Search Results for author: Tong Liu

Found 53 papers, 13 papers with code

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

no code implementations28 Feb 2024 Tong Liu, Yingjie Zhang, Zhe Zhao, Yinpeng Dong, Guozhu Meng, Kai Chen

We evaluate DRA across various open-source and close-source models, showcasing state-of-the-art jailbreak success rates and attack efficiency.

Reconstruction Attack

From COBIT to ISO 42001: Evaluating Cybersecurity Frameworks for Opportunities, Risks, and Regulatory Compliance in Commercializing Large Language Models

no code implementations24 Feb 2024 Timothy R. McIntosh, Teo Susnjak, Tong Liu, Paul Watters, Raza Nowrozy, Malka N. Halgamuge

This study investigated the integration readiness of four predominant cybersecurity Governance, Risk and Compliance (GRC) frameworks - NIST CSF 2. 0, COBIT 2019, ISO 27001:2022, and the latest ISO 42001:2023 - for the opportunities, risks, and regulatory compliance when adopting Large Language Models (LLMs), using qualitative content analysis and expert validation.


Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence

no code implementations15 Feb 2024 Timothy R. McIntosh, Teo Susnjak, Tong Liu, Paul Watters, Malka N. Halgamuge

The rapid rise in popularity of Large Language Models (LLMs) with emerging capabilities has spurred public curiosity to evaluate and compare different LLMs, leading many researchers to propose their LLM benchmarks.

Language Modelling Large Language Model +1

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

no code implementations5 Feb 2024 Yuqian Fu, Yu Wang, Yixuan Pan, Lian Huai, Xingyu Qiu, Zeyu Shangguan, Tong Liu, Yanwei Fu, Luc van Gool, Xingqun Jiang

This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples.

Cross-Domain Few-Shot Few-Shot Object Detection +3

HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy

no code implementations26 Jan 2024 Yongkang Liu, Yiqun Zhang, Qian Li, Tong Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze

As LMs grow in size, fine-tuning the full parameters of LMs requires a prohibitively large amount of GPU memory.

From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape

no code implementations18 Dec 2023 Timothy R. McIntosh, Teo Susnjak, Tong Liu, Paul Watters, Malka N. Halgamuge

This comprehensive survey explored the evolving landscape of generative Artificial Intelligence (AI), with a specific focus on the transformative impacts of Mixture of Experts (MoE), multimodal learning, and the speculated advancements towards Artificial General Intelligence (AGI).

Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction

1 code implementation5 Dec 2023 Hongbin Ye, Honghao Gui, Aijia Zhang, Tong Liu, Wei Hua, Weiqiang Jia

Knowledge graph construction (KGC) is a multifaceted undertaking involving the extraction of entities, relations, and events.

Event Extraction graph construction

Decoupled DETR For Few-shot Object Detection

no code implementations20 Nov 2023 Zeyu Shangguan, Lian Huai, Tong Liu, Xingqun Jiang

We also explore various types of skip connection between the encoder and decoder for DETR.

Few-Shot Object Detection Meta-Learning +2

Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part I: Communication-Aware Vehicle Control

no code implementations19 Nov 2023 Tong Liu, Lei Lei, Kan Zheng, Xuemin, Shen

It is proved that the optimal policy for the augmented state MDP is optimal for the original PC problem with observation delay.

Autonomous Driving Decision Making

Improving fit to human reading times via temperature-scaled surprisal

no code implementations15 Nov 2023 Tong Liu, Iza Škrjanec, Vera Demberg

We propose to use temperature-scaled surprisal, a surprisal calculated by shaped probability, to be the predictor of human reading times.

Spatio-Temporal Similarity Measure based Multi-Task Learning for Predicting Alzheimer's Disease Progression using MRI Data

no code implementations6 Nov 2023 Xulong Wang, Yu Zhang, Menghui Zhou, Tong Liu, Jun Qi, Po Yang

The experimental results show that compared with directly ROI based learning, our proposed method is more effective in predicting disease progression.

Multi-Task Learning

Training Multi-layer Neural Networks on Ising Machine

no code implementations6 Nov 2023 Xujie Song, Tong Liu, Shengbo Eben Li, Jingliang Duan, Wenxuan Wang, Keqiang Li

This paper proposes an Ising learning algorithm to train quantized neural network (QNN), by incorporating two essential techinques, namely binary representation of topological network and order reduction of loss function.

Heterogeneous Graph Neural Networks for Data-driven Traffic Assignment

no code implementations19 Oct 2023 Tong Liu, Hadi Meidani

In this paper, we leverage the power of heterogeneous graph neural networks to propose a novel data-driven approach for traffic assignment and traffic flow learning.


ITRE: Low-light Image Enhancement Based on Illumination Transmission Ratio Estimation

no code implementations8 Oct 2023 Yu Wang, Yihong Wang, Tong Liu, Xiubao Sui, Qian Chen

In this paper, we propose a novel Retinex-based method, called ITRE, which suppresses noise and artifacts from the origin of the model, prevents over-exposure throughout the enhancement process.

