Selected work

Representative Papers

DSVM-UNet : Enhancing VM-UNet with Dual Self-distillation for Medical Image Segmentation

Jan 27, 2026

This work addresses the challenge of balancing model performance and computational efficiency in medical image segmentation by proposing a structure-preserving dual self-distillation mechanism built upon the VM-UNet architecture. The method enhances semantic awareness through alignment of global and local feature representations, leveraging Vision Mamba’s strength in efficiently modeling long-range dependencies. Without altering the underlying network structure, the approach achieves state-of-the-art performance on the ISIC2017, ISIC2018, and Synapse datasets while maintaining high computational efficiency, thereby effectively reconciling accuracy and resource consumption.

0 citationsRead paper

Automated Heuristic Design for Unit Commitment Using Large Language Models

Jun 14, 2025

Unit commitment (UC) in power systems has long suffered from heuristic design relying heavily on manual effort, with limited generalizability and robustness. This paper pioneers the integration of large language models (LLMs) into UC heuristic synthesis, proposing an automated strategy evolution framework grounded in function-space search (FunSearch). The framework leverages LLM-driven program synthesis to generate candidate heuristics, which are iteratively refined via a Lagrangian relaxation–based optimization loop coupled with a verifiable simulation-based evaluator. This closed-loop evolutionary process ensures interpretability, full automation, and strong robustness. Evaluated on a standard 10-unit test system, the method significantly reduces sampling and evaluation time compared to genetic algorithms while lowering total system operating cost. These results demonstrate both computational efficiency and practical engineering viability.

0 citationsRead paper

Recent publications

Latest Papers

DSVM-UNet : Enhancing VM-UNet with Dual Self-distillation for Medical Image Segmentation

Jan 27, 2026

This work addresses the challenge of balancing model performance and computational efficiency in medical image segmentation by proposing a structure-preserving dual self-distillation mechanism built upon the VM-UNet architecture. The method enhances semantic awareness through alignment of global and local feature representations, leveraging Vision Mamba’s strength in efficiently modeling long-range dependencies. Without altering the underlying network structure, the approach achieves state-of-the-art performance on the ISIC2017, ISIC2018, and Synapse datasets while maintaining high computational efficiency, thereby effectively reconciling accuracy and resource consumption.

0 citationsRead paper

Automated Heuristic Design for Unit Commitment Using Large Language Models

Jun 14, 2025

Unit commitment (UC) in power systems has long suffered from heuristic design relying heavily on manual effort, with limited generalizability and robustness. This paper pioneers the integration of large language models (LLMs) into UC heuristic synthesis, proposing an automated strategy evolution framework grounded in function-space search (FunSearch). The framework leverages LLM-driven program synthesis to generate candidate heuristics, which are iteratively refined via a Lagrangian relaxation–based optimization loop coupled with a verifiable simulation-based evaluator. This closed-loop evolutionary process ensures interpretability, full automation, and strong robustness. Evaluated on a standard 10-unit test system, the method significantly reduces sampling and evaluation time compared to genetic algorithms while lowering total system operating cost. These results demonstrate both computational efficiency and practical engineering viability.

0 citationsRead paper