Pengzhi Gao
YOU?
Author Swipe
View article: BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism
BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism Open
Graphical User Interface (GUI) agents have gained substantial attention due to their impressive capabilities to complete tasks through multiple interactions within GUI environments. However, existing agents primarily focus on enhancing the…
View article: BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism
BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism Open
View article: Graph Convolutional Neural Network Based Emotion Recognition with Brain Functional Connectivity Network
Graph Convolutional Neural Network Based Emotion Recognition with Brain Functional Connectivity Network Open
Emotion recognition plays an important role in Human Computer Interaction (HCI) and the evaluation of human behavior based on emotional state is an important research topic. The purpose of emotion recognition is to automatically identify h…
View article: Towards Boosting Many-to-Many Multilingual Machine Translation with Large Language Models
Towards Boosting Many-to-Many Multilingual Machine Translation with Large Language Models Open
The training paradigm for machine translation has gradually shifted, from learning neural machine translation (NMT) models with extensive parallel corpora to instruction finetuning on multilingual large language models (LLMs) with high-qua…
View article: An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation Open
Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neural machine translation (NMT) field. Can we also boost end-t…
View article: Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization Open
Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to more languages. In this paper, we introduce MuSR: a one-for-a…
View article: Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization Open
The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised dir…
View article: Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization Open
Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to more languages. In this paper, we introduce MuSR: a one-for-a…
View article: Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization Open
The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised dir…
View article: Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation Open
We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut,…
View article: Robust Matrix Completion By Exploiting Dynamic Low-Dimensional Structures
Robust Matrix Completion By Exploiting Dynamic Low-Dimensional Structures Open
This paper studies the robust matrix completion problem for time-varying models. Leveraging the low-rank property and the temporal information of the data, we develop novel methods to recover the original data from partially observed and c…
View article: Identification of Successive “Unobservable” Cyber Data Attacks in Power Systems Through Matrix Decomposition
Identification of Successive “Unobservable” Cyber Data Attacks in Power Systems Through Matrix Decomposition Open
This paper presents a new framework of identifying a series of cyber data\nattacks on power system synchrophasor measurements. We focus on detecting\n"unobservable" cyber data attacks that cannot be detected by any existing\nmethod that pu…