Yeji Song
5 papers · 2024–2026 · 4 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Keywords
zero-shot learning
(2)
diffusion model
(2)
embedding learning
(1)
text alignment
(1)
image editing
(1)
text-to-image generation
(1)
text-to-image model
(1)
model fine-tuning
(1)
text embedding
(1)
text-to-video generation
(1)
privacy protection
(1)
text-guided editing
(1)
rectified flow
(1)
subject identity
(1)
image quality
(1)
real image editing
(1)
visual embedding
(1)
attention adaptation
(1)
training trajectory
(1)
textual embedding
(1)
Papers
Targeted Data Protection for Diffusion Model by Matching Training Trajectory
AAAI 2026
Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization
AAAI 2025
ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
ICCV 2025
Exploring Causal Mechanisms for Machine Text Detection Methods
NAACL 2024
SAVE: Protagonist Diversification with Structure Agnostic Video Editing
ECCV 2024