← Search

Lixing Gong

2 accepted papers

2024

TaD: A Plug-and-Play Task-Aware Decoding Method to Better Adapt LLMs on Downstream Tasks

IJCAI 2024poster

Fine-tuning pre-trained models on downstream tasks is a common practice in leveraging large language models (LLMs) today. A critical issue is how to adapt pre-trained models to downstream tasks better, thereby enhancing their performance. This paper introduces Task-aware Decoding (TaD), a plug-and-p…

Cited by 6SourcePDFScholar
2023

DynaMS: Dyanmic Margin Selection for Efficient Deep Learning

ICLR 2023poster

The great success of deep learning is largely driven by training over-parameterized models on massive datasets. To avoid excessive computation, extracting and training only on the most informative subset is drawing increasing attention. Nevertheless, it is still an open question how to select such a…

Cited by 5SourcePDFScholar