Beast code in Giters

Qrange-group's repositories

SUR-adapter

ACM MM'23 (oral), SUR-adapter for pre-trained diffusion models can acquire the powerful semantic understanding and reasoning capabilities from large language models to build a high-quality textual semantic representation for text-to-image generation.

Language:PythonMIT105 4 7

CEM

EMNLP'22, CEM improves MHCH performance by correcting prediction bias and training an auxiliary cost simulator based on user state and labor cost causal graph, without requiring complex model crafting.

Language:PythonMIT11 10

SEM

SEM can automatically decide to select and integrate attention operators to compute attention maps.

Language:PythonMIT8 10

LSAS

Lightweight sub-attention strategy (LSAS) utilizes high-order sub-attention modules to improve the original self-attention modules.

Language:PythonMIT3 10

SPEM

SPEM adopts a self-adaptive pooling strategy based on global max-pooling, global min-pooling and a lightweight module for producing the attention map.

Language:PythonMIT1 10