Selected work

Representative Papers

Enabling Ultra-Low-Power Always-On Feedforward Leakage Suppression Logic Circuits with FDSOI

Aug 13, 2026

This work addresses the growing challenge of always-on (AO) domain leakage power, which has become a critical bottleneck for energy efficiency in low-duty-cycle wearable and IoT edge devices. For the first time, the authors implement and experimentally validate Feedforward Leakage Suppression Logic (FLSL) in a 22 nm fully depleted silicon-on-insulator (FDSOI) process, leveraging its superior junction leakage control to replace conventional high-threshold-voltage (HVT) transistor approaches. Measurements demonstrate that FLSL-based implementations of an FIR filter and an AES encryption core achieve 9.8× and 1.83× lower leakage power, respectively, compared to HVT and ultra-high-threshold-voltage (UHVT) CMOS designs, while also enabling operation at reduced supply voltages—thereby significantly enhancing overall energy efficiency.

0 citationsRead paper

Representation-Based Data Quality Audits for Audio

Sep 30, 2025

Audio datasets commonly suffer from off-topic samples, near-duplicates, and label noise—issues that severely degrade model performance. To address this, we propose the first unified data quality auditing framework tailored for audio, adapting SelfClean from computer vision to the audio domain. Leveraging self-supervised pretrained models (e.g., AST, BEATs), our method extracts robust audio representations and establishes a “representation → ranking” paradigm, enabling simultaneous detection and interpretable prioritization of all three data quality issues in a single pipeline. Evaluated on ESC-50, GTZAN, and an industrial private dataset, our approach significantly outperforms task-specific baselines across multiple ranking metrics (average +12.7% NDCG@10). Human review efficiency improves by 3.2×, substantially reducing annotation costs. The framework offers a scalable, plug-and-play solution for audio data governance.

0 citationsRead paper

SolarCrossFormer: Improving day-ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors

Sep 19, 2025

To address the insufficient spatiotemporal resolution of existing day-ahead solar irradiance forecasting methods—limiting their applicability to large-scale photovoltaic grid integration—this paper proposes a cross-modal graph neural network that jointly leverages satellite remote sensing imagery and ground-based meteorological time series. The model implicitly encodes geographic coordinates as input, enabling probabilistic 15-minute-resolution forecasts up to 24 hours ahead across any location in Switzerland. It exhibits zero-shot generalization: it can seamlessly incorporate newly deployed sensors without retraining and impute irradiance values in unobserved regions. Evaluated on one year of ground-truth measurements from 127 stations, the model achieves a normalized mean absolute error of 6.1%, matching the accuracy of commercial numerical weather prediction systems while substantially improving forecast robustness and deployment flexibility.

0 citationsRead paper

Recent publications

Latest Papers

Enabling Ultra-Low-Power Always-On Feedforward Leakage Suppression Logic Circuits with FDSOI

Aug 13, 2026

This work addresses the growing challenge of always-on (AO) domain leakage power, which has become a critical bottleneck for energy efficiency in low-duty-cycle wearable and IoT edge devices. For the first time, the authors implement and experimentally validate Feedforward Leakage Suppression Logic (FLSL) in a 22 nm fully depleted silicon-on-insulator (FDSOI) process, leveraging its superior junction leakage control to replace conventional high-threshold-voltage (HVT) transistor approaches. Measurements demonstrate that FLSL-based implementations of an FIR filter and an AES encryption core achieve 9.8× and 1.83× lower leakage power, respectively, compared to HVT and ultra-high-threshold-voltage (UHVT) CMOS designs, while also enabling operation at reduced supply voltages—thereby significantly enhancing overall energy efficiency.

0 citationsRead paper

Representation-Based Data Quality Audits for Audio

Sep 30, 2025

Audio datasets commonly suffer from off-topic samples, near-duplicates, and label noise—issues that severely degrade model performance. To address this, we propose the first unified data quality auditing framework tailored for audio, adapting SelfClean from computer vision to the audio domain. Leveraging self-supervised pretrained models (e.g., AST, BEATs), our method extracts robust audio representations and establishes a “representation → ranking” paradigm, enabling simultaneous detection and interpretable prioritization of all three data quality issues in a single pipeline. Evaluated on ESC-50, GTZAN, and an industrial private dataset, our approach significantly outperforms task-specific baselines across multiple ranking metrics (average +12.7% NDCG@10). Human review efficiency improves by 3.2×, substantially reducing annotation costs. The framework offers a scalable, plug-and-play solution for audio data governance.

0 citationsRead paper

SolarCrossFormer: Improving day-ahead Solar Irradiance Forecasting by Integrating Satellite Imagery and Ground Sensors

Sep 19, 2025

To address the insufficient spatiotemporal resolution of existing day-ahead solar irradiance forecasting methods—limiting their applicability to large-scale photovoltaic grid integration—this paper proposes a cross-modal graph neural network that jointly leverages satellite remote sensing imagery and ground-based meteorological time series. The model implicitly encodes geographic coordinates as input, enabling probabilistic 15-minute-resolution forecasts up to 24 hours ahead across any location in Switzerland. It exhibits zero-shot generalization: it can seamlessly incorporate newly deployed sensors without retraining and impute irradiance values in unobserved regions. Evaluated on one year of ground-truth measurements from 127 stations, the model achieves a normalized mean absolute error of 6.1%, matching the accuracy of commercial numerical weather prediction systems while substantially improving forecast robustness and deployment flexibility.

0 citationsRead paper