Search Results for author:
Found 3 papers, 1 papers with code
Consecutive Model Editing with Batch alongside HooK Layers
As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing in order to seek an effective, consecutive, and batch-supportive way to edit the model behavior directly.
WatME: Towards Lossless Watermarking Through Lexical Redundancy
Text watermarking has emerged as an important technique for detecting machine-generated text.
DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text
Specifically, we design a novel node memory scheme and aggregate the information over the depth dimension instead of the breadth dimension of the graph, which empowers the ability to collect long dependencies without stacking multiple layers.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
