1 code implementation • 4 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.
1 code implementation • 13 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.
1 code implementation • 7 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.
1 code implementation • 15 Jul 2019 • Zhen-Yu Zhang, Xiangfeng Luo, Tong Liu, Shaorong Xie, Jianshu Wang, Wei Wang, Yang Li, Yan Peng
Instability and slowness are two main problems in deep reinforcement learning.
1 code implementation • Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence 2023 • Yuanchen Wu, Xiaoqiang Li, Songmin Dai, Jide Li, Tong Liu, Shaorong Xie
Weakly supervised semantic segmentation (WSSS) with image-level annotations has achieved great processes through class activation map (CAM).
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • 16 Nov 2020 • Pengpeng Shao, Guohua Yang, Dawei Zhang, JianHua Tao, Feihu Che, Tong Liu
Developing the model for temporal knowledge graphs completion is an increasingly important task.
1 code implementation • 8 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.
1 code implementation • 3 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.
1 code implementation • 26 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.
1 code implementation • 5 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.
1 code implementation • 16 Mar 2020 • Tharindu Cyril Weerasooriya, Tong Liu, Christopher M. Homan
Supervised machine learning often requires human-annotated data.
no code implementations • 20 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.
1 code implementation • 30 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.
no code implementations • COLING 2016 • Wei Song, Tong Liu, Ruiji Fu, Lizhen Liu, Hanshi Wang, Ting Liu
Parallelism is an important rhetorical device.
no code implementations • 30 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.
no code implementations • 10 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.
no code implementations • 4 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.
no code implementations • 28 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
no code implementations • CVPR 2021 • Zibo Zhao, Wen Liu, Yanyu Xu, Xianing Chen, Weixin Luo, Lei Jin, Bohui Zhu, Tong Liu, Binqiang Zhao, Shenghua Gao
One is a structure prior, it uses a human parsing map to represent the human body structure.
no code implementations • 6 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.
no code implementations • 19 Aug 2021 • Tong Liu, Siyuan Wang, Jingchao Fu, Lei Chen, Zhongyu Wei, Yaqi Liu, Heng Ye, Liaosa Xu, Weiqiang Wan, Xuanjing Huang
Existing system dealing with online complaint provides a final decision without explanations.
no code implementations • 17 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.
no code implementations • 2 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.
no code implementations • 17 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.
no code implementations • 14 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.
no code implementations • 28 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.
no code implementations • 30 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.
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.
no code implementations • 26 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.
no code implementations • 15 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.
no code implementations • 12 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.
no code implementations • 16 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.
no code implementations • 24 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.
no code implementations • 10 Feb 2023 • Deyun Zhang, Shijia Geng, Yang Zhou, Weilun Xu, Guodong Wei, Kai Wang, Jie Yu, Qiang Zhu, Yongkui Li, Yonghong Zhao, Xingyue Chen, Rui Zhang, Zhaoji Fu, Rongbo Zhou, Yanqi E, Sumei Fan, Qinghao Zhao, Chuandong Cheng, Nan Peng, Liang Zhang, Linlin Zheng, Jianjun Chu, Hongbin Xu, Chen Tan, Jian Liu, Huayue Tao, Tong Liu, Kangyin Chen, Chenyang Jiang, Xingpeng Liu, Shenda Hong
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
no code implementations • 7 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.
1 code implementation • 12 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.
no code implementations • 8 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.
no code implementations • 19 Oct 2023 • Tong Liu, Hadi Meidani
The traffic assignment problem is one of the significant components of traffic flow analysis for which various solution approaches have been proposed.
no code implementations • 6 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.
no code implementations • 6 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.
no code implementations • 15 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.
no code implementations • 20 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.
no code implementations • 19 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.
no code implementations • 19 Nov 2023 • Lei Lei, Tong Liu, Kan Zheng, Xuemin, Shen
We focused on the PC sub-problem and proposed the MTCC-PC algorithm to learn an optimal PC policy given an RRA policy.
no code implementations • 18 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).
no code implementations • 26 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.
no code implementations • 5 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.
no code implementations • 15 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.
no code implementations • 21 Feb 2024 • Liqiu Dong, Marta Zagorowska, Tong Liu, Alex Durkin, Mehmet Mercangöz
Physics informed neural networks (PINNs) have recently been proposed as surrogate models for solving process optimization problems.
no code implementations • 24 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.
no code implementations • 28 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.
no code implementations • 16 Apr 2024 • Liang Li, Ting Zhou, Tong Liu, Zhiwei Liu, Yaping Li, Shuo Wu, Shanguang Zhao, Jinglin Zhu, Meiling Liu, Zhihan Lin, Bowen Sun, Jianjun Li, Fangwen Sun, Chongwen Zou
However, its intrinsic insulating state requires the VO2 neuronal device to be driven under large bias voltage, resulting in high power consumption and low frequency.