no code implementations • ECCV 2020 • Jianqiao An, Yucheng Shi, Yahong Han, Meijun Sun, Qi Tian
For a certain object in an image, the relationship between its central region and the peripheral region is not well utilized in existing superpixel segmentation methods.
1 code implementation • 1 May 2024 • Yucheng Shi, Alexandros Agapitos, David Lynch, Giorgio Cruciata, Hao Wang, Yayu Yao, Aleksandar Milenovic
In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives.
no code implementations • 17 Apr 2024 • Zihao Li, Yucheng Shi, Zirui Liu, Fan Yang, Ninghao Liu, Mengnan Du
However, currently there is no work to quantitatively measure the performance of LLMs in low-resource languages.
no code implementations • 28 Mar 2024 • Yucheng Shi, Qiaoyu Tan, Xuansheng Wu, Shaochen Zhong, Kaixiong Zhou, Ninghao Liu
Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge updates, leading to potentially outdated or inaccurate responses.
1 code implementation • 13 Mar 2024 • Xuansheng Wu, Haiyan Zhao, Yaochen Zhu, Yucheng Shi, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu
Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.
no code implementations • 16 Oct 2023 • Chenxu Zhao, Wei Qian, Yucheng Shi, Mengdi Huai, Ninghao Liu
Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks.
no code implementations • 27 Sep 2023 • Yucheng Shi, Shaochen Xu, Zhengliang Liu, Tianming Liu, Xiang Li, Ninghao Liu
Focusing on medical QA using the MedQA-SMILE dataset, we evaluate the impact of different retrieval models and the number of facts provided to the LLM.
1 code implementation • 18 Aug 2023 • Yucheng Shi, Yushun Dong, Qiaoyu Tan, Jundong Li, Ninghao Liu
By considering embeddings encompassing graph topology and attribute information as reconstruction targets, our model could capture more generalized and comprehensive knowledge.
1 code implementation • 3 Jul 2023 • Yucheng Shi, Kaixiong Zhou, Ninghao Liu
Then, we design two data augmentation schemes on graphs for perturbing structural and feature information, respectively.
1 code implementation • 29 Jun 2023 • Xuansheng Wu, Huachi Zhou, Yucheng Shi, Wenlin Yao, Xiao Huang, Ninghao Liu
To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only $17\%$ of the inference time.
no code implementations • 23 May 2023 • Ziqi Zhao, Yucheng Shi, Shushan Wu, Fan Yang, WenZhan Song, Ninghao Liu
Deep learning models developed for time-series associated tasks have become more widely researched nowadays.
1 code implementation • 3 May 2023 • Yucheng Shi, Hehuan Ma, Wenliang Zhong, Qiaoyu Tan, Gengchen Mai, Xiang Li, Tianming Liu, Junzhou Huang
To tackle these limitations, we propose a novel framework that leverages the power of ChatGPT for specific tasks, such as text classification, while improving its interpretability.
1 code implementation • 27 Dec 2022 • Hao Zhen, Yucheng Shi, Jidong J. Yang, Javad Mohammadpour Vehni
Classification using supervised learning requires annotating a large amount of classes-balanced data for model training and testing.
1 code implementation • 7 Dec 2021 • Yucheng Shi, Yahong Han, Yu-an Tan, Xiaohui Kuang
On the other hand, the neglect of noise sensitivity differences between image regions by existing decision-based attacks further compromises the efficiency of noise compression, especially for ViTs.
no code implementations • 21 Jul 2021 • Kunhong Wu, Yucheng Shi, Yahong Han, Yunfeng Shao, Bingshuai Li, Qi Tian
Existing unsupervised domain adaptation (UDA) methods can achieve promising performance without transferring data from source domain to target domain.
no code implementations • 27 Apr 2021 • Yuandu Lai, Yucheng Shi, Yahong Han, Yunfeng Shao, Meiyu Qi, Bingshuai Li
In this paper, We explore the uncertainty in deep learning to construct the prediction intervals.
no code implementations • CVPR 2020 • Yucheng Shi, Yahong Han, Qi Tian
We propose Customized Adversarial Boundary (CAB) attack that uses the current noise to model the sensitivity of each pixel and polish adversarial noise of each image with a customized sampling setting.
1 code implementation • CVPR 2019 • Yucheng Shi, Siyu Wang, Yahong Han
On the one hand, existing iterative attacks add noises monotonically along the direction of gradient ascent, resulting in a lack of diversity and adaptability of the generated iterative trajectories.