Author name cluster

Xudong Wang

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.

18 papers

2 author rows

AAAI Conference 2026 Conference Paper

Adaptive Riemannian Graph Neural Networks

Xudong Wang
Chris Ding
Tongxin Li
Jicong Fan

Graph data often exhibits complex geometric heterogeneity, where structures with varying local curvature, such as tree-like hierarchies and dense communities, coexist within a single network. Existing geometric GNNs, which embed graphs into single fixed-curvature manifolds or discrete product spaces, struggle to capture this diversity. We introduce Adaptive Riemannian Graph Neural Networks (ARGNN), a novel framework that learns a continuous and anisotropic Riemannian metric tensor field over the graph. It allows each node to determine its optimal local geometry, enabling the model to fluidly adapt to the graph's structural landscape. Our core innovation is an efficient parameterization of the node-wise metric tensor, specializing to a learnable diagonal form that captures directional geometric information while maintaining computational tractability. To ensure geometric regularity and stable training, we integrate a Ricci flow-inspired regularization that smooths the learned manifold. Theoretically, we establish the rigorous geometric evolution convergence guarantee for ARGNN and provide a continuous generalization that unifies prior fixed or mixed-curvature GNNs. Empirically, our method demonstrates superior performance on both homophilic and heterophilic benchmark datasets with the ability to capture diverse structures adaptively. Moreover, the learned geometries both offer interpretable insights into the underlying graph structure and empirically corroborate our theoretical analysis.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Auto-PRE: An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation

Junjie Chen
Weihang Su
Zhumin Chu
Haitao Li
Yujia Zhou
Dingbo Yuan
Xudong Wang
Jun Zhou

The rapid development of large language models (LLMs) has highlighted the need for efficient and reliable methods to evaluate their performance. Traditional evaluation methods often face challenges like high costs, limited task formats, dependence on human references, and systematic biases. To address these limitations, we propose Auto-PRE, an automatic LLM evaluation framework inspired by the peer review process. Unlike previous approaches that rely on human annotations, Auto-PRE automatically selects evaluator LLMs based on three core traits: consistency, pertinence, and self-confidence, which correspond to the instruction, content, and response stages, respectively, and collectively cover the entire evaluation process. Experiments on three representative tasks, including summarization, non-factoid QA, and dialogue generation, demonstrate that Auto-PRE achieves state-of-the-art performance while significantly reducing evaluation costs. Furthermore, the structured and scalable design of our automatic qualification exam framework provides valuable insights into automating the evaluation of LLMs-as-judges, paving the way for more advanced LLM-based evaluation frameworks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Bring Your Dreams to Life: Continual Text-to-Video Customization

Jiahua Dong
Xudong Wang
Wenqi Liang
Zongyan Han
Meng Cao
Duzhen Zhang
Hanbin Zhao
Zhi Han

Customized text-to-video generation (CTVG) has recently witnessed great progress in generating tailored videos from user-specific text. However, most CTVG methods assume that personalized concepts remain static and do not expand incrementally over time. Additionally, they struggle with forgetting and concept neglect when continuously learning new concepts, including subjects and motions. To resolve the above challenges, we develop a novel Continual Customized Video Diffusion (CCVD) model, which can continuously learn new concepts to generate videos across various text-to-video generation tasks by tackling forgetting and concept neglect. To address catastrophic forgetting, we introduce a concept-specific attribute retention module and a task-aware concept aggregation strategy. They can capture the unique characteristics and identities of old concepts during training, while combining all subject and motion adapters of old concepts based on their relevance during testing. Besides, to tackle concept neglect, we develop a controllable conditional synthesis to enhance regional features and align video contexts with user conditions, by incorporating layer-specific region attention-guided noise estimation. Extensive experimental comparisons demonstrate that our CCVD outperforms existing CTVG models.

