Author name cluster

Hua Xu

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.

25 papers

2 author rows

AAAI Conference 2026 Short Paper

Building Interpretable, Trust-worthy Systems for Neural Signal Decoding

Hua Xu

While deep learning excels at decoding neural signals, the opacity of state-of-the-art models limits their scientific utility and clinical trustworthiness. We propose a research that bridges this gap by integrating high-performance architectures—specifically Transformers and Graph Neural Networks—with mechanistic interpretability and neuro-symbolic reasoning. This proposal aims to uncover verifiable mappings between artificial computational circuits and biological dynamics without compromising decoding accuracy. Validated through rigorous benchmarking and wet-lab experiments, this work establishes a foundation for transparent brain-computer interfaces and accelerates fundamental neuroscience research.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Ellipsoid-Based Decision Boundaries for Open Intent Classification

Yuetian Zou
Hanlei Zhang
Hua Xu
Songze Li
Long Xiao

Textual open intent classification is crucial for real-world dialogue systems, enabling robust detection of unknown user intents without prior knowledge and contributing to the robustness of the system. While adaptive decision boundary methods have shown great potential by eliminating manual threshold tuning, existing approaches assume isotropic distributions of known classes, restricting boundaries to balls and overlooking distributional variance along different directions. To address this limitation, we propose EliDecide, a novel method that learns ellipsoid decision boundaries with varying scales along different feature directions. First, we employ supervised contrastive learning to obtain a discriminative feature space for known samples. Second, we apply learnable matrices to parameterize ellipsoids as the boundaries of each known class, offering greater flexibility than spherical boundaries defined solely by centers and radii. Third, we optimize the boundaries via a novelly designed dual loss function that balances empirical and open-space risks: expanding boundaries to cover known samples while contracting them against synthesized pseudo-open samples. Our method achieves state-of-the-art performance on multiple text intent benchmarks and further on a question classification dataset. The flexibility of the ellipsoids demonstrates superior open intent detection capability and strong potential for generalization to more text classification tasks in diverse complex open-world scenarios.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging

Qiyuan Zhu
Dezhi Li
Lujun Li
Xiaoyu Qin
Wei Li
Hao Gu
Hua Xu
Sirui Han

Large Reasoning Language Models (LRMs) have recently shown remarkable performance in complex reasoning tasks, but their extensive reasoning chains incur substantial computational overhead. To address this challenge, we propose Outlier-aware Reasoning Conciseness Adaptive Merge (ORCA), a novel plug-and-play model merging framework that leverages outlier activation patterns to fuse base models with reasoning models. Our ORCA introduces three key innovations: (1) adaptive alignment that reduces conflicts between disparate activation patterns during merging, (2) outlier-guided allocation that assigns merging coefficients proportional to each layer's reasoning importance as indicated by outlier concentrations, and (3) dynamic probe-based adjustment that adapts merging coefficients during inference based on input-specific activation characteristics. These strategies allow seamless integration into existing merging pipelines while creating unified models that maintain reasoning accuracy with significantly reduced response verbosity. Comprehensive evaluation across six benchmarks using Qwen and LLaMA models shows ORCA reduces average response length by 55% while improving accuracy by 2.4∼5.7% over existing methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark

Hanlei Zhang
Zhuohang Li
Hua Xu
Yeshuang Zhu
Peiwu Wang
Haige Zhu
Jie Zhou
Jinchao Zhang

Multimodal language analysis is a rapidly evolving field that leverages multiple modalities to enhance the understanding of high-level semantics underlying human conversational utterances. Despite its significance, little research has investigated the capability of multimodal large language models (MLLMs) to comprehend cognitive-level semantics. In this paper, we introduce MMLA, a comprehensive benchmark specifically designed to address this gap. MMLA comprises over 61K multimodal utterances drawn from both staged and real-world scenarios, covering six core dimensions of multimodal semantics: intent, emotion, dialogue act, sentiment, speaking style, and communication behavior. We evaluate eight mainstream branches of LLMs and MLLMs using three methods: zero-shot inference, supervised fine-tuning, and instruction tuning. Extensive experiments reveal that even fine-tuned models achieve only about 60~70% accuracy, underscoring the limitations of current MLLMs in understanding complex human language. We believe that MMLA will serve as a solid foundation for exploring the potential of large language models in multimodal language analysis and provide valuable resources to advance this field. The datasets and code are open-sourced at https: //github. com/thuiar/MMLA.

