Progressive Pseudo-Label Optimization for Point-Supervised Change Detection
该研究针对点监督变化检测中伪标签不完整和噪声问题，提出两阶段框架结合SAM2先验逐步优化伪标签，提高边界质量和结构一致性。
0 citationsRead paper
Selected work
Representative Papers
Quantization Effects on Bangla Language Understanding in Large Language Models: A Systematic Evaluation
研究通过对比三种模型家族在不同量化格式下的表现，系统评估了量化对孟加拉语理解的影响，发现架构和量化方法的选择比位宽更重要。
0 citationsRead paper
Gaussian process learning with flow map refinement for parameter estimation in dynamical systems
本文针对动力系统参数估计问题，提出了一种结合高斯过程学习与流映射精炼的两阶段方法，以提高在稀疏和噪声观测下的参数估计精度。
0 citationsRead paper
FIRM: Fine-Grained Intra-Token Representation of Masks for Remote Sensing Reasoning Segmentation
This study addresses the issues of coarse boundaries and instance adhesion in remote sensing semantic segmentation caused by multi-target mixing within visual tokens. To overcome these limitations, we propose FIRM, a novel method that innovatively introduces intra-token sub-unit mask representations and a lightweight continuous rendering mechanism. By transcending single-label constraints through sub-unit prediction, lookup table transformation, and soft structural field marginalization, FIRM achieves fine-grained segmentation. Extensive experiments demonstrate state-of-the-art performance across five benchmarks. Notably, on the LASER dataset, FIRM attains GIoU/CIoU scores of 70.5/80.5 and improves the EarthReason metric by 3.0 points, significantly enhancing segmentation accuracy in complex scenes.
0 citationsRead paper
Bounds and constructions for constant/low-power error-correcting cooling codes
This study addresses the challenging problem of designing on-chip bus codes that simultaneously constrain peak temperature, average power consumption, and provide error correction capability. By integrating graph theory, probabilistic methods, and combinatorial design theory, the work systematically investigates the theoretical bounds and constructions of constant-power error-correcting cooling codes (CPECC) and low-power error-correcting cooling codes (LPECC). The main contributions include a complete resolution of an open conjecture concerning CPECC codes, the establishment of a structural equivalence between optimal CPECC and LPECC codes, the derivation of new upper bounds for both code families, and the explicit construction of multiple optimal code families that achieve these theoretical limits.
0 citationsRead paper
Recent publications
Latest Papers
Progressive Pseudo-Label Optimization for Point-Supervised Change Detection
该研究针对点监督变化检测中伪标签不完整和噪声问题，提出两阶段框架结合SAM2先验逐步优化伪标签，提高边界质量和结构一致性。
0 citationsRead paper
Quantization Effects on Bangla Language Understanding in Large Language Models: A Systematic Evaluation
研究通过对比三种模型家族在不同量化格式下的表现，系统评估了量化对孟加拉语理解的影响，发现架构和量化方法的选择比位宽更重要。
0 citationsRead paper
Gaussian process learning with flow map refinement for parameter estimation in dynamical systems
本文针对动力系统参数估计问题，提出了一种结合高斯过程学习与流映射精炼的两阶段方法，以提高在稀疏和噪声观测下的参数估计精度。
0 citationsRead paper
FIRM: Fine-Grained Intra-Token Representation of Masks for Remote Sensing Reasoning Segmentation
This study addresses the issues of coarse boundaries and instance adhesion in remote sensing semantic segmentation caused by multi-target mixing within visual tokens. To overcome these limitations, we propose FIRM, a novel method that innovatively introduces intra-token sub-unit mask representations and a lightweight continuous rendering mechanism. By transcending single-label constraints through sub-unit prediction, lookup table transformation, and soft structural field marginalization, FIRM achieves fine-grained segmentation. Extensive experiments demonstrate state-of-the-art performance across five benchmarks. Notably, on the LASER dataset, FIRM attains GIoU/CIoU scores of 70.5/80.5 and improves the EarthReason metric by 3.0 points, significantly enhancing segmentation accuracy in complex scenes.
0 citationsRead paper
Bounds and constructions for constant/low-power error-correcting cooling codes
This study addresses the challenging problem of designing on-chip bus codes that simultaneously constrain peak temperature, average power consumption, and provide error correction capability. By integrating graph theory, probabilistic methods, and combinatorial design theory, the work systematically investigates the theoretical bounds and constructions of constant-power error-correcting cooling codes (CPECC) and low-power error-correcting cooling codes (LPECC). The main contributions include a complete resolution of an open conjecture concerning CPECC codes, the establishment of a structural equivalence between optimal CPECC and LPECC codes, the derivation of new upper bounds for both code families, and the explicit construction of multiple optimal code families that achieve these theoretical limits.
0 citationsRead paper