PDF Details DOI

FM Conference 2026 Conference Paper

EUF-based Solving Dyck-Reachability with Applications to Static Analysis

Yide Du
Zhenbang Chen
Kunlin Liu
Guofeng Zhang
Xudong Wang
Ke Ma
Wei Dong
Ji Wang

Abstract Static analysis plays a crucial role in program optimization, bug detection, and automated testing. Dyck-reachability provides a foundational formulation for static analysis, as Dyck grammars can model critical properties such as field and context sensitivity, thus offering broad applicability. This paper shows that static analysis problems modeled as Dyck-reachability on bidirected graphs can be encoded into the EUF SMT theory; consequently, all such problems admit efficient formulation and solution via EUF-based SMT solvers. By leveraging the optimized nature of modern SMT solvers, our method achieves efficiency comparable to state-of-the-art graph-based bidirected Dyck-reachability algorithms while eliminating the need for developing complex specialized graph reachability algorithms. Our approach opens new avenues for solving these classical static analysis problems, demonstrating the strong potential of SMT solvers in encoding static analysis solutions.

DOI

AAAI Conference 2026 Conference Paper

Lifelong Language-Conditioned Robotic Manipulation Learning

Xudong Wang
Zebin Han
Zhiyu Liu
Gan Li
Jiahua Dong
Baichen Liu
Lianqing Liu
Zhi Han

Traditional language-conditioned manipulation agent adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a novel robotic manipulation framework designed to continually learn multiple skills while reducing catastrophic forgetting of old skills. Specifically, we propose a Manipulation Skills Adaptation to retain the old skills knowledge while inheriting the shared knowledge between new and old skills to facilitate learning of new skills. Meanwhile, we perform the singular value decomposition on the diverse skill instructions to obtain common skill semantic subspace projection matrices, thereby recording the essential semantic space of skills. To achieve forget-less and generalization manipulation, we propose a Skills Specialization Aggregation to compute inter-skills similarity in skill semantic subspaces, achieving aggregation of the previously learned skill knowledge for any new or unknown skill. Extensive simulator and real-world experiments demonstrate the effectiveness and superiority of our SkillsCrafter.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning

Zebin Han
Xudong Wang
Baichen Liu
Qi Lyu
Zhenduo Shang
Jiahua Dong
Lianqing Liu
Zhi Han

Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task trajectory navigation guided by complex, long-horizon natural language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a novel navigation model built on a hierarchical planning framework. Our SeqWalker features: (1) A High-Level Planner that dynamically selects global instructions into contextually relevant sub-instructions based on the agent's current visual observations, thus reducing cognitive load; (2) A Low-Level Planner incorporating an Exploration-Verification strategy that leverages the inherent logical structure of instructions for trajectory error correction. To evaluate SH-VLN performance, we also extend the IVLN dataset and establish a new benchmark. Extensive experiments are performed to demonstrate the effectiveness and superiority of SeqWalker.

PDF Details DOI

AAAI Conference 2025 Conference Paper

DMT-RoleBench: A Dynamic Multi-Turn Dialogue Based Benchmark for Role-Playing Evaluation of Large Language Model and Agent

Dingbo Yuan
Yipeng Chen
Guodong Liu
Chenchen Li
Chengfu Tang
Dongxu Zhang
Zhenkui Wang
Xudong Wang

Recent years have witnessed a profound evolution in the abilities of Large Language Model, which has significantly boosted the proliferation of role-playing agents and platforms. Nonetheless, there is a conspicuous absence of systematic and comprehensive evaluations of role-playing abilities which are truly aligned with users' interaction scenarios in real-world. To address this gap, we have devised DMT-RoleBench, a benchmark designed to evaluate the role-playing abilities of large language models and agents based on dynamic multi-turn dialogues. Compared with existed role-playing benchmarks, DMT-RoleBench boasts several principal advantages: (1) It contains a more diverse role types and system prompts of different formats. (2) We propose an innovative evaluation paradigm to assess role-playing abilities based on dynamically generating multi-turn dialogues constrained by specific evaluation intents and topics, which is well aligned with users' interaction scenarios in real-world. (3) We define a three-tiered metric system and provide DMT-RM, which is a reward model aligned with human annotations, to annotate the dialogues. And we propose DMT-Score to calculate the final scores based on the annotated dialogues. Our experiments and analysis of leading models equipped with role-playing abilities have demonstrated the effectiveness of DMT-RoleBench.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Explainable Graph Representation Learning via Graph Pattern Analysis

