Institution profile

Zhejiang University of Finance and Economics

Academic institutionasia · cn
Official website
Research library9linked papers
Opportunities0open roles
Selected work

Representative Papers

Manifold Fitting by Successive Tangent-Space Projection

Oct 07, 2026

This study addresses the inherent trade-off between fitting accuracy and geometric coverage when recovering latent manifold structures from noisy observations. To this end, we propose a continuous tangent space projection algorithm that achieves high-precision manifold fitting by iteratively suppressing normal noise while preserving tangential variations. Theoretically, we define the fixed-point set of local neighborhoods, prove that its geometric localization order is O(σ²), and introduce a multiscale extension to eliminate curvature bias. Numerical experiments demonstrate that the proposed method significantly mitigates curvature shrinkage under high-noise conditions, outperforming existing approaches in both fitting accuracy and geometric coverage.

0 citationsRead paper

MorphoBranch: A Fine-Structure-Preserving Workbench for Morphometric Analysis of Branched Cellular Structures

Sep 30, 2026

This study addresses the skeletonization measurement biases caused by the fragility and erroneous merging of thin fluorescently labeled cellular branches. We propose a graph-based workflow integrating a deterministic morphology engine with LLM-assisted optimization, achieving high-fidelity structural reconstruction through multi-scale evidence extraction, hysteresis segmentation, constrained skeleton refinement, and graph morphology. Furthermore, this work pioneers an auditable natural language interaction paradigm grounded in computational determinism. Evaluated across three datasets, the proposed method achieves state-of-the-art Skeleton F1 and clDice scores alongside minimal length errors, while attaining a 94.0% success rate on natural language tasks. Ultimately, this framework effectively balances fine-structure preservation with flexible human-machine interaction.

0 citationsRead paper

CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting

Jan 28, 2026

This work addresses the tension in multivariate time series forecasting between modeling inter-channel dependencies and preserving model flexibility: channel-dependent approaches are prone to overfitting due to sensitivity to channel ordering, while channel-independent models neglect inter-channel relationships. To resolve this, we propose CPiRi, a novel framework that introduces permutation invariance over channels into multivariate time series modeling for the first time. CPiRi employs a spatiotemporal decoupling architecture, a frozen pre-trained temporal encoder, a lightweight spatial relation module, and a channel-shuffling training strategy to adaptively infer channel relationships from data. Grounded in permutation equivariance theory, our approach ensures strong inductive generalization to unseen channel configurations. Experiments demonstrate that CPiRi achieves state-of-the-art performance across multiple benchmarks, exhibits robustness to channel order perturbations, generalizes to full-channel settings using only half the channels during training, and maintains efficiency at scale.

0 citationsRead paper
Recent publications

Latest Papers

Manifold Fitting by Successive Tangent-Space Projection

Oct 07, 2026

This study addresses the inherent trade-off between fitting accuracy and geometric coverage when recovering latent manifold structures from noisy observations. To this end, we propose a continuous tangent space projection algorithm that achieves high-precision manifold fitting by iteratively suppressing normal noise while preserving tangential variations. Theoretically, we define the fixed-point set of local neighborhoods, prove that its geometric localization order is O(σ²), and introduce a multiscale extension to eliminate curvature bias. Numerical experiments demonstrate that the proposed method significantly mitigates curvature shrinkage under high-noise conditions, outperforming existing approaches in both fitting accuracy and geometric coverage.

0 citationsRead paper

MorphoBranch: A Fine-Structure-Preserving Workbench for Morphometric Analysis of Branched Cellular Structures

Sep 30, 2026

This study addresses the skeletonization measurement biases caused by the fragility and erroneous merging of thin fluorescently labeled cellular branches. We propose a graph-based workflow integrating a deterministic morphology engine with LLM-assisted optimization, achieving high-fidelity structural reconstruction through multi-scale evidence extraction, hysteresis segmentation, constrained skeleton refinement, and graph morphology. Furthermore, this work pioneers an auditable natural language interaction paradigm grounded in computational determinism. Evaluated across three datasets, the proposed method achieves state-of-the-art Skeleton F1 and clDice scores alongside minimal length errors, while attaining a 94.0% success rate on natural language tasks. Ultimately, this framework effectively balances fine-structure preservation with flexible human-machine interaction.

0 citationsRead paper

CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting

Jan 28, 2026

This work addresses the tension in multivariate time series forecasting between modeling inter-channel dependencies and preserving model flexibility: channel-dependent approaches are prone to overfitting due to sensitivity to channel ordering, while channel-independent models neglect inter-channel relationships. To resolve this, we propose CPiRi, a novel framework that introduces permutation invariance over channels into multivariate time series modeling for the first time. CPiRi employs a spatiotemporal decoupling architecture, a frozen pre-trained temporal encoder, a lightweight spatial relation module, and a channel-shuffling training strategy to adaptively infer channel relationships from data. Grounded in permutation equivariance theory, our approach ensures strong inductive generalization to unseen channel configurations. Experiments demonstrate that CPiRi achieves state-of-the-art performance across multiple benchmarks, exhibits robustness to channel order perturbations, generalizes to full-channel settings using only half the channels during training, and maintains efficiency at scale.

0 citationsRead paper