Institution profile

Guangdong University of Technology

Academic institutionasia · cn
Official website
Research library353linked papers
Opportunities0open roles
Selected work

Representative Papers

Robust Categorical Data Clustering Guided by Multi-Granular Competitive Learning

Jul 23, 2024IEEE International Conference on Distributed Computing Systems

Categorical data pose significant clustering challenges due to the absence of a well-defined distance metric, particularly when they exhibit multi-granular nested cluster structures. To address this, this work proposes a Multi-Granular Competitive Penalty Learning (MGCPL) mechanism that adaptively refines cluster structures in stages, integrated with a Cluster Aggregation and Metric Embedding (CAME) strategy based on learned distributions to enable robust clustering in the embedding space. This approach is the first to incorporate multi-granular competitive learning into categorical data modeling, offering both automatic granularity discovery and linear time complexity, thereby supporting scalability to large-scale datasets and compatibility with distributed pre-partitioning. Extensive experiments on multiple real-world datasets demonstrate its significant superiority over existing methods.

16 citationsRead paper

On the Identification of Temporally Causal Representation with Instantaneous Dependence

May 24, 2024arXiv.org

Existing time-series causal representation learning methods typically neglect instantaneous causal relationships, while emerging approaches accommodating such dependencies rely on latent-variable interventions or grouped observational data—conditions rarely satisfied in practice. To address this, we propose IDOL, the first framework enabling unique identification of latent causal processes with instantaneous dependencies without requiring interventions or data grouping. Theoretically, IDOL introduces sparse influence constraints—unifying delayed and instantaneous causal modeling—and temporal context variability, establishing strong identifiability guarantees. Methodologically, it integrates temporal variational inference with gradient-driven sparse regularization to jointly estimate latent variables and the causal graph. Experiments demonstrate that IDOL achieves exact structural recovery on synthetic benchmarks and significantly improves long-horizon prediction accuracy and causal interpretability across multiple human motion forecasting datasets.

11 citationsRead paper

Non-cooperative Stochastic Target Encirclement by Anti-synchronization Control via Range-only Measurement

May 29, 2023IEEE International Conference on Robotics and Automation

This paper addresses the distributed cooperative pursuit of a high-speed, non-cooperative, randomly maneuvering target by multiple UAVs under GPS-denied and ground-station-free conditions, relying solely on unimodal range-only measurements. To overcome challenges posed by the target’s instantaneous acceleration capability, limited sensing range, and absence of global positioning, we propose a Distributed Anti-Synchronous Controller (DASC). To our knowledge, DASC is the first solution enabling stable围捕 of non-cooperative evading targets using purely range-based measurements. By integrating range-only relative pose estimation with Lyapunov-based stability analysis, we rigorously guarantee joint convergence of the estimator and controller. Experimental validation on real UAV platforms and MATLAB simulations demonstrates a 32% reduction in pursuit time, a 41% decrease in tracking error, and significantly enhanced robustness against disturbances and measurement noise. Video demonstration: https://youtu.be/EDVLvP-bk8M.

5 citationsRead paper

Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection

Feb 01, 2026IEEE Transactions on Emerging Topics in Computational Intelligence

This work addresses the challenge of detecting small concept drifts in data streams that are often obscured by dominant, larger concepts—a phenomenon known as the "masking effect" caused by concept imbalance. To overcome this limitation, the authors propose ICD3, a novel method that employs multi-granularity distribution search to identify concepts of varying scales and constructs an individual one-class classifier (OCC) for each concept to monitor its drift independently, thereby preventing larger concepts from dominating the detection process. ICD3 is the first approach to enable unbiased and interpretable detection of imbalanced concept drifts, accurately pinpointing the specific drifting concepts while remaining robust to variations in inter-concept imbalance ratios. Extensive experiments on multiple benchmark datasets demonstrate that ICD3 consistently outperforms state-of-the-art methods in both detection accuracy and interpretability.

3 citationsRead paper

Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation

Feb 18, 2026arXiv.org

This work addresses the scarcity of real-world data in robotic manipulation by introducing PhysGen, a framework that leverages pretrained video generation models as implicit physics simulators. PhysGen models the dynamic interaction between environments and actions through autoregressive video generation, featuring a novel multimodal continuous physical token representation that unifies the semantic spaces of visual observations and continuous actions. This enables knowledge transfer from purely vision-based pretraining to robotic control without requiring action-labeled pretraining data. By integrating causal masking, inverse kinematics, and Lookahead multi-token prediction, PhysGen outperforms OpenVLA and WorldVLA by 13.8% and 8.8% on the Libero and ManiSkill benchmarks, respectively, and matches the performance of large models like π₀ in real-world settings—particularly excelling in challenging tasks such as grasping transparent objects.

2 citationsRead paper
Recent publications

Latest Papers