Author name cluster

Hongwei 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

Beyond Single-Speed Reasoning: Coordinating Fast and Slow Dynamics for Efficient World Modeling

Hongwei Wang
Yangru Huang
Guangyao Chen
Xu Wang
Yi Jin

Model-based reinforcement learning (MBRL) enables efficient decision-making by learning predictive world modelsof environment dynamics. Despite recent advances, existingmodels often struggle to reconcile accurate short-term transitions with coherent long-term planning, especially in partially observable or long-horizon settings. We argue that thislimitation often stems from modeling all transitions at a single temporal resolution, which makes it challenging to simultaneously capture fine-grained local dynamics and abstractglobal structures. To this end, we propose SF-RSSM (Slow-Fast Recurrent State-Space Model), a novel method that decouples short-term and long-term dynamics via a dualbranchdesign. The fast branch captures short-horizon transitions using residual prediction, while the slow branch models long-range dependencies with a GRU-based recurrent pathway.A distillation mechanism is developed to enable cooperationacross timescales, with the slow model providing soft targetsto guide the fast model. Additionally, a curiosity module encourages exploration by promoting learning in regions wherethe fast and slow branches exhibit divergent dynamics. Experiments on CARLA, DMControl and Atari benchmarks showthat SF-RSSM outperforms strong baselines in policy performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

CP-Router: An Uncertainty-Aware Router Between LLM and LRM

Jiayuan Su
Fulin Lin
Zhaopeng Feng
Han Zheng
Teng Wang
Zhenyu Xiao
Xinlong Zhao
Zuozhu Liu

Recent advances in large reasoning models (LRMs) have significantly enhanced long-chain reasoning capabilities over standard large language models (LLMs). However, LRMs often produce unnecessarily lengthy outputs even for simple queries, leading to inefficiencies or even accuracy degradation compared to LLMs. To address this, we propose CP-Router, a training-free, model-agnostic routing framework that dynamically selects between an LLM and an LRM, demonstrated with multiple-choice question answering (MCQA) prompts. The routing decision is guided by the prediction uncertainty estimates derived via Conformal Prediction (CP), which provides rigorous coverage guarantees. To improve uncertainty differentiation across inputs, we introduce Full and Binary Entropy (FBE), a novel entropy-based criterion that adaptively selects the appropriate CP threshold. Experiments across MCQA and QA benchmarks—including mathematics, logical reasoning, and Chinese chemistry—demonstrate that CP-Router efficiently reduces token usage while maintaining or even improving accuracy compared to using LRM alone. We further demonstrate the generality and robustness of CP-Router by extending it to diverse model pairings beyond the LLM–LRM setting.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation

Zhuonan Wang
Zhenxuan Fan
Siwen Tan
Yu Zhong
Yuqian Yuan
Haoyuan Li
Hao Jiang
Wenqiao Zhang

As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse and complex anomaly patterns. To address these challenges, we introduce MAU-Set, a comprehensive dataset for Multi-type industrial Anomaly Understanding. It spans multiple industrial domains and features a hierarchical task structure, ranging from binary classification to complex reasoning. Alongside this dataset, we establish a rigorous evaluation protocol to facilitate fair and comprehensive model assessment. Building upon this foundation, we further present MAU-GPT, a domain-adapted multimodal large model specifically designed for industrial anomaly understanding. It incorporates a novel AMoE-LoRA mechanism that unifies anomaly-aware and generalist experts adaptation, enhancing both understanding and reasoning across diverse defect classes. Extensive experiments show that MAU-GPT consistently outperforms prior state-of-the-art methods across all domains, demonstrating strong potential for scalable and automated industrial inspection.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Understanding Dynamic Scenes in Ego Centric 4D Point Clouds

