Author name cluster

Xiaolu Zhang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers

2 author rows

EAAI Journal 2026 Journal Article

Evaluating regional green development levels within an incentive effects-based multiple granular probabilistic linguistic combination evaluation method

Xiaolu Zhang

The level of green development serves as a crucial indicator for evaluating the performance of local government officials. Implementing incentive-based measures can effectively enhance officials’ motivation to promote green development. This study aims to develop a multi-granular probabilistic linguistic combination evaluation method based on incentive effects to assess regional green development levels. Probabilistic linguistic term sets in multi-granular contexts are employed to represent the performances of evaluated objects. Novel probabilistic linguistic ranking methods are proposed, emphasizing relative positioning with respect to reference points. Two potent approaches are introduced to determine incentive reference points under different criteria. Incentive mechanisms within multi-granular probabilistic linguistic environments are implemented to reward or penalize objects based on incentive thresholds. Subsequently, four evaluation methods with distinct characteristics and advantages are adopted to assess regional green development levels from diverse perspectives. A consensus degree-based information fusion technique is designed to derive the combined evaluation results for the objects. Finally, the proposed method is applied to evaluate the green development levels of eleven cities. The results enable evaluators to clearly distinguish between rewards and penalties, and to accurately identify the strengths and weaknesses of different objects in terms of green development levels. Comparative and sensitivity analyses further validate the advantages and feasibility of the proposed approach.

Details DOI

ICML Conference 2025 Conference Paper

Effective and Efficient Masked Image Generation Models

Zebin You
Jingyang Ou
Xiaolu Zhang
Jun Hu
Jun Zhou 0011
Chongxuan Li

Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key factors that contribute to both performance and efficiency. Based on the improvements observed during this exploration, we develop our model, referred to as eMIGM. Empirically, eMIGM demonstrates strong performance on ImageNet generation, as measured by Fréchet Inception Distance (FID). In particular, on ImageNet $256\times256$, with similar number of function evaluations (NFEs) and model parameters, eMIGM outperforms the seminal VAR. Moreover, as NFE and model parameters increase, eMIGM achieves performance comparable to the state-of-the-art continuous diffusion model REPA while requiring less than 45% of the NFE. Additionally, on ImageNet $512\times512$, eMIGM outperforms the strong continuous diffusion model EDM2. Code is available at https: //github. com/ML-GSAI/eMIGM.

Details

NeurIPS Conference 2025 Conference Paper

Large Language Diffusion Models

Shen Nie
Fengqi Zhu
Zebin You
Xiaolu Zhang
Jingyang Ou
Jun Hu
Jun Zhou
Yankai Lin

The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning (SFT) paradigm. LLaDA employs a forward data masking process and a reverse generation process, parameterized by a Transformer to predict masked tokens. It provides a principled generative approach for probabilistic inference by optimizing a likelihood lower bound. Across extensive benchmarks on general tasks, math, code, and so on, LLaDA demonstrates strong scalability and performs comparably to our self-constructed ARM baselines. Remarkably, LLaDA 8B is competitive with strong LLMs like LLaMA3 8B in in-context learning and, after SFT, exhibits impressive instruction-following abilities in case studies such as multi-turn dialogue. Moreover, LLaDA addresses the reversal curse, surpassing GPT-4o in a reversal poem completion task. Our findings show the promise of diffusion models for language modeling at scale and challenge the common assumption that core LLM capabilities discussed above inherently depend on ARMs. Project page and codes: \url{https: //ml-gsai. github. io/LLaDA-demo/}.

PDF Details

ICML Conference 2024 Conference Paper

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs

Kaituo Feng
Changsheng Li
Xiaolu Zhang
Jun Zhou 0011
Ye Yuan 0001
Guoren Wang

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Tokens within a rationale vary in significance, and treating them equally may fail to accurately mimic keypoint tokens, leading to reasoning errors. (ii) They usually distill knowledge by consistently predicting all the steps in a rationale, which falls short in distinguishing the learning order of step generation. This diverges from the human cognitive progression of starting with easy tasks and advancing to harder ones, resulting in sub-optimal outcomes. To this end, we propose a unified framework, called KPOD, to address these issues. Specifically, we propose a token weighting module utilizing mask learning to encourage accurate mimicry of keypoint tokens by the student during distillation. Besides, we develop an in-rationale progressive distillation strategy, starting with training the student to generate the final reasoning steps and gradually extending to cover the entire rationale. To accomplish this, a weighted token generation loss is proposed to assess step reasoning difficulty, and a value function is devised to schedule the progressive distillation by considering both step difficulty and question diversity. Extensive experiments on four reasoning benchmarks illustrate our KPOD outperforms previous methods by a large margin.