Xudong Wang
Ziheng Sun
Chris Ding
Jicong Fan

Explainable artificial intelligence (XAI) is an important area in the AI community, and interpretability is crucial for building robust and trustworthy AI models. While previous work has explored model-level and instance-level explainable graph learning, there has been limited investigation into explainable graph representation learning. In this paper, we focus on representation-level explainable graph learning and ask a fundamental question: What specific information about a graph is captured in graph representations? Our approach is inspired by graph kernels, which evaluate graph similarities by counting substructures within specific graph patterns. Although the pattern counting vector can serve as an explainable representation, it has limitations such as ignoring node features and being high-dimensional. To address these limitations, we introduce a framework (PXGL-GNN) for learning and explaining graph representations through graph pattern analysis. We start by sampling graph substructures of various patterns. Then, we learn the representations of these patterns and combine them using a weighted sum, where the weights indicate the importance of each graph pattern's contribution. We also provide theoretical analyses of our methods, including robustness and generalization. In our experiments, we show how to learn and explain graph representations for real-world data using pattern analysis. Additionally, we compare our method against multiple baselines in both supervised and unsupervised learning tasks to demonstrate its effectiveness.

PDF Details DOI

TMLR Journal 2025 Journal Article

Rethinking Patch Dependence for Masked Autoencoders

Letian Fu
Long Lian
Renhao Wang
Baifeng Shi
Xudong Wang
Adam Yala
Trevor Darrell
Alexei A Efros

In this work, we examine the impact of inter-patch dependencies in the decoder of masked autoencoders (MAE) on representation learning. We decompose the decoding mechanism for masked reconstruction into self-attention between mask tokens and cross-attention between masked and visible tokens. Our findings reveal that MAE reconstructs coherent images from visible patches not through interactions between patches in the decoder but by learning a global representation within the encoder. This discovery leads us to propose a simple visual pretraining framework: cross-attention masked autoencoders (CrossMAE). This framework employs only cross-attention in the decoder to independently read out reconstructions for a small subset of masked patches from encoder outputs. This approach achieves comparable or superior performance to traditional MAE across models ranging from ViT-S to ViT-H and significantly reduces computational requirements. By its design, CrossMAE challenges the necessity of interaction between mask tokens for effective masked pretraining. Code and models are publicly available: https://crossmae.github.io/

PDF Details

ICML Conference 2025 Conference Paper

Simplifying DINO via Coding Rate Regularization

Ziyang Wu
Jingyuan Zhang
Druv Pai
Xudong Wang
Chandan Singh
Jianwei Yang
Jianfeng Gao 0001
Yi Ma 0001

DINO and DINOv2 are two model families being widely used to learn representations from unlabeled imagery data at large scales. Their learned representations often enable state-of-the-art performance for downstream tasks, such as image classification and segmentation. However, they employ many empirically motivated design choices and their training pipelines are highly complex and unstable — many hyperparameters need to be carefully tuned to ensure that the representations do not collapse — which poses considerable difficulty to improving them or adapting them to new domains. In this work, we posit that we can remove most such-motivated idiosyncrasies in the pre-training pipelines, and only need to add an explicit coding rate term in the loss function to avoid collapse of the representations. As a result, we obtain highly simplified variants of the DINO and DINOv2 which we call SimDINO and SimDINOv2, respectively. Remarkably, these simplified models are more robust to different design choices, such as network architecture and hyperparameters, and they learn even higher-quality representations, measured by performance on downstream tasks, offering a Pareto improvement over the corresponding DINO and DINOv2 models. This work highlights the potential of using simplifying design principles to improve the empirical practice of deep learning. Code and model checkpoints are available at https: //github. com/RobinWu218/SimDINO.

Details

EAAI Journal 2024 Journal Article

A hybrid artificial intelligence algorithm for fault diagnosis of hot rolled strip crown imbalance

