by Yixin Ye Papers
2 papers found
Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions
Jin Gao, Lei Gan, Yuankai Li et al.
ECCV 2024posterarXiv:2408.01091
4
citations
Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models
Juntu Zhao, Junyu Deng, Yixin Ye et al.
ECCV 2024poster