Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning
本文针对多模态情境学习中模仿表面演示的问题，提出结合对比示例建模与自我优化能力的新框架，通过对比次优与更优响应明确推理路径，并引入响应条件检索机制和轻量级对齐控制器以提高模型性能。
0 citationsRead paper
Selected work
Representative Papers
Testing Interchangeability in LLM Agent Teams
研究通过在多智能体系统中交换角色匹配的代理来测试代理间的互换性，发现虽然任务得分影响小，但沟通成本显著增加。
0 citationsRead paper
Verification of $K$- and Infinite-Step Strong/Weak Anonymity Using Concurrent Compositions
本文通过并发组合技术，定义并验证了部分观测离散事件系统中四种类型的K步和无限步强/弱匿名性，提供了验证条件及复杂度分析。
0 citationsRead paper
IPv2: An Improved Image Purification Strategy for Real-World Ultra-Low-Dose Lung CT Denoising
This work addresses the limitations of existing ultra-low-dose lung CT denoising methods, which struggle to effectively suppress noise in both background regions and pulmonary parenchyma and lack a principled strategy for constructing evaluation labels. To overcome these challenges, the authors propose a novel image purification framework employing a three-stage strategy—background removal, controllable noise injection, and denoising—that enhances the model’s joint denoising capability for both regions during training and enables more realistic label construction during testing. This approach represents the first systematic refinement of the image purification pipeline, is compatible with various mainstream denoising architectures, and demonstrates significant improvements in background suppression and lung structure recovery on real patient CT scans acquired at only 2% of standard radiation dose.
0 citationsRead paper
A Denoising Framework for Real-World Ultra-Low Dose Lung CT Images Based on an Image Purification Strategy
Ultra-low-dose CT (uLDCT) reduces radiation exposure but introduces severe noise, artifacts, and structural misalignment with normal-dose CT (NDCT), degrading the performance of existing denoising methods. To address this, we propose an image purification strategy that, for the first time, generates structurally aligned uLDCT–NDCT paired samples from real clinical data. Building upon this, we design a Frequency-domain Flow Matching (FFM) model that explicitly models the noise distribution in the frequency domain while enforcing anatomical structure consistency via frequency-aware constraints. The resulting dataset and FFM framework significantly improve the denoising performance of multiple state-of-the-art models on real-world uLDCT scans, achieving superior structural fidelity—setting a new standard in clinical uLDCT denoising. Both the dataset and source code are publicly released.
0 citationsRead paper
Recent publications
Latest Papers
Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning
本文针对多模态情境学习中模仿表面演示的问题，提出结合对比示例建模与自我优化能力的新框架，通过对比次优与更优响应明确推理路径，并引入响应条件检索机制和轻量级对齐控制器以提高模型性能。
0 citationsRead paper
Testing Interchangeability in LLM Agent Teams
研究通过在多智能体系统中交换角色匹配的代理来测试代理间的互换性，发现虽然任务得分影响小，但沟通成本显著增加。
0 citationsRead paper
Verification of $K$- and Infinite-Step Strong/Weak Anonymity Using Concurrent Compositions
本文通过并发组合技术，定义并验证了部分观测离散事件系统中四种类型的K步和无限步强/弱匿名性，提供了验证条件及复杂度分析。
0 citationsRead paper
IPv2: An Improved Image Purification Strategy for Real-World Ultra-Low-Dose Lung CT Denoising
This work addresses the limitations of existing ultra-low-dose lung CT denoising methods, which struggle to effectively suppress noise in both background regions and pulmonary parenchyma and lack a principled strategy for constructing evaluation labels. To overcome these challenges, the authors propose a novel image purification framework employing a three-stage strategy—background removal, controllable noise injection, and denoising—that enhances the model’s joint denoising capability for both regions during training and enables more realistic label construction during testing. This approach represents the first systematic refinement of the image purification pipeline, is compatible with various mainstream denoising architectures, and demonstrates significant improvements in background suppression and lung structure recovery on real patient CT scans acquired at only 2% of standard radiation dose.
0 citationsRead paper
A Denoising Framework for Real-World Ultra-Low Dose Lung CT Images Based on an Image Purification Strategy
Ultra-low-dose CT (uLDCT) reduces radiation exposure but introduces severe noise, artifacts, and structural misalignment with normal-dose CT (NDCT), degrading the performance of existing denoising methods. To address this, we propose an image purification strategy that, for the first time, generates structurally aligned uLDCT–NDCT paired samples from real clinical data. Building upon this, we design a Frequency-domain Flow Matching (FFM) model that explicitly models the noise distribution in the frequency domain while enforcing anatomical structure consistency via frequency-aware constraints. The resulting dataset and FFM framework significantly improve the denoising performance of multiple state-of-the-art models on real-world uLDCT scans, achieving superior structural fidelity—setting a new standard in clinical uLDCT denoising. Both the dataset and source code are publicly released.
0 citationsRead paper