Search Results for author: Jie Yu

Found 31 papers, 12 papers with code

SWEA: Changing Factual Knowledge in Large Language Models via Subject Word Embedding Altering

no code implementations31 Jan 2024 Xiaopeng Li, Shasha Li, Shezheng Song, Huijun Liu, Bin Ji, Xi Wang, Jun Ma, Jie Yu, Xiaodong Liu, Jing Wang, Weimin Zhang

To further validate the reasoning ability of SWEA$\oplus$OS in editing knowledge, we evaluate it on the more complex RippleEdits benchmark.

Model Editing Word Embeddings

How to Bridge the Gap between Modalities: A Comprehensive Survey on Multimodal Large Language Model

no code implementations10 Nov 2023 Shezheng Song, Xiaopeng Li, Shasha Li, Shan Zhao, Jie Yu, Jun Ma, Xiaoguang Mao, Weimin Zhang

The study surveys existing modal alignment methods in MLLMs into four groups: (1) Multimodal Converters that change data into something LLMs can understand; (2) Multimodal Perceivers to improve how LLMs perceive different types of data; (3) Tools Assistance for changing data into one common format, usually text; and (4) Data-Driven methods that teach LLMs to understand specific types of data in a dataset.

Language Modelling Large Language Model

Automatic nodule identification and differentiation in ultrasound videos to facilitate per-nodule examination

no code implementations10 Oct 2023 Siyuan Jiang, Yan Ding, Yuling Wang, Lei Xu, Wenli Dai, Wanru Chang, Jianfeng Zhang, Jie Yu, Jianqiao Zhou, Chunquan Zhang, Ping Liang, Dexing Kong

Ultrasound is a vital diagnostic technique in health screening, with the advantages of non-invasive, cost-effective, and radiation free, and therefore is widely applied in the diagnosis of nodules.

Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models

1 code implementation28 Sep 2023 Jia-Shu Pan, Yuan-Sen Ting, Jie Yu

Notably, the error remains under 3% for 30-day light curves, whose oscillations are undetectable by a conventional pipeline in 30% cases.

PMET: Precise Model Editing in a Transformer

1 code implementation17 Aug 2023 Xiaopeng Li, Shasha Li, Shezheng Song, Jing Yang, Jun Ma, Jie Yu

To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns.

General Knowledge Model Editing

Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World

1 code implementation27 Jul 2023 Xingxing Wei, Yao Huang, Yitong Sun, Jie Yu

We also demonstrate the effectiveness of our approach in physical-world scenarios under various settings, including different angles, distances, postures, and scenes for both visible and infrared sensors.

Unified Adversarial Patch for Cross-modal Attacks in the Physical World

1 code implementation ICCV 2023 Xingxing Wei, Yao Huang, Yitong Sun, Jie Yu

To show the potential risks under such scenes, we propose a unified adversarial patch to perform cross-modal physical attacks, i. e., fooling visible and infrared object detectors at the same time via a single patch.

Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction

no code implementations9 Mar 2023 Jing Yang, Bin Ji, Shasha Li, Jun Ma, Long Peng, Jie Yu

Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction.

Relation Relation Extraction

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks

1 code implementation26 Dec 2022 Xingxing Wei, Ying Guo, Jie Yu, Bo Zhang

Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency.

Face Recognition Position +2

Behavior Prior Representation learning for Offline Reinforcement Learning

1 code implementation2 Nov 2022 Hongyu Zang, Xin Li, Jie Yu, Chen Liu, Riashat Islam, Remi Tachet des Combes, Romain Laroche

Our method, Behavior Prior Representation (BPR), learns state representations with an easy-to-integrate objective based on behavior cloning of the dataset: we first learn a state representation by mimicking actions from the dataset, and then train a policy on top of the fixed representation, using any off-the-shelf Offline RL algorithm.

Offline RL reinforcement-learning +2

Span-based joint entity and relation extraction augmented with sequence tagging mechanism

no code implementations23 Oct 2022 Bin Ji, Shasha Li, Hao Xu, Jie Yu, Jun Ma, Huijun Liu, Jing Yang

On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE.

Joint Entity and Relation Extraction named-entity-recognition +3

A Two-Phase Paradigm for Joint Entity-Relation Extraction

no code implementations18 Aug 2022 Bin Ji, Hao Xu, Jie Yu, Shasha Li, Jun Ma, Yuke Ji, Huijun Liu

An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task.

Joint Entity and Relation Extraction Relation +1

A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search

no code implementations17 Aug 2022 Huijun Liu, Jie Yu, Shasha Li, Jun Ma, Bin Ji

Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness.

Adversarial Attack

Topic-Grained Text Representation-based Model for Document Retrieval

no code implementations11 Jul 2022 Mengxue Du, Shasha Li, Jie Yu, Jun Ma, Bin Ji, Huijun Liu, Wuhang Lin, Zibo Yi

Document retrieval enables users to find their required documents accurately and quickly.

Retrieval

SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder

no code implementations11 Jul 2022 Wuhang Lin, Shasha Li, Chen Zhang, Bin Ji, Jie Yu, Jun Ma, Zibo Yi

However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with human scoring and inhibition of summary diversity.

