TRACE: Two-Stage Detector-Response Estimation With Angular Cosine Expansion for Ring Artifact Correction in Photon-Counting CT
本文提出TRACE方法，通过两阶段无监督正弦图分解估计并校正光子计数CT中的探测器响应非均匀性引起的环状伪影。
0 citationsRead paper
Selected work
Representative Papers
PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction
PhaseGAN通过解耦幅度和基于GAN的相位重建方法，解决了神经网络声码器中准确相位重建的问题，提高了音频质量和建模效率。
0 citationsRead paper
ABSE-NET: A Lightweight Neural Model for Active Binaural Speech Enhancement in Open-Fit Hearing Aids
为解决开放式助听器声泄漏问题，提出ABSE-NET模型结合主动降噪与双耳语音增强技术，采用轻量级神经网络与BMVDR级联方法，有效提升目标语音质量。
0 citationsRead paper
Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?
研究提出Peony基准，通过四个任务评估大型语言模型理解现代中文诗歌独特逻辑的能力，揭示现有模型的局限。
0 citationsRead paper
SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing
为解决文化、语言和社会群体挑战，提出SPAR-Hate框架，通过多代理和证据约束仲裁过程改进双语仇恨言论解析。
0 citationsRead paper
Recent publications
Latest Papers
TRACE: Two-Stage Detector-Response Estimation With Angular Cosine Expansion for Ring Artifact Correction in Photon-Counting CT
本文提出TRACE方法，通过两阶段无监督正弦图分解估计并校正光子计数CT中的探测器响应非均匀性引起的环状伪影。
0 citationsRead paper
PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction
PhaseGAN通过解耦幅度和基于GAN的相位重建方法，解决了神经网络声码器中准确相位重建的问题，提高了音频质量和建模效率。
0 citationsRead paper
ABSE-NET: A Lightweight Neural Model for Active Binaural Speech Enhancement in Open-Fit Hearing Aids
为解决开放式助听器声泄漏问题，提出ABSE-NET模型结合主动降噪与双耳语音增强技术，采用轻量级神经网络与BMVDR级联方法，有效提升目标语音质量。
0 citationsRead paper
Do Large Language Models Perform Well on Comprehending Poetic Logic in Modern Chinese Poetry?
研究提出Peony基准，通过四个任务评估大型语言模型理解现代中文诗歌独特逻辑的能力，揭示现有模型的局限。
0 citationsRead paper
SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing
为解决文化、语言和社会群体挑战，提出SPAR-Hate框架，通过多代理和证据约束仲裁过程改进双语仇恨言论解析。
0 citationsRead paper