48 citations · 181 across the 24 of their papers we have counts for
24 papers
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
Siqi Kou, Jiachun Jin, Zetong Zhou +8
Recent progress in text-to-image (T2I) diffusion models (DMs) has enabled high-quality visual synthesis from diverse textual prompts. Yet, most existing T2I DMs, even those equippe…
Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models
Peng Cui, Guande He, Dan Zhang +3
Datasets collected from the open world unavoidably suffer from various forms of randomness or noiseness, leading to the ubiquity of aleatoric (data) uncertainty. Quantifying such u…
Improved Operator Learning by Orthogonal Attention
Zipeng Xiao, Zhongkai Hao, Bokai Lin +2
Neural operators, as an efficient surrogate model for learning the solutions of PDEs, have received extensive attention in the field of scientific machine learning. Among them, att…
Heterogeneous Multi-Task Gaussian Cox Processes
Feng Zhou, Quyu Kong, Zhijie Deng +3
This paper presents a novel extension of multi-task Gaussian Cox processes for modeling multiple heterogeneous correlated tasks jointly, e.g., classification and regression, via mu…
Towards Accelerated Model Training via Bayesian Data Selection
Zhijie Deng, Peng Cui, Jun Zhu
Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard sam…
Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks
Hongcheng Gao, Hao Zhang, Yinpeng Dong +1
Text-to-image (T2I) diffusion models (DMs) have shown promise in generating high-quality images from textual descriptions. The real-world applications of these models require parti…
Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
Yibo Miao, Hongcheng Gao, Hao Zhang +1
The detection of machine-generated text, especially from large language models (LLMs), is crucial in preventing serious social problems resulting from their misuse. Some methods tr…
Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation
Zhijie Deng, Yucen Luo
Unsupervised semantic segmentation is a long-standing challenge in computer vision with great significance. Spectral clustering is a theoretically grounded solution to it where the…
Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
Peng Cui, Dan Zhang, Zhijie Deng +2
Large-scale pre-trained models have achieved remarkable success in many applications, but how to leverage them to improve the prediction reliability of downstream models is undesir…
On Calibrating Diffusion Probabilistic Models
Tianyu Pang, Cheng Lu, Chao Du +3
Recently, diffusion probabilistic models (DPMs) have achieved promising results in diverse generative tasks. A typical DPM framework includes a forward process that gradually diffu…
Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
Zhijie Deng, Feng Zhou, Jun Zhu
Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks. The generalized Gauss-Newto…
Neural Eigenfunctions Are Structured Representation Learners
Zhijie Deng, Jiaxin Shi, Hao Zhang +3
This paper introduces a structured, adaptive-length deep representation called Neural Eigenmap. Unlike prior spectral methods such as Laplacian Eigenmap that operate in a nonparame…
NeuralEF: Deconstructing Kernels by Deep Neural Networks
Zhijie Deng, Jiaxin Shi, Jun Zhu
Learning the principal eigenfunctions of an integral operator defined by a kernel and a data distribution is at the core of many machine learning problems. Traditional nonparametri…
Deep Ensemble as a Gaussian Process Approximate Posterior
Zhijie Deng, Feng Zhou, Jianfei Chen +2
Deep Ensemble (DE) is an effective alternative to Bayesian neural networks for uncertainty quantification in deep learning. The uncertainty of DE is usually conveyed by the functio…
Exploring Memorization in Adversarial Training
Yinpeng Dong, Ke Xu, Xiao Yang +4
Deep learning models have a propensity for fitting the entire training set even with random labels, which requires memorization of every training sample. In this paper, we explore…
Accurate and Reliable Forecasting using Stochastic Differential Equations
Peng Cui, Zhijie Deng, Wenbo Hu +1
It is critical yet challenging for deep learning models to properly characterize uncertainty that is pervasive in real-world environments. Although a lot of efforts have been made,…
Black-box Detection of Backdoor Attacks with Limited Information and Data
Yinpeng Dong, Xiao Yang, Zhijie Deng +4
Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by…
LiBRe: A Practical Bayesian Approach to Adversarial Detection
Zhijie Deng, Xiao Yang, Shizhen Xu +2
Despite their appealing flexibility, deep neural networks (DNNs) are vulnerable against adversarial examples. Various adversarial defense strategies have been proposed to resolve t…
BayesAdapter: Being Bayesian, Inexpensively and Reliably, via Bayesian Fine-tuning
Zhijie Deng, Jun Zhu
Despite their theoretical appealingness, Bayesian neural networks (BNNs) are left behind in real-world adoption, mainly due to persistent concerns on their scalability, accessibili…
Adversarial Distributional Training for Robust Deep Learning
Yinpeng Dong, Zhijie Deng, Tianyu Pang +2
Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. However, most existing AT method…
Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure
Zhijie Deng, Yucen Luo, Jun Zhu +1
Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayes…
Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
Zhijie Deng, Yucen Luo, Jun Zhu
Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain wit…
Batch Virtual Adversarial Training for Graph Convolutional Networks
Zhijie Deng, Yinpeng Dong, Jun Zhu
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not cons…
Structured Generative Adversarial Networks
Zhijie Deng, Hao Zhang, Xiaodan Liang +4
We study the problem of conditional generative modeling based on designated semantics or structures. Existing models that build conditional generators either require massive labele…