PDF Details

ICML Conference 2025 Conference Paper

IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction

Zhangyi Hu
Jiemin Wu
Hua Xu
Mingqian Liao
Ninghui Feng
Bo Gao
Songning Lai
Yutao Yue

Irregular Multivariate Time Series (IMTS) forecasting is challenging due to the unaligned nature of multi-channel signals and the prevalence of extensive missing data. Existing methods struggle to capture reliable temporal patterns from such data due to significant missing values. While pre-trained foundation models show potential for addressing these challenges, they are typically designed for Regularly Sampled Time Series (RTS). Motivated by the visual Mask AutoEncoder’s (MAE) powerful capability for modeling sparse multi-channel information and its success in RTS forecasting, we propose VIMTS, a framework adapting V isual MAE for IMTS forecasting. To mitigate the effect of missing values, VIMTS first processes IMTS along the timeline into feature patches at equal intervals. These patches are then complemented using learned cross-channel dependencies. Then it leverages visual MAE’s capability in handling sparse multichannel data for patch reconstruction, followed by a coarse-to-fine technique to generate precise predictions from focused contexts. In addition, we integrate self-supervised learning for improved IMTS modeling by adapting the visual MAE to IMTS data. Extensive experiments demonstrate VIMTS’s superior performance and few-shot capability, advancing the application of visual foundation models in more general time series tasks. Our code is available at https: //github. com/WHU-HZY/VIMTS.

Details

AAAI Conference 2024 Conference Paper

Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition

Qianrui Zhou
Hua Xu
Hao Li
Hanlei Zhang
Xiaohan Zhang
Yifan Wang
Kai Gao

Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world multimodal scenarios. Nevertheless, the majority of existing methods ignore potential correlations among different modalities and own limitations in effectively learning semantic features from nonverbal modalities. In this paper, we introduce a token-level contrastive learning method with modality-aware prompting (TCL-MAP) to address the above challenges. To establish an optimal multimodal semantic environment for text modality, we develop a modality-aware prompting module (MAP), which effectively aligns and fuses features from text, video and audio modalities with similarity-based modality alignment and cross-modality attention mechanism. Based on the modality-aware prompt and ground truth labels, the proposed token-level contrastive learning framework (TCL) constructs augmented samples and employs NT-Xent loss on the label token. Specifically, TCL capitalizes on the optimal textual semantic insights derived from intent labels to guide the learning processes of other modalities in return. Extensive experiments show that our method achieves remarkable improvements compared to state-of-the-art methods. Additionally, ablation analyses demonstrate the superiority of the modality-aware prompt over the handcrafted prompt, which holds substantial significance for multimodal prompt learning. The codes are released at https://github.com/thuiar/TCL-MAP.

PDF Details DOI

AAAI Conference 2023 Short Paper

Adaptive Constraint Partition Based Optimization Framework for Large-Scale Integer Linear Programming (Student Abstract)

Huigen Ye
Hongyan Wang
Hua Xu
Chengming Wang
Yu Jiang

Integer programming problems (IPs) are challenging to be solved efficiently due to the NP-hardness, especially for large-scale IPs. To solve this type of IPs, Large neighborhood search (LNS) uses an initial feasible solution and iteratively improves it by searching a large neighborhood around the current solution. However, LNS easily steps into local optima and ignores the correlation between variables to be optimized, leading to compromised performance. This paper presents a general adaptive constraint partition-based optimization framework (ACP) for large-scale IPs that can efficiently use any existing optimization solver as a subroutine. Specifically, ACP first randomly partitions the constraints into blocks, where the number of blocks is adaptively adjusted to avoid local optima. Then, ACP uses a subroutine solver to optimize the decision variables in a randomly selected block of constraints to enhance the variable correlation. ACP is compared with LNS framework with different subroutine solvers on four IPs and a real-world IP. The experimental results demonstrate that in specified wall-clock time ACP shows better performance than SCIP and Gurobi.

