2 citations · 4 across the 6 of their papers we have counts for
6 papers
Hierarchical Skip Decoding for Efficient Autoregressive Text Generation
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the i…
Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
The increasing size of language models raises great research interests in parameter-efficient fine-tuning such as LoRA that freezes the pre-trained model, and injects small-scale t…
Leveraging Summary Guidance on Medical Report Summarization
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report and summary that are derive…
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization
Ding Li, Xuebing Yang, Yongqiang Tang +2
Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised so…
Differentiable N-gram Objective on Abstractive Summarization
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +2
ROUGE is a standard automatic evaluation metric based on n-grams for sequence-to-sequence tasks, while cross-entropy loss is an essential objective of neural network language model…
Learnable Faster Kernel-PCA for Nonlinear Fault Detection: Deep Autoencoder-Based Realization
Zelin Ren, Xuebing Yang, Yuchen Jiang +1
Kernel principal component analysis (KPCA) is a well-recognized nonlinear dimensionality reduction method that has been widely used in nonlinear fault detection tasks. As a kernel…