Junsheng Huang
Shengyu Hao
Bo-Cheng Hu
Hongwei Wang
Gaoang Wang

Understanding dynamic 4D scenes from an egocentric perspective—modeling changes in 3D spatial structure over time—is crucial for human–machine interaction, autonomous navigation, and embodied intelligence. While existing egocentric datasets contain dynamic scenes, they lack unified 4D annotations and task-driven evaluation protocols for fine-grained spatio-temporal reasoning, especially on motion of objects and human, together with their interactions. To address this gap, we introduce EgoDynamic4D, a novel QA benchmark on highly dynamic scenes, comprising RGB-D video, camera poses, globally unique instance masks, and 4D bounding boxes. We construct 927K QA pairs accompanied by explicit Chain-of-Thought (CoT), enabling verifiable, step-by-step spatio-temporal reasoning. We design 12 dynamic QA tasks covering agent motion, human–object interaction, trajectory prediction, relation understanding, and temporal–causal reasoning, with fine-grained, multidimensional metrics. To tackle these tasks, we propose an end-to-end spatio-temporal reasoning framework that unifies dynamic and static scene information, using instance-aware feature encoding, time and camera encoding, and spatially adaptive down-sampling to compress large 4D scenes into token sequences manageable by LLMs. Experiments on EgoDynamic4D show that our method consistently outperforms baselines, validating the effectiveness of multimodal temporal modeling for egocentric dynamic scene understanding.

PDF Details DOI

AAAI Conference 2025 Conference Paper

FSTA-SNN:Frequency-Based Spatial-Temporal Attention Module for Spiking Neural Networks

Kairong Yu
Tianqing Zhang
Hongwei Wang
Qi Xu

Spiking Neural Networks (SNNs) are emerging as a promising alternative to Artificial Neural Networks (ANNs) due to their inherent energy efficiency. Owing to the inherent sparsity in spike generation within SNNs, the in-depth analysis and optimization of intermediate output spikes are often neglected. This oversight significantly restricts the inherent energy efficiency of SNNs and diminishes their advantages in spatiotemporal feature extraction, resulting in a lack of accuracy and unnecessary energy expenditure. In this work, we analyze the inherent spiking characteristics of SNNs from both temporal and spatial perspectives. In terms of spatial analysis, we find that shallow layers tend to focus on learning vertical variations, while deeper layers gradually learn horizontal variations of features. Regarding temporal analysis, we observe that there is not a significant difference in feature learning across different time steps. This suggests that increasing the time steps has limited effect on feature learning. Based on the insights derived from these analyses, we propose a Frequency-based Spatial-Temporal Attention (FSTA) module to enhance feature learning in SNNs. This module aims to improve the feature learning capabilities by suppressing redundant spike features. The experimental results indicate that the introduction of the FSTA module significantly reduces the spike firing rate of SNNs, demonstrating superior performance compared to state-of-the-art baselines across multiple datasets.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Data

Mengxuan Li
Ke Liu
Jialong Guo
Jiajun Bu
Hongwei Wang
Haishuai Wang

Healthcare data frequently contain a substantial proportion of missing values, necessitating effective time series imputation to support downstream disease diagnosis tasks. However, existing imputation methods focus on discrete data points and are unable to effectively model sparse data, resulting in particularly poor performance for imputing substantial missing values. In this paper, we propose a novel approach, ImputeINR, for time series imputation by employing implicit neural representations (INR) to learn continuous functions for time series. ImputeINR leverages the merits of INR in that the continuous functions are not coupled to sampling frequency and have infinite sampling frequency, allowing ImputeINR to generate fine-grained imputations even on extremely sparse observed values. Extensive experiments conducted on eight datasets with five ratios of masked values show the superior imputation performance of ImputeINR, especially for high missing ratios in time series data. We also validate that applying ImputeINR to impute missing values in healthcare data enhances the performance of downstream disease diagnosis tasks.

