Does a prosody-trained representation help beyond trainable fusion? A parameter-matched study with frozen HuBERTResearchOct 1, 2026
Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization FrameworkResearchOct 1, 2026
Asymptotic Properties of Support Vector Machines in High-Dimension, Low-Sample-Size Settings under a Spiked ModelResearchOct 1, 2026
Authority Bias in Language Models: Source Deference and User Agreement Are Not InterchangeableResearchOct 1, 2026