Details

NeurIPS Conference 2024 Conference Paper

Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization

Rongzhen Wang
Chenyu Zheng
Guoqiang Wu
Xu Min
Xiaolu Zhang
Jun Zhou
Chongxuan Li

Gradient-based bilevel programming leverages unrolling differentiation (UD) or implicit function theorem (IFT) to solve hyperparameter optimization (HO) problems, and is proven effective and scalable in practice. To understand their generalization behavior, existing works establish upper bounds on the uniform stability of these algorithms, while their tightness is still unclear. To this end, this paper attempts to establish stability lower bounds for UD-based and IFT-based algorithms. A central technical challenge arises from the dependency of each outer-level update on the concurrent stage of inner optimization in bilevel programming. To address this problem, we introduce lower-bounded expansion properties to characterize the instability in update rules which can serve as general tools for lower-bound analysis. These properties guarantee the hyperparameter divergence at the outer level and the Lipschitz constant of inner output at the inner level in the context of HO. Guided by these insights, we construct a quadratic example that yields tight lower bounds for the UD-based algorithm and meaningful bounds for a representative IFT-based algorithm. Our tight result indicates that uniform stability has reached its limit in stability analysis for the UD-based algorithm.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models

Hanxiao Zhang
Lin Ju
Chan Wu
Jinjing Huang
Youshao Xiao
Zhenglei Zhou
Zhiming Fan
Zhaoxin Huan

Recently, various strategies for distributed training of large language models (LLMs) have been proposed. By categorizing them into basic strategies and composite strategies, we have discovered that existing basic strategies provide limited options in specific scenarios, leaving considerable room for optimization in training speed. In this paper, we rethink the impact of memory and communication costs on the training speed of LLMs, taking into account the impact of intra- and inter-group communication performance disparities, and then propose a new set of basic strategies named the \textbf{Pa}rtial \textbf{R}edundancy \textbf{O}ptimizer (PaRO). PaRO Data Parallelism (PaRO-DP) accelerates LLM training through refined model state partitioning and tailored training procedures. At the same time, PaRO Collective Communications (PaRO-CC) speeds up collective communication operations by rearranging the topology. We also propose a guideline for choosing different DP strategies based on simple quantitative calculations, which yields minimal ranking errors. Our experiments demonstrate that PaRO improves the training speed of LLMs by up to 266\% that of ZeRO-3 as basic DP strategies. Moreover, employing PaRO-CC independently for model parallel strategies, such as Megatron, can also boost the training speed by 17\%.

PDF Details DOI

ICML Conference 2024 Conference Paper

Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations

Kaiwen Xue
Yuhao Zhou
Shen Nie
Xu Min
Xiaolu Zhang
Jun Zhou 0011
Chongxuan Li

Bayesian flow networks (BFNs) iteratively refine the parameters, instead of the samples in diffusion models (DMs), of distributions at various noise levels through Bayesian inference. Owing to its differentiable nature, BFNs are promising in modeling both continuous and discrete data, while simultaneously maintaining fast sampling capabilities. This paper aims to understand and enhance BFNs by connecting them with DMs through stochastic differential equations (SDEs). We identify the linear SDEs corresponding to the noise-addition processes in BFNs, demonstrate that BFN’s regression losses are aligned with denoise score matching, and validate the sampler in BFN as a first-order solver for the respective reverse-time SDE. Based on these findings and existing recipes of fast sampling in DMs, we propose specialized solvers for BFNs that markedly surpass the original BFN sampler in terms of sample quality with a limited number of function evaluations (e. g. , 10) on both image and text datasets. Notably, our best sampler achieves an increase in speed of $5\sim20$ times for free.

