Shitian Zhao
5 papers · 2024–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
🐣
Hot Topic Early Bird
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(3)
Deep Learning
(3)
Machine Learning
(3)
Core AI
(3)
Computer Vision
(2)
Natural Language Processing
(2)
Architectures
(2)
Learning Types
(2)
Models
(2)
Computer Science
(1)
Knowledge & Reasoning
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Core Methods
(1)
Generation
(1)
Keywords
multimodal language model
(2)
visual question answering
(2)
image generation
(1)
style transfer
(1)
video generation
(1)
prompt engineering
(1)
image editing
(1)
image-to-image translation
(1)
model fusion
(1)
instruction tuning
(1)
diffusion model
(1)
ensemble method
(1)
multimodal large language model
(1)
visual encoder
(1)
diffusion transformer
(1)
log probability
(1)
font generation
(1)
one-stage training
(1)
context generation
(1)
font transfer
(1)
Papers
FontAnimate: High Quality Few-shot Font Generation via Animating Font Transfer Process
ICCV 2025
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
ICLR 2025
Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models
CVPR 2024
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
ICML 2024
Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models
EMNLP 2024