Trung Le

Sharpness-Aware Teleportation on Riemannian Manifolds

2023 · arXiv (Cornell University)

Recent studies highlight the effectiveness of flat minima in enhancing generalization, with sharpness-aware minimization (SAM) achieving state-of-the-art performance. Additionally, insights into the intrinsic geometry of the loss landscape have shown promise for improving model generalization. …

Preserving Generalization of Language models in Few-shot Continual Relation Extraction

2024 · arXiv (Cornell University)

Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior knowledge from …