Institution profile

University of Macau

Academic institutionasia · mo
Official website
Research library727linked papers
Opportunities0open roles
Selected work

Representative Papers

A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge

Oct 18, 2023arXiv.org

Managing and retrieving high-dimensional vector data poses significant challenges, particularly as traditional databases fail to meet performance requirements and the need for tight integration with large language models (LLMs) intensifies. Method: This paper systematically surveys four major approximate nearest neighbor search (ANNS) paradigms—hashing, tree-based indexing, graph-based methods (e.g., HNSW), and quantization (PQ/SQ)—and integrates hybrid optimization strategies. Contribution/Results: It introduces, for the first time, a “Four-Dimensional Methodology” framework tailored for industrial deployment of vector databases, analyzing trade-offs among accuracy, latency, memory footprint, and scalability. The work constructs a structured knowledge graph covering 200+ ANNS algorithms and proposes a novel paradigm for deep synergy between vector databases and LLMs. Collectively, these contributions provide both theoretical foundations and practical guidelines for system selection, architectural design, and development of AI-native database systems.

62 citations3 influentialRead paper

Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering

Sep 04, 2024arXiv.org

Diffusion models face the curse of dimensionality when modeling high-dimensional image distributions, hindering effective learning of low-dimensional manifold structures underlying images. Method: We reformulate the diffusion training objective as an equivalent subspace clustering problem—establishing, for the first time, a rigorous theoretical equivalence between diffusion models and subspace clustering. Leveraging manifold geometry and the low-rank property of denoising autoencoders, we derive theoretical guarantees showing sample complexity scales linearly with intrinsic dimension. Our framework integrates low-rank Gaussian mixture modeling, score function parameterization, and diffusion loss analysis. Contribution/Results: We prove that learned subspaces admit precise semantic interpretations—corresponding to editable, concept-level image representations. Theoretically, our method ensures exact recovery of low-dimensional distributions even in low-sample regimes. Experiments on synthetic and real-world image data validate both semantic consistency of the recovered subspaces and their strong controllability for image editing.

14 citations1 influentialRead paper

An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient-Boosting and Fuzzy Rule-Based Models

Nov 01, 2024IEEE Transactions on Artificial Intelligence

Fuzzy rule models offer strong interpretability but suffer from poor scalability and susceptibility to overfitting in complex tasks and large-scale data scenarios. To address these limitations, this paper proposes a novel ensemble framework integrating gradient boosting with fuzzy rule-based base learners. We introduce a dynamic control factor that adaptively adjusts the weights of fuzzy base models in each boosting iteration, simultaneously serving as a regularizer and performance optimizer. Additionally, we design a validation-set-driven, sample-level correction mechanism to enhance generalization and ensemble diversity. Experimental results demonstrate that our approach significantly mitigates overfitting, reduces rule complexity (e.g., fewer rules and shorter antecedents), and preserves high model interpretability and maintainability. The method thus provides a practical pathway for deploying interpretable AI in complex industrial applications.

6 citationsRead paper

SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation

Aug 31, 2024IEEE International Conference on Bioinformatics and Biomedicine

To address the low segmentation accuracy of irregularly shaped and minute tumors in medical images, this paper proposes a Synergistic Multi-Attention Transformer (SMA-Transformer). The architecture innovatively integrates pixel-wise, channel-wise, and spatial-wise attention mechanisms, coupled with a feature fusion modulator to jointly model local details and global context—thereby mitigating information loss during attention transformation and feature recalibration. Its modular design incorporates residual connections to enhance gradient flow and feature reuse. Evaluated on multi-organ, liver tumor, and bladder tumor segmentation tasks, the method achieves state-of-the-art (SOTA) performance, particularly for small-target segmentation. It delivers significant improvements in key metrics: Dice coefficient and 95th-percentile Hausdorff Distance (HD95), demonstrating superior accuracy and boundary localization.

6 citationsRead paper

Multimodal Multi-Agent Empowered Legal Judgment Prediction

Jan 19, 2026

This work addresses the limitations of traditional legal judgment prediction methods, which often exhibit poor adaptability and lack standardized procedures when handling cases involving multiple charges, multimodal evidence, and complex factual scenarios. To overcome these challenges, we propose JurisMMA, a novel framework that introduces, for the first time, a multimodal multi-agent architecture to decompose the adjudication process into standardized stages, enabling the collaborative integration of heterogeneous judicial data such as textual records and video evidence. We construct JurisMM, a large-scale multimodal dataset comprising over 100,000 Chinese judicial records, and evaluate our approach on both this dataset and the LawBench benchmark. Experimental results demonstrate that JurisMMA significantly improves judgment prediction accuracy, advancing legal AI toward more systematic, modular, and process-oriented paradigms.

4 citationsRead paper
Recent publications

Latest Papers