PPAD injects MLLM semantic feedback into diffusion denoising via lookahead sketches and ping-pong-ahead resampling, improving text-to-image alignment.
Proceedings Combined 30th International Workshop on Expressiveness in Concurrency and 20th Workshop on Structural Operational Semantics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This volume contains the proceedings of EXPRESS/SOS 2023: the Combined 30th International Workshop on Expressiveness in Concurrency and the 20th Workshop on Structural Operational Semantics, which was held in Antwerp, Belgium, as an affiliated workshop of CONCUR 2023, the 34rd International Conference on Concurrency Theory. The EXPRESS/SOS workshop series aims at bringing together researchers interested in the formal semantics of systems and programming concepts, and in the expressiveness of computational models.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
PPAD injects MLLM semantic feedback into diffusion denoising via lookahead sketches and ping-pong-ahead resampling, improving text-to-image alignment.