PDF Details DOI

AAAI Conference 2023 System Paper

Robust-MSA: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis

Huisheng Mao
Baozheng Zhang
Hua Xu
Ziqi Yuan
Yihe Liu

Improving model robustness against potential modality noise, as an essential step for adapting multimodal models to real-world applications, has received increasing attention among researchers. For Multimodal Sentiment Analysis (MSA), there is also a debate on whether multimodal models are more effective against noisy features than unimodal ones. Stressing on intuitive illustration and in-depth analysis of these concerns, we present Robust-MSA, an interactive platform that visualizes the impact of modality noise as well as simple defence methods to help researchers know better about how their models perform with imperfect real-world data.

PDF Details DOI

AAAI Conference 2023 Short Paper

Self-Paced Learning Based Graph Convolutional Neural Network for Mixed Integer Programming (Student Abstract)

Li Chen
Hua Xu
Ziteng Wang
Chengming Wang
Yu Jiang

Graph convolutional neural network (GCN) based methods have achieved noticeable performance in solving mixed integer programming problems (MIPs). However, the generalization of existing work is limited due to the problem structure. This paper proposes a self-paced learning (SPL) based GCN network (SPGCN) with curriculum learning (CL) to make the utmost of samples. SPGCN employs a GCN model to imitate the branching variable selection during the branch and bound process, while the training process is conducted in a self-paced fashion. Specifically, SPGCN contains a loss-based automatic difficulty measurer, where the training loss of the sample represents the difficulty level. In each iteration, a dynamic training dataset is constructed according to the difficulty level for GCN model training. Experiments on four NP-hard datasets verify that CL can lead to generalization improvement and convergence speedup in solving MIPs, where SPL performs better than predefined CL methods.

PDF Details DOI

AAAI Conference 2022 System Paper

An End-to-End Traditional Chinese Medicine Constitution Assessment System Based on Multimodal Clinical Feature Representation and Fusion

Huisheng Mao
Baozheng Zhang
Hua Xu
Kai Gao

Traditional Chinese Medicine (TCM) constitution is a fundamental concept in TCM theory. It is determined by multimodal TCM clinical features which, in turn, are obtained from TCM clinical information of image (face, tongue, etc.), audio (pulse and voice), and text (inquiry) modality. The auto assessment of TCM constitution is faced with two major challenges: (1) learning discriminative TCM clinical feature representations; (2) jointly processing the features using multimodal fusion techniques. The TCM Constitution Assessment System (TCM-CAS) is proposed to provide an end-to-end solution to this task, along with auxiliary functions to aid TCM researchers. To improve the results of TCM constitution prediction, the system combines multiple machine learning algorithms such as facial landmark detection, image segmentation, graph neural networks and multimodal fusion. Extensive experiments are conducted on a four-category multimodal TCM constitution dataset, and the proposed method achieves state-of-the-art accuracy. Provided with datasets containing annotations of diseases, the system can also perform automatic disease diagnosis from a TCM perspective.

PDF Details

AAAI Conference 2021 Conference Paper

Deep Open Intent Classification with Adaptive Decision Boundary

Hanlei Zhang
Hua Xu
Ting-En Lin

Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge. Current models are limited in finding the appropriate decision boundary to balance the performances of both known intents and the open intent. In this paper, we propose a postprocessing method to learn the adaptive decision boundary (ADB) for open intent classification. We first utilize the labeled known intent samples to pre-train the model. Then, we automatically learn the adaptive spherical decision boundary for each known class with the aid of well-trained features. Specifically, we propose a new loss function to balance both the empirical risk and the open space risk. Our method does not need open intent samples and is free from modifying the model architecture. Moreover, our approach is surprisingly insensitive with less labeled data and fewer known intents. Extensive experiments on three benchmark datasets show that our method yields significant improvements compared with the state-of-the-art methods. The codes are released at https: //github. com/thuiar/Adaptive-Decision-Boundary.