Details

YNIMG Journal 2023 Journal Article

Differential responses in the mirror neuron system during imitation of individual emotional facial expressions and association with autistic traits

Weihua Zhao
Qi Liu
Xiaolu Zhang
Xinwei Song
Zhao Zhang
Peng Qing
Xiaolong Liu
Siyu Zhu

The mirror neuron system (MNS), including the inferior frontal gyrus (IFG), inferior parietal lobule (IPL) and superior temporal sulcus (STS) plays an important role in action representation and imitation and may be dysfunctional in autism spectrum disorder (ASD). However, it's not clear how these three regions respond and interact during the imitation of different basic facial expressions and whether the pattern of responses is influenced by autistic traits. Thus, we conducted a natural facial expression (happiness, angry, sadness and fear) imitation task in 100 healthy male subjects where expression intensity was measured using facial emotion recognition software (FaceReader) and MNS responses were recorded using functional near-infrared spectroscopy (fNIRS). Autistic traits were measured using the Autism Spectrum Quotient questionnaire. Results showed that imitation of happy expressions produced the highest expression intensity but a small deactivation in MNS responses, suggesting a lower processing requirement compared to other expressions. A cosine similarity analysis indicated a distinct pattern of MNS responses during imitation of each facial expression with functional intra-hemispheric connectivity between the left IPL and left STS being significantly higher during happy compared to other expressions, while inter-hemispheric connectivity between the left and right IPL differed between imitation of fearful and sad expressions. Furthermore, functional connectivity changes during imitation of each different expression could reliably predict autistic trait scores. Overall, the results provide evidence for distinct patterns of functional connectivity changes between MNS regions during imitation of different emotions which are also associated with autistic traits.

Details DOI

ICLR Conference 2023 Conference Paper

Towards Open Temporal Graph Neural Networks

Kaituo Feng
Changsheng Li
Xiaolu Zhang
Jun Zhou 0011

Graph neural networks (GNNs) for temporal graphs have recently attracted increasing attentions, where a common assumption is that the class set for nodes is closed. However, in real-world scenarios, it often faces the open set problem with the dynamically increased class set as the time passes by. This will bring two big challenges to the existing dynamic GNN methods: (i) How to dynamically propagate appropriate information in an open temporal graph, where new class nodes are often linked to old class nodes. This case will lead to a sharp contradiction. This is because typical GNNs are prone to make the embeddings of connected nodes become similar, while we expect the embeddings of these two interactive nodes to be distinguishable since they belong to different classes. (ii) How to avoid catastrophic knowledge forgetting over old classes when learning new classes occurred in temporal graphs. In this paper, we propose a general and principled learning approach for open temporal graphs, called OTGNet, with the goal of addressing the above two challenges. We assume the knowledge of a node can be disentangled into class-relevant and class-agnostic one, and thus explore a new message passing mechanism by extending the information bottleneck principle to only propagate class-agnostic knowledge between nodes of different classes, avoiding aggregating conflictive information. Moreover, we devise a strategy to select both important and diverse triad sub-graph structures for effective class-incremental learning. Extensive experiments on three real-world datasets of different domains demonstrate the superiority of our method, compared to the baselines.

Details

IJCAI Conference 2022 Conference Paper

Learning Mixture of Neural Temporal Point Processes for Multi-dimensional Event Sequence Clustering

Yunhao Zhang
Junchi Yan
Xiaolu Zhang
Jun Zhou
Xiaokang Yang

Multi-dimensional event sequence clustering applies to many scenarios e. g. e-Commerce and electronic health. Traditional clustering models fail to characterize complex real-world processes due to the strong parametric assumption. While Neural Temporal Point Processes (NTPPs) mainly focus on modeling similar sequences instead of clustering. To fill the gap, we propose Mixture of Neural Temporal Point Processes (NTPP-MIX), a general framework that can utilize many existing NTPPs for multi-dimensional event sequence clustering. In NTPP-MIX, the prior distribution of coefficients for cluster assignment is modeled by a Dirichlet distribution. When the assignment is given, the conditional probability of a sequence is modeled by the mixture of a series of NTPPs. We combine variational EM algorithm and Stochastic Gradient Descent (SGD) to efficiently train the framework. In E-step, we fix parameters for NTPPs and approximate the true posterior with variational distributions. In M-step, we fix variational distributions and use SGD to update parameters of NTPPs. Extensive experimental results on four synthetic datasets and three real-world datasets show the effectiveness of NTPP-MIX against state-of-the-arts.

