(1)
unified architecture
(1)
teacher network
(1)
large language model
(1)
Papers
Lumina-Image 2.0: A Unified and Efficient Image Generative Framework
ICCV 2025
Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation
ICLR 2025
A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
ICLR 2024
Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
NeurIPS 2024
"SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models"
ECCV 2024
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
ICML 2024
Function-Consistent Feature Distillation
ICLR 2023