MAGE

Researchers introduced DWT-Fusion, a training-free signal-based framework for detecting LLM-generated text using discrete wavelet analysis of token-level log-probability sequences. The best single wav…

Researchers present T5-CSBoost, an extension to the T5-Sentinel framework that uses contrastive style regularization to improve robustness of LLM-generated text detection against adversarial perturbat…

Researchers propose MAGE, a geometry-aware framework for view-guided point cloud completion that integrates efficient modality alignment and adaptive geometry enhancement to address cross-modal geomet…