PDF Details DOI

ICML Conference 2021 Conference Paper

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

Jiawei Zhang 0013
Linyi Li 0001
Huichen Li
Xiaolu Zhang
Shuang Yang
Bo Li 0026

Boundary based blackbox attack has been recognized as practical and effective, given that an attacker only needs to access the final model prediction. However, the query efficiency of it is in general high especially for high dimensional image data. In this paper, we show that such efficiency highly depends on the scale at which the attack is applied, and attacking at the optimal scale significantly improves the efficiency. In particular, we propose a theoretical framework to analyze and show three key characteristics to improve the query efficiency. We prove that there exists an optimal scale for projective gradient estimation. Our framework also explains the satisfactory performance achieved by existing boundary black-box attacks. Based on our theoretical framework, we propose Progressive-Scale enabled projective Boundary Attack (PSBA) to improve the query efficiency via progressive scaling techniques. In particular, we employ Progressive-GAN to optimize the scale of projections, which we call PSBA-PGAN. We evaluate our approach on both spatial and frequency scales. Extensive experiments on MNIST, CIFAR-10, CelebA, and ImageNet against different models including a real-world face recognition API show that PSBA-PGAN significantly outperforms existing baseline attacks in terms of query efficiency and attack success rate. We also observe relatively stable optimal scales for different models and datasets. The code is publicly available at https: //github. com/AI-secure/PSBA.

Details

AAAI Conference 2020 Conference Paper

Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics

Bingzhe Wu
Chaochao Chen
Shiwan Zhao
Cen Chen
Yuan Yao
Guangyu Sun
Li Wang
Xiaolu Zhang

Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks (DNNs). Stochastic Gradient Langevin Dynamics (SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing properties of SGLD, ranging from the convergence properties to the generalization bounds. In this paper, we study the properties of SGLD from a novel perspective of membership privacy protection (i. e. , preventing the membership attack). The membership attack, which aims to determine whether a speciﬁc sample is used for training a given DNN model, has emerged as a common threat against deep learning algorithms. To this end, we build a theoretical framework to analyze the information leakage (w. r. t. the training dataset) of a model trained using SGLD. Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent. Moreover, our theoretical analysis can be naturally extended to other types of Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods. Empirical results on different datasets and models verify our theoretical ﬁndings and suggest that the SGLD algorithm can not only reduce the information leakage but also improve the generalization ability of the DNN models in real-world applications.

PDF Details

AAAI Conference 2020 Conference Paper

Dynamic Network Pruning with Interpretable Layerwise Channel Selection

Yulong Wang
Xiaolu Zhang
Xiaolin Hu
Bo Zhang
Hang Su

Dynamic network pruning achieves runtime acceleration by dynamically determining the inference paths based on different inputs. However, previous methods directly generate continuous decision values for each weight channel, which cannot reﬂect a clear and interpretable pruning process. In this paper, we propose to explicitly model the discrete weight channel selections, which encourages more diverse weights utilization, and achieves more sparse runtime inference paths. Meanwhile, with the help of interpretable layerwise channel selections in the dynamic network, we can visualize the network decision paths explicitly for model interpretability. We observe that there are clear differences in the layerwise decisions between normal and adversarial examples. Therefore, we propose a novel adversarial example detection algorithm by discriminating the runtime decision features. Experiments show that our dynamic network achieves higher prediction accuracy under the similar computing budgets on CIFAR10 and ImageNet datasets compared to traditional static pruning methods and other dynamic pruning approaches. The proposed adversarial detection algorithm can signiﬁcantly improve the state-of-the-art detection rate across multiple attacks, which provides an opportunity to build an interpretable and robust model.

