Institution profile

Technology Innovation Institute

Academic institutionasia · ae
Official website
Research library118linked papers
Opportunities0open roles
Selected work

Representative Papers

Local Interpolation via Low-Rank Tensor Trains

Jan 07, 2026arXiv.org

High-dimensional grid data represented in the tensor train (TT) format often suffer from rank explosion due to global unfolding, hindering efficient interpolation and compression. This work proposes a low-rank TT local interpolation framework that starts from a coarse-grid TT representation and constructs a fine-grid TT with uniformly bounded tail ranks through multiscale local refinement. The method achieves, for the first time, an ℓ² error bound independent of the total number of cores, exponential compression rates at fixed accuracy, and logarithmic computational complexity with respect to the number of grid points. Its efficacy is demonstrated on 1D/2D/3D tasks—including airfoil mask embedding, image super-resolution, and synthetic turbulent noise—and it enables direct generation of fractal noise fields with logarithmic complexity.

1 citationsRead paper

DiffNMR: Advancing Inpainting of Randomly Sampled Nuclear Magnetic Resonance Signals

May 26, 2025

To address severe artifacts and low fidelity in non-uniformly sampled (NUS) nuclear magnetic resonance (NMR) spectrum reconstruction, this work introduces denoising diffusion probabilistic models (DDPMs) to NMR signal recovery for the first time. We propose a time–frequency joint sparse representation framework incorporating complex-domain preprocessing, adaptive noise scheduling, and Fourier-domain constraints—significantly outperforming conventional time–time domain modeling. On the Artina benchmark, our method effectively suppresses NUS-induced artifacts, improves signal-to-noise ratio and peak shape accuracy, and achieves state-of-the-art spectral fidelity. Moreover, reconstruction time is reduced by 3–5× compared to existing approaches. This study not only establishes the efficacy of diffusion models for NMR spectral reconstruction but also pioneers a novel time–frequency collaborative modeling paradigm, opening new avenues for deep generative modeling in analytical spectroscopy.

1 citationsRead paper
Recent publications

Latest Papers

WiFiSpectralJam: A Large-Scale Open Wi-Fi Spectral Scan Dataset with Controlled RF Jamming

Aug 16, 2026

This study addresses the critical scarcity of large-scale Wi-Fi spectrum and controlled interference datasets by developing an open scanning platform based on Raspberry Pi CM4 and QCA9880 commercial network interface cards. The research collected 520 million observations encompassing background noise and controlled interference scenarios across 2.4 GHz and 5 GHz bands, resulting in the release of a 14.52 GB dataset accompanied by comprehensive metadata and reproducible protocols. This work establishes a vital benchmark for spectrum sensing using commercial off-the-shelf hardware, filling a significant gap in existing resources. Consequently, the released dataset effectively facilitates key tasks including radio frequency interference detection, distribution shift evaluation, and machine learning model validation, thereby advancing empirical research in wireless spectrum analysis.

0 citationsRead paper

Wind-Informed Rapid Flight-Planning in Complex Urban Topologies via Machine Learning and Experimental Validation

Aug 10, 2026

This study addresses the hazardous airflow patterns generated by building-wind interactions in urban environments, which pose significant risks to low-altitude aerial vehicles. The work proposes the first end-to-end system that integrates real-time wind field prediction with trajectory planning. Leveraging building geometry and incoming wind data, a machine learning surrogate model rapidly predicts three-dimensional urban wind fields and constructs a scalar field representing flight challenge levels that account for aerodynamic disturbances. Building upon this field, a cost-minimizing path planner generates safe trajectories. Wind tunnel experiments demonstrate that, compared to conventional approaches ignoring wind effects, the proposed method substantially reduces unintended vehicle deviations and enhances flight stability, enabling micro aerial vehicles to safely navigate through complex urban settings.

0 citationsRead paper