PDF Details

AAAI Conference 2021 Conference Paper

Discovering New Intents with Deep Aligned Clustering

Hanlei Zhang
Hua Xu
Ting-En Lin
Rui Lyu

Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents. In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data. Firstly, we leverage a few labeled known intent samples as prior knowledge to pre-train the model. Then, we perform k-means to produce cluster assignments as pseudo-labels. Moreover, we propose an alignment strategy to tackle the label inconsistency problem during clustering assignments. Finally, we learn the intent representations under the supervision of the aligned pseudo-labels. With an unknown number of new intents, we predict the number of intent categories by eliminating low-confidence intent-wise clusters. Extensive experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods. The codes are released at https: //github. com/thuiar/DeepAligned- Clustering.

PDF Details

AAAI Conference 2021 Conference Paper

Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis

Wenmeng Yu
Hua Xu
Ziqi Yuan
Jiele Wu

Representation Learning is a significant and challenging task in multimodal learning. Effective modality representations should contain two parts of characteristics: the consistency and the difference. Due to the unified multimodal annotation, existing methods are restricted in capturing differentiated information. However, additional unimodal annotations are high time- and labor-cost. In this paper, we design a label generation module based on the self-supervised learning strategy to acquire independent unimodal supervisions. Then, joint training the multimodal and uni-modal tasks to learn the consistency and difference, respectively. Moreover, during the training stage, we design a weight-adjustment strategy to balance the learning progress among different subtasks. That is to guide the subtasks to focus on samples with the larger difference between modality supervisions. Last, we conduct extensive experiments on three public multimodal baseline datasets. The experimental results validate the reliability and stability of auto-generated unimodal supervisions. On MOSI and MOSEI datasets, our method surpasses the current state-of-the-art methods. On the SIMS dataset, our method achieves comparable performance than humanannotated unimodal labels. The full codes are available at https: //github. com/thuiar/Self-MM.

PDF Details

AAAI Conference 2020 Short Paper

A Multi-Task Learning Machine Reading Comprehension Model for Noisy Document (Student Abstract)

Zhijing Wu
Hua Xu

Current neural models for Machine Reading Comprehension (MRC) have achieved successful performance in recent years. However, the model is too fragile and lack robustness to tackle the imperceptible adversarial perturbations to the input. In this work, we propose a multi-task learning MRC model with a hierarchical knowledge enrichment to further improve the robustness for noisy document. Our model follows a typical encode-align-decode framework. Additionally, we apply a hierarchical method of adding background knowledge into the model from coarse-to-ﬁne to enhance the language representations. Besides, we optimize our model by jointly training the answer span and unanswerability prediction, aiming to improve the robustness to noise. Experiment results on benchmark datasets conﬁrm the superiority of our method, and our method can achieve competitive performance compared with other strong baselines.

PDF Details

AAAI Conference 2020 Short Paper

Combining Fine-Tuning with a Feature-Based Approach for Aspect Extraction on Reviews (Student Abstract)

Xili Wang
Hua Xu
Xiaomin Sun
Guangcan Tao

One key task of ﬁne-grained sentiment analysis on reviews is to extract aspects or features that users have expressed opinions on. Generally, ﬁne-tuning BERT with sophisticated taskspeciﬁc layers can achieve better performance than only extend one extra task-speciﬁc layer (e. g. , a fully-connected + softmax layer) since not all tasks can easily be represented by Transformer encoder architecture and special task-speciﬁc layer can capture task-speciﬁc features. However, BERT ﬁnetuning may be unstable on a small-scale dataset. Besides, in our experiments, directly ﬁne-tuning BERT on extending sophisticated task-speciﬁc layers did not take advantage of the features of task-speciﬁc layers and even restrict the performance of BERT module. To address the above consideration, this paper combines Fine-tuning with a feature-based approach to extract aspect. To the best of our knowledge, this is the ﬁrst paper to combine ﬁne-tuning with a feature-based approach for aspect extraction.

