RAEE: A Training-Free Retrieval-Augmented Early Exiting Framework for Efficient Inference

no code implementations • 24 May 2024 • Lianming Huang, Shangyu Wu, Yufei Cui, Ying Xiong, Xue Liu, Tei-Wei Kuo, Nan Guan, Chun Jason Xue

Finally, based on the pre-built retrieval database, RAEE leverages the retrieved similar data's exiting information to guide the backbone model to exit at the layer, which is predicted by the approximated distribution.

ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion

no code implementations • 4 Jan 2024 • Shangyu Wu, Ying Xiong, Yufei Cui, Xue Liu, Buzhou Tang, Tei-Wei Kuo, Chun Jason Xue

Retrieval-based augmentations (RA) incorporating knowledge from an external database into language models have greatly succeeded in various knowledge-intensive (KI) tasks.

Natural Language Understanding Neural Architecture Search +5

NFL: Robust Learned Index via Distribution Transformation

1 code implementation • 24 May 2022 • Shangyu Wu, Yufei Cui, Jinghuan Yu, Xuan Sun, Tei-Wei Kuo, Chun Jason Xue

Based on the characteristics of the transformed keys, we propose a robust After-Flow Learned Index (AFLI).