PDF Details DOI

ICLR Conference 2025 Conference Paper

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Di Wu 0054
Hongwei Wang
Wenhao Yu 0002
Yuwei Zhang 0001
Kai-Wei Chang 0001
Dong Yu 0001

Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assistant chat histories, LongMemEval presents a significant challenge to existing long-term memory systems, with commercial chat assistants and long-context LLMs showing a 30% accuracy drop on memorizing information across sustained interactions. We then present a unified framework that breaks down the long-term memory design into three stages: indexing, retrieval, and reading. Built upon key experimental insights, we propose several memory design optimizations including session decomposition for value granularity, fact-augmented key expansion for indexing, and time-aware query expansion for refining the search scope. Extensive experiments show that these optimizations greatly improve both memory recall and downstream question answering on LongMemEval. Overall, our study provides valuable resources and guidance for advancing the long-term memory capabilities of LLM-based chat assistants, paving the way toward more personalized and reliable conversational AI. Our benchmark and code are publicly available at https://github.com/xiaowu0162/LongMemEval.

Details

JBHI Journal 2025 Journal Article

Personalized Continuous Blood Pressure Tracking Through Single Channel PPG in Wearable Scenarios

Yiming Zhang
Congcong Zhou
Xianglin Ren
Qing Wang
Hongwei Wang
Ting Xiang
Shirong Qiu
Yuan-Ting Zhang

The real-time tracking of human physiopathology states can significantly enhance the quality of personalized healthcare services. Photoplethysmography (PPG) detection is a rapid, portable and non-invasive method for measuring blood flow volume, widely used for monitoring blood pressure (BP) and cardiovascular status. However, continuous BP monitoring technologies based on PPG face numerous challenges in real-world wearable scenarios, such as poor signal quality, complex model computation, and the need for frequent calibration. This work proposed a personalized continuous BP tracking pipeline that performed automatic PPG signal quality grading to reduce the difficulty of model fitting, introduced a lightweight BP model (SCI-GTCN) to alleviate computational complexity, and employed an adaptive calibration strategy to achieve long-term BP monitoring performance under different scenarios. The proposed pipeline was validated using data from 134 subjects in various monitoring scenarios (daytime, nighttime, and abnormal states), assessing the model's performance during rapid BP changes, circadian rhythm fluctuations, and long-term monitoring. The ME ± SD was 0. 99 ± 7. 91/0. 36 ± 5. 43 mmHg. Overall, the results of our method are within the accuracy requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standards, though the subject distribution differs. The method demonstrated good robustness and applicability, making it convenient for deployment on wearable devices and promising in the healthcare field.

Details DOI

IROS Conference 2025 Conference Paper

Reinforcement Learning-Based Energy-Efficient and Obstacle-Free Path Planning for Magnetic Microrobots in Dynamic Environments

Hongwei Wang
Mingxue Cai
Jun Luo
Mingguo Jiang
Chenyang Huang 0004
Haolan Shen
Tiantian Xu 0001

Online path planning for magnetic microrobots actuated by electromagnetic system in dynamic flow field presents significant challenges due to time-varying fluid dynamics, energy constraints, and collision risks. Traditional path planning approaches, which often rely on static flow assumptions or simplified geometric models, struggle to balance energy efficiency, path continuity, and adaptability in real-world scenarios. This paper introduces an end-to-end path planner for energy-efficient and collision-free navigation of magnetic helical microrobots, integrating flow field feature extraction and reinforcement learning (RL) framework. Our method employs a transformer encoder to capture contextual correlations of flow field and uses a Soft Actor-Critic (SAC) framework to optimize energy consumption while ensuring dynamic obstacle avoidance. Simulations and experiments in dynamic flow environments validate our approach, demonstrating 14. 7% lower energy consumption and robust collision avoidance in several different test scenarios.