Ruixiao Zhang
Yushuo Qi
Shanshan Kong
Xudong Wang
Mingduo Li

In the production process of hot continuous rolling, due to the imbalance between the number of normal cases and fault cases, the traditional supervised learning methods are often unable to deal with them efficiently. In order to address this problem, a new Hybrid Artificial Intelligence Algorithm is proposed, which is based on Light Gradient Boosting Machine (LightGBM) and combines resampling technique with Support Vector Machine (SVM) to deal with multi-class imbalance problems. Specifically, Support Vector Machines-Synthetic Minority Oversampling Technique (SVM-SMOTE) is used to increase the training data, so as to change the distribution of training data and improve the accuracy of the model, and the Particle Swarm Optimization (PSO) algorithm is used to find the hyper parameters of the model to determine the optimal hyper parameters combination. At the same time, the method of SHapley Additive exPlanation (SHAP) based on game theory is used to reveal the factors affecting the convexity of strip steel plate in hot rolling process and its interpretability. In check to see the validity of the model, experiments were carried out on UCI data set and hot rolling production data set, and multi-model comparison was carried out. The values of Geometric mean (G-mean), macroscopic F1 fraction (F1-Macro) and Matthews correlation coefficient (MCC) tested on the hot rolling data set are 0. 992, 0. 992 and 0. 987 respectively. The model has a good effect. The results show that the model is significantly better than traditional models in solving the problem of strip convexity diagnosis during hot rolling process.

Details DOI

AAAI Conference 2024 Conference Paper

Federated Label-Noise Learning with Local Diversity Product Regularization

Xiaochen Zhou
Xudong Wang

Training data in federated learning (FL) frameworks can have label noise, since they must be stored and annotated on clients' devices. If trained over such corrupted data, the models learn the wrong knowledge of label noise, which highly degrades their performance. Although several FL schemes are designed to combat label noise, they suffer performance degradation when the clients' devices only have limited local training samples. To this end, a new scheme called federated label-noise learning (FedLNL) is developed in this paper. The key problem of FedLNL is how to estimate a noise transition matrix (NTM) accurately in the case of limited local training samples. If a gradient-based update method is used to update the local NTM on each client's device, it can generate too large gradients for the local NTM, causing a high estimation error of the local NTM. To tackle this issue, an alternating update method for the local NTM and the local classifier is designed in FedLNL, where the local NTM is updated by a Bayesian inference-based update method. Such an alternating update method makes the loss function of existing NTM-based schemes not applicable to FedLNL. To enable federated optimization of FedLNL, a new regularizer on the parameters of the classifier called local diversity product regularizer is designed for the loss function of FedLNL. The results show that FedLNL improves the test accuracy of a trained model by up to 25.98%, compared with the state-of-the-art FL schemes that tackle label-noise issues.

PDF Details DOI

ICML Conference 2024 Conference Paper

Learning Graph Representation via Graph Entropy Maximization

Ziheng Sun
Xudong Wang
Chris H. Q. Ding
Jicong Fan 0001

Graph representation learning aims to represent graphs as vectors that can be utilized in downstream tasks such as graph classification. In this work, we focus on learning diverse representations that can capture the graph information as much as possible. We propose quantifying graph information using graph entropy, where we define a probability distribution of a graph based on its nodes’ representations and global-graph representation. However, the computation of graph entropy is NP-hard due to the complex vertex-packing polytope involved in its definition. To address this challenge, we provide an approximation method leveraging orthonormal representations for graph entropy maximization. The proposed method is implemented via graph neural networks, resulting in informative node-level and graph-level representations. Experimental results demonstrate the effectiveness of our method in comparison to many baselines in unsupervised learning and semi-supervised learning tasks. The code of our method is available at https: //github. com/MathAdventurer/GeMax.

Details

NeurIPS Conference 2024 Conference Paper

Segment Anything without Supervision

Xudong Wang
Jingfeng Yang
Trevor Darrell

The Segmentation Anything Model (SAM) requires labor-intensive data labeling. We present Unsupervised SAM (UnSAM) for promptable and automatic whole-image segmentation that does not require human annotations. UnSAM utilizes a divide-and-conquer strategy to “discover” the hierarchical structure of visual scenes. We first leverage top-down clustering methods to partition an unlabeled image into instance/semantic level segments. For all pixels within a segment, a bottom-up clustering method is employed to iteratively merge them into larger groups, thereby forming a hierarchical structure. These unsupervised multi-granular masks are then utilized to supervise model training. Evaluated across seven popular datasets, UnSAM achieves competitive results with the supervised counterpart SAM, and surpasses the previous state-of-the-art in unsupervised segmentation by 11% in terms of AR. Moreover, we show that supervised SAM can also benefit from our self-supervised labels. By integrating our unsupervised pseudo masks into SA-1B’s ground-truth masks and training UnSAM with only 1% of SA-1B, a lightly semi-supervised UnSAM can often segment entities overlooked by supervised SAM, exceeding SAM’s AR by over 6. 7% and AP by 3. 9% on SA-1B.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Hierarchical Open-vocabulary Universal Image Segmentation

