Author name cluster

Dexian 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.

4 papers

1 author row

EAAI Journal 2026 Journal Article

A trend-aware reinforcement learning approach for adaptive motion planning of robotic manipulators in dynamic environments

Dexian Wang
Peng Zhang
Pengfei Ding
Junliang Wang
Jie Zhang

In engineering applications such as service robotics, human–robot collaboration, and industrial automation, robotic manipulators frequently operate in highly dynamic and partially observable environments. The presence of dynamic obstacles, unpredictable human behaviors, and rapidly changing task demands intensify the inherent conflicts between positioning accuracy, obstacle avoidance, and operational safety. At the same time, these systems must rely on incomplete and noisy sensor data to perceive and interpret their surroundings. Such dynamic scenarios significantly increase system complexity and require adaptive, real-time control strategies capable of making reliable decisions under uncertainty. To address these challenges, this paper proposes Trend Learning – Adaptive Reward Shaping – Temporal Difference Knowledge Distillation of Q-value(Action-Value Function), collectively referred to as TL-ARS-TDKDQ, a reinforcement learning framework designed to enable robotic manipulators to adaptively perform precise positioning and dynamic obstacle avoidance in dynamic environments. Trend Learning(TL) alleviates environmental uncertainty by extracting temporal dependencies from sequential data of the manipulator. Adaptive Reward Shaping(ARS) dynamically balances positioning accuracy and obstacle avoidance for the robotic manipulator while progressively increasing task difficulty via curriculum learning. To enhance stability during reward fluctuations caused by ARS, Temporal Difference Knowledge Distillation Q-value (TDKDQ) employs a dynamic teacher network and Temporal Difference(TD) error-based balancing, ensuring stable policy convergence in non-stationary scenarios involving robotic manipulator control. Experiments with a KUKA arm in CoppeliaSim demonstrate that TL-ARS-TDKDQ significantly improves convergence speed, control stability, and task success when integrated into mainstream continuous control reinforcement learning algorithms.

Details DOI

AAAI Conference 2026 Conference Paper

Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers

Liang Lin
Miao Yu
Kaiwen Luo
Yibo Zhang
Lilan Peng
Dexian Wang
Xuehai Tang
Yuanhe Zhang

As Audio Large Language Models (ALLMs) emerge as powerful tools for speech processing, their safety implications demand urgent attention. While considerable research has explored textual and vision safety, audio’s distinct characteristics present significant challenges. This paper first investigates: Is ALLM vulnerable to backdoor attacks exploiting acoustic triggers? In response to this issue, we introduce Hidden in the Noise (HIN), a novel backdoor attack framework designed to exploit subtle, audio-specific features. HIN applies acoustic modifications to raw audio waveforms, such as alterations to temporal dynamics and strategic injection of spectrally tailored noise. These changes introduce consistent patterns that an ALLM’s acoustic feature encoder captures, embedding robust triggers within the audio stream. To evaluate ALLM robustness against audio-feature-based triggers, we develop the AudioSafe benchmark, assessing nine distinct risk types. Extensive experiments on AudioSafe and three established safety datasets reveal critical vulnerabilities in existing ALLMs: (I) audio features like environment noise and speech rate variations achieve over 90% average attack success rate, (II) ALLMs exhibit significant sensitivity differences across acoustic features, particularly showing minimal response to volume as a trigger, and (III) poisoned sample inclusion causes only marginal loss curve fluctuations, highlighting the attack’s stealth.

PDF Details DOI

EAAI Journal 2025 Journal Article

Symmetric non-negative matrix factorization-based deep representation algorithm for multi-view clustering

Ping Deng
Xinying Zhou
Ji Xu
Wei Huang
Jie Wang
Dexian Wang
Tianrui Li

Symmetric Non-negative Matrix Factorization (SNMF) shows significant advantages in clustering task due to its unique mathematical properties. However, it still has several key limitations: (1) the single optimization scheme of traditional multiplicative update rule limits the flexibility of the algorithm; (2) linear factorization leads to insufficient representation ability for complex nonlinear features; (3) lack of learning rate guidance mechanism. These factors together constrain the algorithm representation learning ability in complex data. To address these issues, this paper proposes a SNMF-based Deep Representation algorithm for Multi-view Clustering (SNDRMvC). First, the matrix elements are decoupled, and the stochastic gradient descent as well as nonlinear activation function are used to implement non-negative matrix update. Then, based on the corresponding gradients of the elements and nonlinear function, the neural network learning mechanism is introduced into the SNMF update rule to construct a novel framework SNMF-based deep representation network for optimizing SNMF. This network aims to update the elements in the low-dimensional matrix of each view and fuse the low-dimensional matrices of multiple views to derive a consensus matrix. Finally, extensive experiments conducted on several public datasets demonstrate that the proposed algorithm exhibits notable advantages in clustering performance. We provide the code at: https: //github. com/Code706/SNDRMvC.

Details DOI

TIST Journal 2024 Journal Article

DNSRF: Deep Network-based Semi-NMF Representation Framework

Dexian Wang
Tianrui Li
Ping Deng
Zhipeng Luo
Pengfei Zhang
Keyu Liu
Wei Huang

Representation learning is an important topic in machine learning, pattern recognition, and data mining research. Among many representation learning approaches, semi-nonnegative matrix factorization (SNMF) is a frequently-used one. However, a typical problem of SNMF is that usually there is no learning rate guidance during the optimization process, which often leads to a poor representation ability. To overcome this limitation, we propose a very general representation learning framework (DNSRF) that is based on a deep neural net. Essentially, the parameters of the deep net used to construct the DNSRF algorithms are obtained by matrix element update. In combination with different activation functions, DNSRF can be implemented in various ways. In our experiments, we tested nine instances of our DNSRF framework on six benchmark datasets. In comparison with other state-of-the-art methods, the results demonstrate the superior performance of our framework, which is thus shown to have a great representation ability.

Details DOI