paper-conference

CAMAL: Optimizing LSM-trees via Active Learning
We use machine learning to optimize the LSM-tree structure, aiming to reduce the cost of processing various read/write operations.
Cite
CAMAL: Optimizing LSM-trees via Active Learning
GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs
We propose GENTI, a GPU-oriented subgraph-based graph representation learning algorithm for dynamic graphs.
PDF Cite
GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs
Accelerating Text-to-image Editing via Cache-enabled Sparse Diffusion Inference
We introduce Fast Image Semantically Edit (FISEdit), a framework for image editing based on minor textual modifications. FISEdit automatically identifies the region to edit and sparsely updates the image to improve efficiency.
PDF Cite
Accelerating Text-to-image Editing via Cache-enabled Sparse Diffusion Inference
Accelerating Text-to-image Editing via Cache-enabled Sparse Diffusion Inference
We introduce Fast Image Semantically Edit (FISEdit), a framework for image editing based on minor textual modifications. FISEdit automatically identifies the region to edit and sparsely updates the image to improve efficiency.
PDF Cite
Accelerating Text-to-image Editing via Cache-enabled Sparse Diffusion Inference