Tag
The paper introduces a novel approach using Poly-Encoders for computationally efficient automated creativity assessment, achieving performance comparable to Large Language Models with significantly reduced computational demands.
This paper explores Mamba-based State Space Models for Bangla fake news detection, comparing them to Transformer models like BanglaBERT. It demonstrates that Mamba offers competitive performance with higher efficiency in resource-constrained settings.
The paper introduces PAWC, an exact O(N log N) time algorithm for computing the full profile of partial optimal transport on the circle, which is robust to outliers and applicable to periodic data.
RouteTS is a unified forecasting framework that routes time series components between frequency and time domains based on spectral characteristics, improving accuracy and efficiency in handling periodicity and transience.