Details

EAAI Journal 2024 Journal Article

A novel brain-inspired approach based on spiking neural network for cooperative control and protection of multiple trains

Zixuan Zhang
Haifeng Song
Hongwei Wang
Ligang Tan
Hairong Dong

The ongoing challenge of addressing critical issues related to intelligent cooperative control and active protection persists due to the absence of a comprehensive and efficient integrated solution. To address this challenge, this paper introduces a brain-inspired controller that emulates the collaborative functionalities of various brain regions, harnessing the power of spiking neural networks. The controller’s primary tasks include reference velocity tracking, cooperative control, and active protection, with a special focus on cooperative protection within distinct operational modes. Furthermore, the fundamental principles of incorporating spiking neural networks into train control, such as coding and decoding mechanisms, are expounded. The overarching controller is partitioned into two principal functional segments. The first segment involves emulating the prefrontal cortex (PFC) for reference velocity tracking and active protection against overspeed and collisions through motor control and movement planning. The second segment employs a cerebellum-inspired network for cooperative control. Additionally, the brain-inspired network introduced in this study undergoes training utilizing biologically-inspired mechanisms, incorporating dopamine and pertinent teaching signals to facilitate realistic synaptic modifications. Simulation results in several scenarios validate the proposed approach.

Details DOI

EAAI Journal 2024 Journal Article

Reliability-centered availability collaborative optimization allocation approach for machine tools

Yifan Chen
Zongyi Mu
Hongwei Wang
Genbao Zhang

The availability of computer numerical control (CNC) machine tools is a comprehensive reflection of reliability and maintainability. To ensure the availability requirements of products, it is necessary to allocate the availability indicators of the entire machine to all units. Traditional methods based on reliability allocation or maintainability allocation ignore the coupling relationships among them, which cannot comprehensively improve the availability level of machine tools. Therefore, in this paper, a availability collaborative optimization allocation model for CNC machine tools is proposed to maximize the availability under the optimal combination of failure rate and repair rate. Firstly, a two-stage reliability allocation model based on different allocation mechanisms is established by taking the Function-Motion-Action (FMA) decomposition tree as the allocation path. In the first stage, the allocation weights are determined based on global sensitivity analysis. In the second stage, the reliability optimization allocation model based on Copula function is established. Then, with reliability as the center, an availability collaborative optimization allocation model constrained by maintainability is constructed, and the non-dominated sorting genetic algorithm II (NSGA-II) algorithm is used to solve the model. Finally, a CNC gear milling machine is taken as an example to verify the rationality and effectiveness of the method on product availability requirements under collaborative allocation.

Details DOI

IJCAI Conference 2024 Conference Paper

SemanticMask: A Contrastive View Design for Anomaly Detection in Tabular Data

Shuting Tao
Tongtian Zhu
Hongwei Wang
Xiangming Meng

Contrastive learning based on data augmentation techniques has recently achieved substantial advancement in learning a representation well-suited for anomaly detection in image domain. However, due to the lack of spatial structure, designing effective data augmentation methods for tabular data remains challenging. Conventional techniques, such as random mask, disregard the inter-feature correlations and fail to accurately represent the data. To address this issue, we propose a novel augmentation technique called SemanticMask which leverages the semantic information from column names to generate better augmented views. SemanticMask aims to ensure that the shared information between views contains sufficient information for anomaly detection without redundancy. We analyze the relationship between shared information and anomaly detection performance and empirically demonstrate that good views for tabular anomaly detection tasks are feature-dependent. Our experiment results validate the superiority of SemanticMask over the state-of-the-art anomaly detection methods and existing augmentation techniques for tabular data. In further evaluations of the multi-class novelty detection task, SemanticMask also significantly outperforms the baseline.

