Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation · 相关技术
相关技术
ORMMultimodal Large Language Models (MLLMs)ODELLMlanguage model扩散模型多模态image generationdivide-and-conquer partitioningdiffusion modelsdenoisingVAEUCTStraight-Through EstimatorSEMReferring expression comprehension (REC)PPRMITLMMlarge language modelsHISGrouped Memorization EvaluationForFOLEffort Metric AttentionDiffusionDiTCamouflaged object detectionARGANN