Dequan Wang* — accepted AI-conference papers

2024

Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions

Jin Gao, Lei Gan, Yuankai Li, Yixin Ye, Dequan Wang*

ECCV 2024poster

"Large multimodal models (LMMs) excel in adhering to human instructions. However, self-contradictory instructions may arise due to the increasing trend of multimodal interaction and context length, which is challenging for language beginners and vulnerable populations. We introduce the Self-Contradi…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2024

Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models

Juntu Zhao, Junyu Deng, Yixin Ye, Chongxuan Li, Zhijie Deng*, Dequan Wang*

ECCV 2024poster

"Advancements in text-to-image diffusion models have broadened extensive downstream practical applications, but such models often encounter misalignment issues between text and image. Taking the generation of a combination of two disentangled concepts as an example, say given the prompt a tea cup of…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