1 code implementation • 17 Mar 2024 • Jie Ren, Yaxin Li, Shenglai Zen, Han Xu, Lingjuan Lyu, Yue Xing, Jiliang Tang
Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts.
no code implementations • 6 Mar 2024 • Rajdeep Haldar, Yue Xing, Qifan Song
The existence of adversarial attacks on machine learning models imperceptible to a human is still quite a mystery from a theoretical perspective.
1 code implementation • 23 Feb 2024 • Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, Jiliang Tang
In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database.
no code implementations • 1 Feb 2024 • Yue Xing, Xiaofeng Lin, Namjoon Suh, Qifan Song, Guang Cheng
In practice, it is observed that transformer-based models can learn concepts in context in the inference stage.
no code implementations • 30 Jan 2024 • Yingqian Cui, Jie Ren, Pengfei He, Jiliang Tang, Yue Xing
We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks.
no code implementations • 26 Jan 2024 • Yue Xing, Xiaofeng Lin, Qifan Song, Yi Xu, Belinda Zeng, Guang Cheng
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models.
no code implementations • 10 Oct 2023 • Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, Dawei Yin
In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks.
no code implementations • 3 Oct 2023 • Yingqian Cui, Jie Ren, Yuping Lin, Han Xu, Pengfei He, Yue Xing, Wenqi Fan, Hui Liu, Jiliang Tang
Text-to-image generative models based on latent diffusion models (LDM) have demonstrated their outstanding ability in generating high-quality and high-resolution images according to language prompt.
no code implementations • 21 Jun 2023 • Yue Xing
In recent years, studies such as \cite{carmon2019unlabeled, gowal2021improving, xing2022artificial} have demonstrated that incorporating additional real or generated data with pseudo-labels can enhance adversarial training through a two-stage training approach.
no code implementations • 25 May 2023 • Yingqian Cui, Jie Ren, Han Xu, Pengfei He, Hui Liu, Lichao Sun, Yue Xing, Jiliang Tang
By detecting the watermark from generated images, copyright infringement can be exposed with evidence.
no code implementations • 23 Feb 2022 • Yue Xing, Qifan Song, Guang Cheng
In some studies \citep[e. g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero.
no code implementations • 14 Feb 2022 • Yue Xing, Qifan Song, Guang Cheng
The recent proposed self-supervised learning (SSL) approaches successfully demonstrate the great potential of supplementing learning algorithms with additional unlabeled data.
no code implementations • NeurIPS 2021 • Yue Xing, Qifan Song, Guang Cheng
In contrast, this paper studies the algorithmic stability of a generic adversarial training algorithm, which can further help to establish an upper bound for generalization error.
no code implementations • 18 Dec 2020 • Yue Xing, Ruizhi Zhang, Guang Cheng
Further, we reveal an explicit connection of adversarial and standard estimates, and propose a straightforward two-stage adversarial learning framework, which facilitates to utilize model structure information to improve adversarial robustness.
no code implementations • 15 Aug 2020 • Yue Xing, Qifan Song, Guang Cheng
Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed.
1 code implementation • NeurIPS 2020 • Shih-Kang Chao, Zhanyu Wang, Yue Xing, Guang Cheng
In the light of the fact that the stochastic gradient descent (SGD) often finds a flat minimum valley in the training loss, we propose a novel directional pruning method which searches for a sparse minimizer in or close to that flat region.
1 code implementation • 28 Apr 2020 • Mina Jafari, Ruizhe Li, Yue Xing, Dorothee Auer, Susan Francis, Jonathan Garibaldi, Xin Chen
In this paper, we present a generic deep convolutional neural network (DCNN) for multi-class image segmentation.
no code implementations • 13 Feb 2020 • Yue Xing, Qifan Song, Guang Cheng
We consider a data corruption scenario in the classical $k$ Nearest Neighbors ($k$-NN) algorithm, that is, the testing data are randomly perturbed.
no code implementations • 25 Sep 2019 • Yue Xing, Qifan Song, Guang Cheng
The over-parameterized models attract much attention in the era of data science and deep learning.
no code implementations • 5 Oct 2018 • Yue Xing, Qifan Song, Guang Cheng
In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important.