2 papers
cs.AI2024
Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions
Jin Gao, Lei Gan, Yuankai Li +2
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…
cs.CV2023
BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
Siqi Kou, Lei Gan, Dequan Wang +2
Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper samp…