Xudong Wang
Shufan Li
Konstantinos Kallidromitis
Yusuke Kato
Kazuki Kozuka
Trevor Darrell

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple lev4 els of granularity, introducing inherent segmentation ambiguity. Unlike existing methods that typically sidestep this ambiguity and treat it as an external factor, our approach actively incorporates a hierarchical representation encompassing different semantic-levels into the learning process. We propose a decoupled text-image fusion mechanism and representation learning modules for both “things” and “stuff”. Additionally, we systematically examine the differences that exist in the textual and visual features between these types of categories. Our resulting model, named HIPIE, tackles HIerarchical, oPen-vocabulary, and unIvErsal segmentation tasks within a unified framework. Benchmarked on diverse datasets, e. g. , ADE20K, COCO, Pascal-VOC Part, and RefCOCO/RefCOCOg, HIPIE achieves the state-of14 the-art results at various levels of image comprehension, including semantic-level (e. g. , semantic segmentation), instance-level (e. g. , panoptic/referring segmentationand object detection), as well as part-level (e. g. , part/subpart segmentation) tasks.

PDF Details

JAIR Journal 2022 Journal Article

C-Face: Using Compare Face on Face Hallucination for Low-Resolution Face Recognition

Feng Han
Xudong Wang
Furao Shen
Jian Zhao

Face hallucination is a task of generating high-resolution (HR) face images from low-resolution (LR) inputs, which is a subfield of the general image super-resolution. However, most of the previous methods only consider the visual effect, ignoring how to maintain the identity of the face. In this work, we propose a novel face hallucination model, called C-Face network, which can generate HR images with high visual quality while preserving the identity information. A face recognition network is used to extract the identity features in the training process. In order to make the reconstructed face images keep the identity information to a great extent, a novel metric, i.e., C-Face loss, is proposed. We also propose a new training algorithm to deal with the convergence problem. Moreover, since our work mainly focuses on the recognition accuracy of the output, we integrate face recognition into the face hallucination process which ensures that the model can be used in real scenarios. Extensive experiments on two large scale face datasets demonstrate that our C-Face network has the best performance compared with other state-of-the-art methods.

PDF Details DOI

JBHI Journal 2022 Journal Article

SDoF-Net: Super Depth of Field Network for Cell Detection in Leucorrhea Micrograph

Xiaohui Du
Xiangzhou Wang
Guangming Ni
Jing Zhang
Ruqian Hao
Jiaxi Zhao
Xudong Wang
Juanxiu Liu

Accompanied with the rapid increase of the demand for routine examination of leucorrhea, efficiency and accuracy become the primary task. However, in super depth of field (SDoF) system, the problem of automatic detection and localization of cells in leucorrhea micro-images is still a big challenge. The changing of the relative position between the cell center and focus plane of microscope lead to variable cell morphological structure in the two-dimensional image, which is an important reason for the low accuracy of current deep learning target detection algorithms. In this paper, an object detection method based on Retinanet in state of super depth of field is proposed, which can achieve high precision detecting of leucorrhea components by the SDoF feature aggregation module. Compared with the current mainstream algorithms, the mean average accuracy (mAP) index has been improved significantly, the mAP index is 82. 7% for SDoF module and 83. 0% for SDoF+ module, with an average increase of more than 10%. These improved features can significantly improve the efficiency and accuracy of the algorithm. The algorithm proposed in this paper can be integrated into the leucorrhea automatic detection system.

Details DOI

AAAI Conference 2021 Conference Paper

Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

Xudong Wang
Stella X. Yu

Convolution is the main building block of a convolutional neural network (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations. We propose Tied Block Convolution (TBC) that shares the same thinner filter over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules. Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates that TBC is consistently leaner and significantly better than standard convolution and group convolution. On attention, with 64× fewer parameters, our TiedSE performs on par with the standard SE. On detection and segmentation, TBC can effectively handle highly overlapping instances, whereas standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals. By sharing filters across channels, TBC reduces correlation and delivers a sizable gain of 6% in the average precision for object detection on MS-COCO when the occlusion ratio is 80%. Our code is publicly available.

PDF Details