Low-Light Image Enhancement

Cognitive Mirage: A Review of Hallucinations in Large Language Models

1 code implementation13 Sep 2023 Hongbin Ye, Tong Liu, Aijia Zhang, Wei Hua, Weiqiang Jia

Our contribution are threefold: (1) We provide a detailed and complete taxonomy for hallucinations appearing in text generation tasks; (2) We provide theoretical analyses of hallucinations in LLMs and provide existing detection and improvement methods; (3) We propose several research directions that can be developed in the future.

Hallucination Text Generation

A Persistent-Excitation-Free Method for System Disturbance Estimation Using Concurrent Learning

1 code implementation12 Apr 2023 Zengjie Zhang, Fangzhou Liu, Tong Liu, Jianbin Qiu, Martin Buss

A simulation study on epidemic control shows that the proposed method produces higher estimation precision than the conventional disturbance observer when PE is not satisfied.

Simultaneous Recursive Identification of Parameters and Switching Manifolds Identification of Discrete-Time Switched Linear Systems

no code implementations7 Mar 2023 Zengjie Zhang, Yingwei Du, Tong Liu, Fangzhou Liu, Martin Buss

Thirdly, techniques of incremental support vector machine are applied to develop the recursive algorithm to estimate the system switching manifolds, with its stability proven by a Lynapunov-based method.

Few-shot Object Detection with Refined Contrastive Learning

no code implementations24 Nov 2022 Zeyu Shangguan, Lian Huai, Tong Liu, Xingqun Jiang

A pre-determination component is introduced to find out the Resemblance Group from novel classes which contains confusable classes.

Contrastive Learning Few-Shot Object Detection +2

Deep Intention-Aware Network for Click-Through Rate Prediction

no code implementations16 Nov 2022 Yaxian Xia, Yi Cao, Sihao Hu, Tong Liu, Lingling Lu

We identify that the key to TIRA is to extract customers' personalized entering intention and weigh the impact of triggers based on this intention.

Click-Through Rate Prediction

Hybrid HMM Decoder For Convolutional Codes By Joint Trellis-Like Structure and Channel Prior

1 code implementation26 Oct 2022 Haoyu Li, Xuan Wang, Tong Liu, Dingyi Fang, Baoying Liu

In this paper, we propose the use of a Hidden Markov Model (HMM) for the reconstruction of convolutional codes and decoding by the Viterbi algorithm.


Graph Neural Network Surrogate for seismic reliability analysis of highway bridge system

no code implementations12 Oct 2022 Tong Liu, Hadi Meidani

Rapid reliability assessment of transportation networks can enhance preparedness, risk mitigation and response management procedures related to these systems.

Computational Efficiency Management

Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming

no code implementations15 Jun 2022 Tong Liu, Lei Lei, Kan Zheng, Kuan Zhang

Deep Reinforcement Learning (DRL) is regarded as a potential method for car-following control and has been mostly studied to support a single following vehicle.

reinforcement-learning Reinforcement Learning (RL)

On Calibration of Graph Neural Networks for Node Classification

1 code implementation3 Jun 2022 Tong Liu, Yushan Liu, Marcel Hildebrandt, Mitchell Joblin, Hang Li, Volker Tresp

We investigate the calibration of graph neural networks for node classification, study the effect of existing post-processing calibration methods, and analyze the influence of model capacity, graph density, and a new loss function on calibration.

Classification Link Prediction +1

Adaptive Pseudo-Siamese Policy Network for Temporal Knowledge Prediction

no code implementations26 Apr 2022 Pengpeng Shao, Tong Liu, Feihu Che, Dawei Zhang, JianHua Tao

Specifically, we design the policy network in our model as a pseudo-siamese policy network that consists of two sub-policy networks.

Knowledge Graphs Link Prediction +1

Adaptive Observer for a Class of Systems with Switched Unknown Parameters Using DREM

no code implementations30 Mar 2022 Tong Liu, Zengjie Zhang, Fangzhou Liu, Martin Buss

These responses depend on the unknown states at switching instants (SASI) and constitute an additive disturbance to the parameter estimation, which obstructs parameter convergence to zero.

Deep Reinforcement Learning Aided Platoon Control Relying on V2X Information

no code implementations28 Mar 2022 Lei Lei, Tong Liu, Kan Zheng, Lajos Hanzo

In this context, the value of V2X communications for DRL-based platoon controllers is studied with an emphasis on the tradeoff between the gain of including exogenous information in the system state for reducing uncertainty and the performance erosion due to the curse-of-dimensionality.

reinforcement-learning Reinforcement Learning (RL)

Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training

no code implementations14 Mar 2022 Jiahao Shao, Shijia Geng, Zhaoji Fu, Weilun Xu, Tong Liu, Shenda Hong

The results show that our method performed more effectively against adversarial attacks targeting on ECG classification than the other baseline methods, namely, adversarial training, defensive distillation, Jacob regularization, and noise-to-signal ratio regularization.