PDF Details DOI

ICLR Conference 2022 Conference Paper

Chemical-Reaction-Aware Molecule Representation Learning

Hongwei Wang
Weijiang Li
Xiaomeng Jin
Kyunghyun Cho
Heng Ji 0001
Jiawei Han 0001
Martin D. Burke

Molecule representation learning (MRL) methods aim to embed molecules into a real vector space. However, existing SMILES-based (Simplified Molecular-Input Line-Entry System) or GNN-based (Graph Neural Networks) MRL methods either take SMILES strings as input that have difficulty in encoding molecule structure information, or over-emphasize the importance of GNN architectures but neglect their generalization ability. Here we propose using chemical reactions to assist learning molecule representation. The key idea of our approach is to preserve the equivalence of molecules with respect to chemical reactions in the embedding space, i.e., forcing the sum of reactant embeddings and the sum of product embeddings to be equal for each chemical equation. This constraint is proven effective to 1) keep the embedding space well-organized and 2) improve the generalization ability of molecule embeddings. Moreover, our model can use any GNN as the molecule encoder and is thus agnostic to GNN architectures. Experimental results demonstrate that our method achieves state-of-the-art performance in a variety of downstream tasks, e.g., reaction product prediction, molecule property prediction, reaction classification, and graph-edit-distance prediction. The code is available at https://github.com/hwwang55/MolR.

Details

NeurIPS Conference 2020 Conference Paper

Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

Pan Li
Yanbang Wang
Hongwei Wang
Jure Leskovec

Learning representations of sets of nodes in a graph is crucial for applications ranging from node-role discovery to link prediction and molecule classification. Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, expressive power of GNNs is limited by the 1-Weisfeiler-Lehman (WL) test and thus GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order-WL tests, only focus on representing entire graphs and they are computationally inefficient as they cannot utilize sparsity of the underlying graph. Here we propose and mathematically analyze a general class of structure-related features, termed Distance Encoding (DE). DE assists GNNs in representing any set of nodes, while providing strictly more expressive power than the 1-WL test. DE captures the distance between the node set whose representation is to be learned and each node in the graph. To capture the distance DE can apply various graph-distance measures such as shortest path distance or generalized PageRank scores. We propose two ways for GNNs to use DEs (1) as extra node features, and (2) as controllers of message aggregation in GNNs. Both approaches can utilize the sparse structure of the underlying graph, which leads to computational efficiency and scalability. We also prove that DE can distinguish node sets embedded in almost all regular graphs where traditional GNNs always fail. We evaluate DE on three tasks over six real networks: structural role prediction, link prediction, and triangle prediction. Results show that our models outperform GNNs without DE by up-to 15\% in accuracy and AUROC. Furthermore, our models also significantly outperform other state-of-the-art methods especially designed for the above tasks.

PDF Details

AAAI Conference 2019 Conference Paper

Modeling Local Dependence in Natural Language with Multi-Channel Recurrent Neural Networks

Chang Xu
Weiran Huang
Hongwei Wang
Gang Wang
Tie-Yan Liu

Recurrent Neural Networks (RNNs) have been widely used in processing natural language tasks and achieve huge success. Traditional RNNs usually treat each token in a sentence uniformly and equally. However, this may miss the rich semantic structure information of a sentence, which is useful for understanding natural languages. Since semantic structures such as word dependence patterns are not parameterized, it is a challenge to capture and leverage structure information. In this paper, we propose an improved variant of RNN, Multi-Channel RNN (MC-RNN), to dynamically capture and leverage local semantic structure information. Concretely, MC-RNN contains multiple channels, each of which represents a local dependence pattern at a time. An attention mechanism is introduced to combine these patterns at each step, according to the semantic information. Then we parameterize structure information by adaptively selecting the most appropriate connection structures among channels. In this way, diverse local structures and dependence patterns in sentences can be well captured by MC-RNN. To verify the effectiveness of MC-RNN, we conduct extensive experiments on typical natural language processing tasks, including neural machine translation, abstractive summarization, and language modeling. Experimental results on these tasks all show significant improvements of MC-RNN over current top systems.