PDF Details

AAAI Conference 2020 Conference Paper

Pruning from Scratch

Yulong Wang
Xiaolu Zhang
Lingxi Xie
Jun Zhou
Hang Su
Bo Zhang
Xiaolin Hu

Network pruning is an important research ﬁeld aiming at reducing computational costs of neural networks. Conventional approaches follow a ﬁxed paradigm which ﬁrst trains a large and redundant network, and then determines which units (e. g. , channels) are less important and thus can be removed. In this work, we ﬁnd that pre-training an over-parameterized model is not necessary for obtaining the target pruned structure. In fact, a fully-trained over-parameterized model will reduce the search space for the pruned structure. We empirically show that more diverse pruned structures can be directly pruned from randomly initialized weights, including potential models with better performance. Therefore, we propose a novel network pruning pipeline which allows pruning from scratch with little training overhead. In the experiments for compressing classiﬁcation models on CIFAR10 and ImageNet datasets, our approach not only greatly reduces the pre-training burden of traditional pruning methods, but also achieves similar or even higher accuracy under the same computation budgets. Our results facilitate the community to rethink the effectiveness of existing techniques used for network pruning.

PDF Details

IJCAI Conference 2019 Conference Paper

AntProphet: an Intention Mining System behind Alipay's Intelligent Customer Service Bot

Cen Chen
Xiaolu Zhang
Sheng Ju
Chilin Fu
Caizhi Tang
Jun Zhou
Xiaolong Li

We create an intention mining system, named AntProphet, for Alipay's intelligent customer service bot, to alleviate the burden of customer service. Whenever users have any questions, AntProphet is the first stop to help users to answer their questions. Our system gathers users' profile and their historical behavioral trajectories, together with contextual information to predict users' intention, i. e. , the potential questions that users want to resolve. AntProphet takes care of more than 90% of the customer service demands in the Alipay APP and resolves most of the users' problems on the spot, thus significantly reduces the burden of manpower. With the help of it, the overall satisfaction rate of our customer service bot exceeds 85%.

PDF Details

AAAI Conference 2019 Conference Paper

G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification

Bingzhe Wu
Xiaolu Zhang
Shiwan Zhao
Lingxi Xie
Caihong Zeng
Zhihong Liu
Guangyu Sun

Pathological glomerulus classification plays a key role in the diagnosis of nephropathy. As the difference between different subcategories is subtle, doctors often refer to slides from different staining methods to make decisions. However, creating correspondence across various stains is labor-intensive, bringing major difficulties in collecting data and training a vision-based algorithm to assist nephropathy diagnosis. This paper provides an alternative solution for integrating multi-stained visual cues for glomerulus classification. Our approach, named generator-to-classifier (G2C), is a twostage framework. Given an input image from a specified stain, several generators are first applied to estimate its appearances in other staining methods, and a classifier follows to combine visual cues from different stains for prediction (whether it is pathological, or which type of pathology it has). We optimize these two stages in a joint manner. To provide a reasonable initialization, we pre-train the generators in an unlabeled reference set under an unpaired image-to-image translation task, and then fine-tune them together with the classifier. We conduct experiments on a glomerulus type classification dataset collected by ourselves (there are no publicly available datasets for this purpose). Although joint optimization slightly harms the authenticity of the generated patches, it boosts classification performance, suggesting more effective visual cues are extracted in an automatic way. We also transfer our model to a public dataset for breast cancer classification, and outperform the state-of-the-arts significantly.

PDF Details

NeurIPS Conference 2019 Conference Paper

Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection

Bingzhe Wu
Shiwan Zhao
Chaochao Chen
Haoyang Xu
Li Wang
Xiaolu Zhang
Guangyu Sun
Jun Zhou

In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i. e. , the generalization gap can be bounded. Moreover, some recent works, such as the Bayesian GAN, can be re-interpreted based on our theoretical insight from privacy protection. Quantitatively, to evaluate the information leakage of well-trained GAN models, we perform various membership attacks on these models. The results show that previous Lipschitz regularization techniques are effective in not only reducing the generalization gap but also alleviating the information leakage of the training dataset.

PDF Details