Tag
This paper addresses the challenge of estimating individual treatment effects from graph data by modeling differentiated networked effects, proposing a mechanism with partial attention and a message amplifier to capture varying neighbor importance and scale. Experiments show improved performance over existing methods.
This paper proposes that quantum probability can be understood as a projection of contextual spacetime formation under finite-state requirements, reinterpreting interference and noncommutativity as mismatches from a fixed classical spacetime projection.
This paper empirically evaluates vector merging methods for multilingual knowledge editing in large language models, identifying vector summation with shared covariance as the most reliable strategy and highlighting the limited effectiveness of Task Singular Vectors for Merging (TSVM) in reducing multilingual interference.