FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis

Posted by dbos UCAS

Kavli Affiliate: Yi Zhou | First 5 Authors: Ziqi Ni, Ao Fu, Yi Zhou, , | Summary: Achieving high-fidelity lip-speech synchronization in audio-driven talking portrait synthesis remains challenging. While multi-stage pipelines or diffusion models yield high-quality results, they suffer from high computational costs. Some approaches perform well on specific individuals with low resources, yet still […]


Continue.. FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis

OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD

Posted by dbos UCAS

Kavli Affiliate: Long Zhang | First 5 Authors: Yuxuan Chen, Long Zhang, Xu Zhu, Hua Zhou, Zhuyin Ren | Summary: Merging natural language interfaces with computational fluid dynamics (CFD) workflows presents transformative opportunities for both industry and research. In this study, we introduce OptMetaOpenFOAM – a novel framework that bridges MetaOpenFOAM with external analysis and […]


Continue.. OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD

Beyond Visibility Limits: A DRL-Based Navigation Strategy for Unexpected Obstacles

Posted by dbos UCAS

Kavli Affiliate: Biao Huang | First 5 Authors: Mingao Tan, Shanze Wang, Biao Huang, Zhibo Yang, Rongfei Chen | Summary: Distance-based reward mechanisms in deep reinforcement learning (DRL) navigation systems suffer from critical safety limitations in dynamic environments, frequently resulting in collisions when visibility is restricted. We propose DRL-NSUO, a novel navigation strategy for unexpected […]


Continue.. Beyond Visibility Limits: A DRL-Based Navigation Strategy for Unexpected Obstacles

Directional propagation of quantum Hall viscous fluid by nano-structural engineering

Posted by dbos UCAS

Kavli Affiliate: Mamoru Matsuo | First 5 Authors: Hiroshi Funaki, Ai Yamakage, Ryotaro Sano, Mamoru Matsuo, | Summary: We present a microscopic theory of the viscous electron fluid in the quantum Hall state based on the nonequilibrium Green’s function method and the von Neumann lattice representation. This approach permits the formulation of hydrodynamic equations in […]


Continue.. Directional propagation of quantum Hall viscous fluid by nano-structural engineering

Mean-Shift Distillation for Diffusion Mode Seeking

Posted by dbos UCSB

Kavli Affiliate: Matthew Fisher | First 5 Authors: Vikas Thamizharasan, Nikitas Chatzis, Iliyan Georgiev, Matthew Fisher, Difan Liu | Summary: We present mean-shift distillation, a novel diffusion distillation technique that provides a provably good proxy for the gradient of the diffusion output distribution. This is derived directly from mean-shift mode seeking on the distribution, and […]


Continue.. Mean-Shift Distillation for Diffusion Mode Seeking

Mean-Shift Distillation for Diffusion Mode Seeking

Posted by dbos UCSB

Kavli Affiliate: Matthew Fisher | First 5 Authors: Vikas Thamizharasan, Nikitas Chatzis, Iliyan Georgiev, Matthew Fisher, Evangelos Kalogerakis | Summary: We present mean-shift distillation, a novel diffusion distillation technique that provides a provably good proxy for the gradient of the diffusion output distribution. This is derived directly from mean-shift mode seeking on the distribution, and […]


Continue.. Mean-Shift Distillation for Diffusion Mode Seeking

Solving quadratic binary optimization problems using quantum SDP methods: Non-asymptotic running time analysis

Posted by dbos UCSB

Kavli Affiliate: David Gross | First 5 Authors: Fabian Henze, Viet Tran, Birte Ostermann, Richard Kueng, Timo de Wolff | Summary: Quantum computers can solve semidefinite programs (SDPs) using resources that scale better than state-of-the-art classical methods as a function of the problem dimension. At the same time, the known quantum algorithms scale very unfavorably […]


Continue.. Solving quadratic binary optimization problems using quantum SDP methods: Non-asymptotic running time analysis

Accuracy of Wearable ECG Parameter Calculation Method for Long QT and First-Degree A-V Block Detection: A Multi-Center Real-World Study with External Validations Compared to Standard ECG Machines and Cardiologist Assessments

Posted by dbos UCAS

Kavli Affiliate: Cheng Peng | First 5 Authors: Sumei Fan, Deyun Zhang, Yue Wang, Shijia Geng, Kun Lu | Summary: In recent years, wearable devices have revolutionized cardiac monitoring by enabling continuous, non-invasive ECG recording in real-world settings. Despite these advances, the accuracy of ECG parameter calculations (PR interval, QRS interval, QT interval, etc.) from […]


Continue.. Accuracy of Wearable ECG Parameter Calculation Method for Long QT and First-Degree A-V Block Detection: A Multi-Center Real-World Study with External Validations Compared to Standard ECG Machines and Cardiologist Assessments

Detecting Long QT Syndrome and First-Degree Atrioventricular Block using Single-Lead AI-ECG: A Multi-Center Real-World Study

Posted by dbos UCAS

Kavli Affiliate: Cheng Peng | First 5 Authors: Sumei Fan, Deyun Zhang, Yue Wang, Shijia Geng, Kun Lu | Summary: Home-based single-lead AI-ECG devices have enabled continuous, real-world cardiac monitoring. However, the accuracy of parameter calculations from single-lead AI-ECG algorithm remains to be fully validated, which is critical for conditions such as Long QT Syndrome […]


Continue.. Detecting Long QT Syndrome and First-Degree Atrioventricular Block using Single-Lead AI-ECG: A Multi-Center Real-World Study