← Search

Tong Su

2 accepted papers

2024

Unlocking Parameter-Efficient Fine-Tuning for Low-Resource Language Translation

NAACL 2024findings

Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale pre-trained language models for diverse tasks, offering a balance between adaptability and computational efficiency. They are important in Low-Resource Language (LRL) Neural Machine Translation (NMT) to enh…

Cited by 5SourcePDFScholar
2023

ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals

CVPR 2023highlight

Motion forecasting is a key module in an autonomous driving system. Due to the heterogeneous nature of multi-sourced input, multimodality in agent behavior, and low latency required by onboard deployment, this task is notoriously challenging. To cope with these difficulties, this paper proposes a no…

Cited by 70SourcePDFScholar