PDF Details

AAAI Conference 2020 Short Paper

Constrained Self-Supervised Clustering for Discovering New Intents (Student Abstract)

Ting-En Lin
Hua Xu
Hanlei Zhang

Discovering new user intents is an emerging task in the dialogue system. In this paper, we propose a self-supervised clustering method that can naturally incorporate pairwise constraints as prior knowledge to guide the clustering process and does not require intensive feature engineering. Extensive experiments on three benchmark datasets show that our method can yield signiﬁcant improvements over strong baselines.

PDF Details

AAAI Conference 2020 Short Paper

CORAL-DMOEA: Correlation Alignment-Based Information Transfer for Dynamic Multi-Objective Optimization (Student Abstract)

Li Chen
Hua Xu

One essential characteristic of dynamic multi-objective optimization problems is that Pareto-Optimal Front/Set (POF/POS) varies over time. Tracking the time-dependent POF/POS is a challenging problem. Since continuous environments are usually highly correlated, past information is critical for the next optimization process. In this paper, we integrate CORAL methodology into a dynamic multi-objective evolutionary algorithm, named CORAL-DMOEA. This approach employs CORAL to construct a transfer model which transfer past well-performed solutions to form an initial population for the next optimization process. Experimental results demonstrate that CORAL-DMOEA can effectively improve the quality of solutions and accelerate the evolution process.

PDF Details

AAAI Conference 2020 Conference Paper

Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement

Ting-En Lin
Hua Xu
Hanlei Zhang

Identifying new user intents is an essential task in the dialogue system. However, it is hard to get satisfying clustering results since the deﬁnition of intents is strongly guided by prior knowledge. Existing methods incorporate prior knowledge by intensive feature engineering, which not only leads to overﬁtting but also makes it sensitive to the number of clusters. In this paper, we propose constrained deep adaptive clustering with cluster reﬁnement (CDAC+), an end-toend clustering method that can naturally incorporate pairwise constraints as prior knowledge to guide the clustering process. Moreover, we reﬁne the clusters by forcing the model to learn from the high conﬁdence assignments. After eliminating low conﬁdence assignments, our approach is surprisingly insensitive to the number of clusters. Experimental results on the three benchmark datasets show that our method can yield signiﬁcant improvements over strong baselines. 1

PDF Details

AAAI Conference 2020 Short Paper

Multi-Channel Convolutional Neural Networks with Adversarial Training for Few-Shot Relation Classification (Student Abstract)

Yuxiang Xie
Hua Xu
Congcong Yang
Kai Gao

The distant supervised (DS) method has improved the performance of relation classiﬁcation (RC) by means of extending the dataset. However, DS also brings the problem of wrong labeling. Contrary to DS, the few-shot method relies on few supervised data to predict the unseen classes. In this paper, we use word embedding and position embedding to construct multi-channel vector representation and use the multi-channel convolutional method to extract features of sentences. Moreover, in order to alleviate few-shot learning to be sensitive to overﬁtting, we introduce adversarial learning for training a robust model. Experiments on the FewRel dataset show that our model achieves signiﬁcant and consistent improvements on few-shot RC as compared with baselines.

PDF Details

AAAI Conference 2020 Short Paper

SATNet: Symmetric Adversarial Transfer Network Based on Two-Level Alignment Strategy towards Cross-Domain Sentiment Classification (Student Abstract)

Yu Cao
Hua Xu

In recent years, domain adaptation tasks have attracted much attention, especially, the task of cross-domain sentiment classiﬁcation (CDSC). In this paper, we propose a novel domain adaptation method called Symmetric Adversarial Transfer Network (SATNet). Experiments on the Amazon reviews dataset demonstrate the effectiveness of SATNet.