PDF Details

AAAI Conference 2018 Conference Paper

Deep Representation-Decoupling Neural Networks for Monaural Music Mixture Separation

Zhuo Li
Hongwei Wang
Miao Zhao
Wenjie Li
Minyi Guo

Monaural source separation (MSS) aims to extract and reconstruct different sources from a single-channel mixture, which could facilitate a variety of applications such as chord recognition, pitch estimation and automatic transcription. In this paper, we study the problem of separating vocals and instruments from monaural music mixture. Existing works for monaural source separation either utilize linear and shallow models (e. g. , non-negative matrix factorization), or do not explicitly address the coupling and tangling of multiple sources in original input signals, hence they do not perform satisfactorily in real-world scenarios. To overcome the above limitations, we propose a novel end-to-end framework for monaural music mixture separation called Deep Representation- Decoupling Neural Networks (DRDNN). DRDNN takes advantages of both traditional signal processing methods and popular deep learning models. For each input of music mixture, DRDNN converts it to a two-dimensional timefrequency spectrogram using short-time Fourier transform (STFT), followed by stacked convolutional neural networks (CNN) layers and long-short term memory (LSTM) layers to extract more condensed features. Afterwards, DRDNN utilizes a decoupling component, which consists of a group of multi-layer perceptrons (MLP), to decouple the features further into different separated sources. The design of decoupling component in DRDNN produces puriﬁed single-source signals for subsequent full-size restoration, and can signiﬁcantly improve the performance of ﬁnal separation. Through extensive experiments on real-world dataset, we prove that DRDNN outperforms state-of-the-art baselines in the task of monaural music mixture separation and reconstruction.

PDF Details

AAAI Conference 2018 Conference Paper

GraphGAN: Graph Representation Learning With Generative Adversarial Nets

Hongwei Wang
Jia Wang
Jialin Wang
Miao Zhao
Weinan Zhang
Fuzheng Zhang
Xing Xie
Minyi Guo

The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space. Existing graph representation learning methods can be classiﬁed into two categories: generative models that learn the underlying connectivity distribution in the graph, and discriminative models that predict the probability of edge existence between a pair of vertices. In this paper, we propose Graph- GAN, an innovative graph representation learning framework unifying above two classes of methods, in which the generative model and discriminative model play a game-theoretical minimax game. Speciﬁcally, for a given vertex, the generative model tries to ﬁt its underlying true connectivity distribution over all other vertices and produces “fake” samples to fool the discriminative model, while the discriminative model tries to detect whether the sampled vertex is from ground truth or generated by the generative model. With the competition between these two models, both of them can alternately and iteratively boost their performance. Moreover, when considering the implementation of generative model, we propose a novel graph softmax to overcome the limitations of traditional softmax function, which can be proven satisfying desirable properties of normalization, graph structure awareness, and computational efﬁciency. Through extensive experiments on real-world datasets, we demonstrate that Graph- GAN achieves substantial gains in a variety of applications, including link prediction, node classiﬁcation, and recommendation, over state-of-the-art baselines.

PDF Details

ICRA Conference 2009 Conference Paper

Robust velocity sliding mode control of mobile wheeled inverted pendulum systems

Jian Huang 0001
Hongwei Wang
Takayuki Matsuno
Toshio Fukuda
Kosuke Sekiyama

There has been an increasing interest in a kind of underactuated mechanical systems, mobile wheeled inverted pendulum (MWIP) models, which are widely used in the field of autonomous robotics and intelligent vehicles. Robust velocity tracking problem of MWIP systems is investigated in this study. In the velocity control problem, model uncertainties accompany uncertain equilibriums, which make the controller design become more difficult. A sliding mode control (SMC) method based on a novel sliding surface is proposed for the systems, which are capable of handling both parameter uncertainties and external disturbances. By assuming the specially designed sliding surface, the proposed SMC controller is capable of eliminating the steady velocity tracking error. The asymptotical stability of the closed-loop system is achieved through selecting sliding surface parameters in terms of some rules. The effectiveness of the proposed methods is finally confirmed by numerical simulations.

Details