1 code implementation • ALTA 2021 • Xinzhe Li, Ming Liu, Xingjun Ma, Longxiang Gao
Universal adversarial texts (UATs) refer to short pieces of text units that can largely affect the predictions of NLP models.
no code implementations • 30 Apr 2024 • Xinzhe Li, Ming Liu, Shang Gao
Retrieval-augmented Generation (RAG) systems have been actively studied and deployed across various industries to query on domain-specific knowledge base.
1 code implementation • 30 Nov 2023 • Xinzhe Li, Sun Rui, Yiming Niu, Yao Liu
Specifically, the framework consists of a precipitation predictor with multiple lightweight heads (learners) and a controller that combines the outputs from these heads.
no code implementations • 22 Oct 2023 • Yong Du, Jiahui Zhan, Shengfeng He, Xinzhe Li, Junyu Dong, Sheng Chen, Ming-Hsuan Yang
In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences.
1 code implementation • 2 Jul 2023 • Xinzhe Li, Ming Liu, Shang Gao
This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution.
1 code implementation • 27 Jun 2023 • Xinzhe Li, Ming Liu, Shang Gao
For Pretrained Language Models (PLMs), their susceptibility to noise has recently been linked to subword segmentation.
no code implementations • 27 Jun 2023 • Xinzhe Li, Ming Liu, Shang Gao, Wray Buntine
Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models.
1 code implementation • NeurIPS 2019 • Xinzhe Li, Qianru Sun, Yaoyao Liu, Shibao Zheng, Qin Zhou, Tat-Seng Chua, Bernt Schiele
On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning.
no code implementations • 1 Apr 2018 • Qin Zhou, Heng Fan, Shibao Zheng, Hang Su, Xinzhe Li, Shuang Wu, Haibin Ling
In this paper, we propose a graph correspondence transfer (GCT) approach for person re-identification.