PDF Details

AAAI Conference 2019 Short Paper

Video-Based Sentiment Analysis with hvnLBP-TOP Feature and bi-LSTM

Haoran Li
Hua Xu

In this paper, we propose a new feature extraction method called hvnLBP-TOP for video-based sentiment analysis. Furthermore, we use principal component analysis (PCA) and bidirectional long short term memory (bi-LSTM) for dimensionality reduction and classification. We achieved an average recognition accuracy of 71. 1% on the MOUD dataset and 63. 9% on the CMU-MOSI dataset.

PDF Details

AIIM Journal 2017 Journal Article

Identification of adverse drug-drug interactions through causal association rule discovery from spontaneous adverse event reports

Ruichu Cai
Mei Liu
Yong Hu
Brittany L. Melton
Michael E. Matheny
Hua Xu
Lian Duan
Lemuel R. Waitman

Objective Drug-drug interaction (DDI) is of serious concern, causing over 30% of all adverse drug reactions and resulting in significant morbidity and mortality. Early discovery of adverse DDI is critical to prevent patient harm. Spontaneous reporting systems have been a major resource for drug safety surveillance that routinely collects adverse event reports from patients and healthcare professionals. In this study, we present a novel approach to discover DDIs from the Food and Drug Administration’s adverse event reporting system. Methods Data-driven discovery of DDI is an extremely challenging task because higher-order associations require analysis of all combinations of drugs and adverse events and accurate estimate of the relationships between drug combinations and adverse event require cause-and-effect inference. To efficiently identify causal relationships, we introduce the causal concept into association rule mining by developing a method called Causal Association Rule Discovery (CARD). The properties of V-structures in Bayesian Networks are utilized in the search for causal associations. To demonstrate feasibility, CARD is compared to the traditional association rule mining (AR) method in DDI identification. Results Based on physician evaluation of 100 randomly selected higher-order associations generated by CARD and AR, CARD is demonstrated to be more accurate in identifying known drug interactions compared to AR, 20% vs. 10% respectively. Moreover, CARD yielded a lower number of drug combinations that are unknown to interact, i. e. , 50% for CARD and 79% for AR. Conclusion Evaluation analysis demonstrated that CARD is more likely to identify true causal drug variables and associations to adverse event.

Details DOI

IS Journal 2012 Journal Article

Product Feature Grouping for Opinion Mining

Zhongwu Zhai
Bing Liu
Jingyuan Wang
Hua Xu
Peifa Jia

A constrained semisupervised learning method classifies words and phrases into feature groups, making it easier to produce an opinion summary of various product reviews.

Details DOI

AAAI Conference 2011 Conference Paper

Identifying Evaluative Sentences in Online Discussions

Zhongwu Zhai
Bing Liu
Lei Zhang
Hua Xu
Peifa Jia

Much of opinion mining research focuses on product reviews because reviews are opinion-rich and contain little irrelevant information. However, this cannot be said about online discussions and comments. In such postings, the discussions can get highly emotional and heated with many emotional statements, and even personal attacks. As a result, many of the postings and sentences do not express positive or negative opinions about the topic being discussed. To find people’s opinions on a topic and its different aspects, which we call evaluative opinions, those irrelevant sentences should be removed. The goal of this research is to identify evaluative opinion sentences. A novel unsupervised approach is proposed to solve the problem, and our experimental results show that it performs well.

PDF Details

IROS Conference 2006 Conference Paper

RTOC: A Rt-Linux Based Open Robot Controller

Hua Xu
Peifa Jia

An open robot control system pursues easy extension, flexible reconfiguration, facile portability and jointless interoperation. Therefore, the system elements from multi-disciplinary areas can be integrated and reconfigured easily in such a system. Also the system modules can be ported flexibly. In this paper, a Rt-linux based open robot controller (RTOC) is investigated. A reference model for robot controlling is proposed, in which hardware platform, operating system module and application modules are included. Then for the implementation of RTOC, two critical implementation problems- layered architecture and the intra-layer interfaces are discussed on the base of its reference model. The RTOC openness is also analyzed. Consequently, the proposed RTOC is applied to an industrial arc welding robot.

Details