Shitian Zhao
5 papers · 2024–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (5) π Renaissance Researcher (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
CVPR (1)
EMNLP (1)
ICCV (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
multi-modal language model
(2)
visual question answering
(2)
style transfer
(1)
video generation
(1)
prompt engineering
(1)
image-to-image translation
(1)
model fusion
(1)
diffusion model
(1)
ensemble method
(1)
multimodal language model
(1)
log probability
(1)
font generation
(1)
context generation
(1)
font transfer
(1)
ensemble composition
(1)
causal inference
(1)
likelihood composition
(1)
few-shot learning
(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
Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models
EMNLP 2024
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
ICML 2024