Text Matching Text Summarization

Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition

no code implementations7 Jul 2022 Bin Ji, Shasha Li, Jie Yu, Jun Ma, Huijun Liu

Previous research has demonstrated that the two paradigms have clear complementary advantages, but few models have attempted to leverage these advantages in a single NER model as far as we know.

named-entity-recognition Named Entity Recognition +2

Astroconformer: Inferring Surface Gravity of Stars from Stellar Light Curves with Transformer

no code implementations6 Jul 2022 Jiashu Pan, Yuan-Sen Ting, Jie Yu

We introduce Astroconformer, a Transformer-based model to analyze stellar light curves from the Kepler mission.

Time Series Time Series Analysis

Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling

1 code implementation6 Dec 2021 Zhuoling Li, Gaowei Zhang, Lingyu Xu, Jie Yu

The model acquires static and dynamic graph matrices from data to model long- and short-term patterns respectively.

Graph Learning Inductive Bias +2

Generating Transferable Adversarial Patch by Simultaneously Optimizing its Position and Perturbations

no code implementations29 Sep 2021 Xingxing Wei, Ying Guo, Jie Yu, Huanqian Yan, Bo Zhang

In this paper, we propose a method to simultaneously optimize the position and perturbation to generate transferable adversarial patches, and thus obtain high attack success rates in the black-box setting.

Face Recognition Position

One Million Scenes for Autonomous Driving: ONCE Dataset

1 code implementation21 Jun 2021 Jiageng Mao, Minzhe Niu, Chenhan Jiang, Hanxue Liang, Jingheng Chen, Xiaodan Liang, Yamin Li, Chaoqiang Ye, Wei zhang, Zhenguo Li, Jie Yu, Hang Xu, Chunjing Xu

To facilitate future research on exploiting unlabeled data for 3D detection, we additionally provide a benchmark in which we reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.

3D Object Detection Autonomous Driving +1

Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanism

no code implementations21 May 2021 Bin Ji, Shasha Li, Jie Yu, Jun Ma, Huijun Liu

To solve this problem, we pro-pose Sequence Tagging enhanced Span-based Network (STSN), a span-based joint extrac-tion network that is enhanced by token BIO label information derived from sequence tag-ging based NER.

Joint Entity and Relation Extraction named-entity-recognition +4

Adversarial Sticker: A Stealthy Attack Method in the Physical World

1 code implementation14 Apr 2021 Xingxing Wei, Ying Guo, Jie Yu

Unlike the previous adversarial patches by designing perturbations, our method manipulates the sticker's pasting position and rotation angle on the objects to perform physical attacks.

Face Recognition Image Retrieval +4

CardioLearn: A Cloud Deep Learning Service for Cardiac Disease Detection from Electrocardiogram

1 code implementation4 Jul 2020 Shenda Hong, Zhaoji Fu, Rongbo Zhou, Jie Yu, Yongkui Li, Kai Wang, Guanlin Cheng

Electrocardiogram (ECG) is one of the most convenient and non-invasive tools for monitoring peoples' heart condition, which can use for diagnosing a wide range of heart diseases, including Cardiac Arrhythmia, Acute Coronary Syndrome, et al.

Multi-Modal Three-Stream Network for Action Recognition

no code implementations8 Sep 2019 Muhammad Usman Khalid, Jie Yu

Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data.

Action Classification Action Recognition +2

The K2 Bright Star Survey I: Methodology and Data Release

1 code implementation19 Aug 2019 Benjamin J. S. Pope, Timothy R. White, Will M. Farr, Jie Yu, Michael Greklek-McKeon, Daniel Huber, Conny Aerts, Suzanne Aigrain, Timothy R. Bedding, Tabetha Boyajian, Orlagh L. Creevey, David W. Hogg

While the Kepler Mission was designed to look at tens of thousands of faint stars (V > 12), brighter stars that saturated the detector are important because they can be and have been observed very accurately by other instruments.

Solar and Stellar Astrophysics Instrumentation and Methods for Astrophysics

Asteroseismology of 16000 Kepler Red Giants: Global Oscillation Parameters, Masses, and Radii

2 code implementations13 Feb 2018 Jie Yu, Daniel Huber, Timothy R. Bedding, Dennis Stello, Marc Hon, Simon J. Murphy, Shourya Khanna

Thanks to the large red giant sample, we confirm that red-giant-branch (RGB) and helium-core-burning (HeB) stars collectively differ in the distribution of oscillation amplitude, granulation power, and width of power excess, which is mainly due to the mass difference.

Solar and Stellar Astrophysics

Attention-based Natural Language Person Retrieval

no code implementations24 May 2017 Tao Zhou, Muhao Chen, Jie Yu, Demetri Terzopoulos

Following the recent progress in image classification and captioning using deep learning, we develop a novel natural language person retrieval system based on an attention mechanism.

Image Classification Person Retrieval +2

Drug-drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers

no code implementations9 May 2017 Zibo Yi, Shasha Li, Jie Yu, Qingbo Wu

The experiments show that our model classifies most of the drug pairs into correct DDI categories, which outperforms the existing NLP or deep learning methods.

Drug–drug Interaction Extraction Feature Engineering +2

Cannot find the paper you are looking for? You can Submit a new open access paper.