Adversarial Attack Classification +1

On the evaluation of (meta-)solver approaches

no code implementations17 Feb 2022 Roberto Amadini, Maurizio Gabbrielli, Tong Liu, Jacopo Mauro

Meta-solver approaches exploits a number of individual solvers to potentially build a better solver.

Training a Bidirectional GAN-based One-Class Classifier for Network Intrusion Detection

no code implementations2 Feb 2022 Wen Xu, Julian Jang-Jaccard, Tong Liu, Fariza Sabrina

The network intrusion detection task is challenging because of the imbalanced and unlabeled nature of the dataset it operates on.

Anomaly Detection Network Intrusion Detection +1

From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba

no code implementations17 Sep 2021 Xinyuan Qi, Kai Hou, Tong Liu, Zhongzhong Yu, Sihao Hu, Wenwu Ou

Except for introducing future knowledge for prediction, we propose Aliformer based on the bidirectional Transformer, which can utilize the historical information, current factor, and future knowledge to predict future sales.

Time Series Time Series Forecasting

Multi-Level Graph Contrastive Learning

no code implementations6 Jul 2021 Pengpeng Shao, Tong Liu, Dawei Zhang, JianHua Tao, Feihu Che, Guohua Yang

In this paper, we propose a Multi-Level Graph Contrastive Learning (MLGCL) framework for learning robust representation of graph data by contrasting space views of graphs.

Contrastive Learning Graph Representation Learning +3

Photometric space object classification via deep learning algorithms

no code implementations Acta Astronautica 2021 Tong Liu, K. Ulrich Schreiber ∗

Accurate time transfer by time of flight measurements via diffuse reflections on passive orbiting space debris targets requires a selection of suitable objects out of a large catalogue of debris items.

Classification Classification with Binary Neural Network +1

Model Reference Adaptive Control of Piecewise Affine Systems with State Tracking Performance Guarantees

no code implementations4 Mar 2021 Tong Liu, Martin Buss

We also prove that the Lyapunov function is non-increasing even at the switching instants and thus does not impose extra dwell time constraints.

Comparison of prismatic cohomology and derived de Rham cohomology

no code implementations28 Dec 2020 Shizhang Li, Tong Liu

We establish a comparison isomorphism between prismatic cohomology and derived de Rham cohomology respecting various structures, such as their Frobenius actions and filtrations.

Algebraic Geometry Number Theory 14F30, 11F80

Self-supervised Graph Representation Learning via Bootstrapping

no code implementations10 Nov 2020 Feihu Che, Guohua Yang, Dawei Zhang, JianHua Tao, Pengpeng Shao, Tong Liu

In addition, we summarize three kinds of augmentation methods for graph-structured data and apply them to the DGB.

Graph Representation Learning

ECG Beats Fast Classification Base on Sparse Dictionaries

1 code implementation8 Sep 2020 Nanyu Li, Yujuan Si, Di Wang, Tong Liu, Jinrun Yu

In VQ method, a set of dictionaries corresponding to segments of ECG beats is trained, and VQ codes are used to represent each heartbeat.

Classification Dictionary Learning +3

sunny-as2: Enhancing SUNNY for Algorithm Selection

1 code implementation7 Sep 2020 Tong Liu, Roberto Amadini, Jacopo Mauro, Maurizio Gabbrielli

A preliminary version of sunny-as2 was submitted to the Open Algorithm Selection Challenge (OASC) in 2017, where it turned out to be the best approach for the runtime minimization of decision problems.

feature selection

Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style Transfer

1 code implementation4 Feb 2020 Tong Liu, Zhaowei Chen, Yi Yang, Zehao Wu, Haowei Li

Nowadays, deep learning techniques are widely used for lane detection, but application in low-light conditions remains a challenge until this day.

Lane Detection Multi-Task Learning +1

Twitter Job/Employment Corpus: A Dataset of Job-Related Discourse Built with Humans in the Loop

no code implementations30 Jan 2019 Tong Liu, Christopher M. Homan

We present the Twitter Job/Employment Corpus, a collection of tweets annotated by a humans-in-the-loop supervised learning framework that integrates crowdsourcing contributions and expertise on the local community and employment environment.

Segmentation of histological images and fibrosis identification with a convolutional neural network

no code implementations20 Mar 2018 Xiaohang Fu, Tong Liu, Zhaohan Xiong, Bruce H. Smaill, Martin K. Stiles, Jichao Zhao

Segmentation of histological images is one of the most crucial tasks for many biomedical analyses including quantification of certain tissue type.


Learning from various labeling strategies for suicide-related messages on social media: An experimental study

1 code implementation30 Jan 2017 Tong Liu, Qijin Cheng, Christopher M. Homan, Vincent M. B. Silenzio

Suicide is an important but often misunderstood problem, one that researchers are now seeking to better understand through social media.

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