Direct Conditional Transition Sampling for Diffusion Inverse Problems
本文提出直接条件转换采样法解决扩散逆问题，通过估计测量条件下的清洁均值并直接将高斯源噪声传输到下一个噪声状态，实现快速准确的重建。
0 citationsRead paper
Selected work
Representative Papers
Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values
研究通过构建多语言对比探针数据集C-Voices和提出无需微调的价值向量引导方法，解决大语言模型在不同语言中对中文社会价值观一致性的挑战。
0 citationsRead paper
Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution
This work addresses the challenges of high-resolution remote sensing image reconstruction, which is constrained by sensor costs and acquisition conditions, as well as the inefficiency and limited scalability of existing generative super-resolution methods. To overcome these limitations, the authors propose FlowGS, a novel framework that introduces 2D Gaussian Splatting into remote sensing image super-resolution for the first time. By constructing a continuous feature field, FlowGS enables efficient arbitrary-scale reconstruction. Additionally, a flow matching mechanism with shortcut consistency is designed to model the distribution of high-frequency details between low- and high-resolution images, thereby reducing generation complexity. The method achieves superior perceptual quality on both fixed- and continuous-scale super-resolution tasks while significantly improving inference efficiency.
0 citationsRead paper
MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models
High-resolution land cover mapping is hindered by the prohibitive cost of pixel-level annotations. This work proposes MapSR, a novel framework that introduces prompt-based mechanisms to map super-resolution for the first time. By leveraging a frozen vision foundation model, MapSR extracts class-specific prompts from low-resolution labels and combines linear probing, cosine similarity matching, and graph propagation to enable training-free inference without high-resolution supervision. The approach decouples supervisory signals from model training, reducing trainable parameters by four orders of magnitude and shrinking training time from hours to minutes. Evaluated on the Chesapeake Bay dataset, MapSR achieves a mean Intersection-over-Union (mIoU) of 59.64%, demonstrating substantial gains in efficiency and scalability while maintaining competitive accuracy.
0 citationsRead paper
One-Step Face Restoration via Shortcut-Enhanced Coupling Flow
This work addresses the limitations of existing flow-matching-based face restoration methods, which initialize from Gaussian noise and neglect the intrinsic dependency between low-quality (LQ) and high-quality (HQ) images, leading to curved trajectories, path crossings, and the need for multi-step sampling. To overcome these issues, the authors propose a data-dependent coupling mechanism that explicitly models the LQ–HQ relationship through conditional mean estimation and introduces a shortcut path constraint to supervise the average velocity field at any time step. This approach achieves high-fidelity single-step face restoration within the flow-matching framework for the first time, significantly improving restoration quality while maintaining inference speed comparable to conventional non-diffusion methods, thereby establishing state-of-the-art performance among single-step techniques.
0 citationsRead paper
Recent publications
Latest Papers
Direct Conditional Transition Sampling for Diffusion Inverse Problems
本文提出直接条件转换采样法解决扩散逆问题，通过估计测量条件下的清洁均值并直接将高斯源噪声传输到下一个噪声状态，实现快速准确的重建。
0 citationsRead paper
Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values
研究通过构建多语言对比探针数据集C-Voices和提出无需微调的价值向量引导方法，解决大语言模型在不同语言中对中文社会价值观一致性的挑战。
0 citationsRead paper
Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution
This work addresses the challenges of high-resolution remote sensing image reconstruction, which is constrained by sensor costs and acquisition conditions, as well as the inefficiency and limited scalability of existing generative super-resolution methods. To overcome these limitations, the authors propose FlowGS, a novel framework that introduces 2D Gaussian Splatting into remote sensing image super-resolution for the first time. By constructing a continuous feature field, FlowGS enables efficient arbitrary-scale reconstruction. Additionally, a flow matching mechanism with shortcut consistency is designed to model the distribution of high-frequency details between low- and high-resolution images, thereby reducing generation complexity. The method achieves superior perceptual quality on both fixed- and continuous-scale super-resolution tasks while significantly improving inference efficiency.
0 citationsRead paper
MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models
High-resolution land cover mapping is hindered by the prohibitive cost of pixel-level annotations. This work proposes MapSR, a novel framework that introduces prompt-based mechanisms to map super-resolution for the first time. By leveraging a frozen vision foundation model, MapSR extracts class-specific prompts from low-resolution labels and combines linear probing, cosine similarity matching, and graph propagation to enable training-free inference without high-resolution supervision. The approach decouples supervisory signals from model training, reducing trainable parameters by four orders of magnitude and shrinking training time from hours to minutes. Evaluated on the Chesapeake Bay dataset, MapSR achieves a mean Intersection-over-Union (mIoU) of 59.64%, demonstrating substantial gains in efficiency and scalability while maintaining competitive accuracy.
0 citationsRead paper
One-Step Face Restoration via Shortcut-Enhanced Coupling Flow
This work addresses the limitations of existing flow-matching-based face restoration methods, which initialize from Gaussian noise and neglect the intrinsic dependency between low-quality (LQ) and high-quality (HQ) images, leading to curved trajectories, path crossings, and the need for multi-step sampling. To overcome these issues, the authors propose a data-dependent coupling mechanism that explicitly models the LQ–HQ relationship through conditional mean estimation and introduces a shortcut path constraint to supervise the average velocity field at any time step. This approach achieves high-fidelity single-step face restoration within the flow-matching framework for the first time, significantly improving restoration quality while maintaining inference speed comparable to conventional non-diffusion methods, thereby establishing state-of-the-art performance among single-step techniques.
0 citationsRead paper