Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Paper
•
2512.17909
•
Published
•
37
•
6
james curry
ainbo
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
upvoted
a
paper
13 days ago
DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset
upvoted
a
paper
17 days ago
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
Organizations
commented
a
paper
about 1 month ago