AIA loss teaches unified multimodal models task-specific cross-modal attention patterns to reduce conflicts between image understanding and generation without architecture decoupling.
Geneval: An object-focused framework for evaluating text- to-image alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model
AIA loss teaches unified multimodal models task-specific cross-modal attention patterns to reduce conflicts between image understanding and generation without architecture decoupling.