Institution profile

San Francisco State University

Academic institutionnorthamerica · us
Official website
Research library17linked papers
Opportunities0open roles
Selected work

Representative Papers

GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation

Sep 24, 2026

This study addresses the failure of side information in imputing continuous block missingness in air quality sensor data by proposing a geometry-aware conditional diffusion model. Through joint conditioning on masks and observed values alongside variable identity encoding, the model preserves temporal characteristics while mitigating interference from absolute positional embeddings. Furthermore, a block-missing-specific configuration is designed to effectively isolate the geometry-aware conditioning effects, thereby enhancing robustness. Evaluated on the ItalyAir dataset, the proposed method achieves an RMSE of 0.340, significantly outperforming both full-context and CSDI baselines. This work establishes an efficient imputation paradigm for scenarios involving long continuous missing segments.

0 citationsRead paper

UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim Verification

Sep 24, 2026

This study addresses the challenge that existing methods struggle to capture critical local mismatches in the forensic verification of images paired with misleading claims. To this end, we propose a directional multi-scale coverage representation framework. This approach innovatively introduces a compact directional multi-scale local affinity representation to effectively preserve decisive local mismatch information. Furthermore, by integrating a threshold-supported ratio with a lightweight global-local classifier, it achieves precise image-text correspondence detection. Experimental results demonstrate that the proposed model attains a Macro-F1 score of 69.82% and a balanced accuracy of 71.05% on the Fauxtography benchmark, significantly outperforming existing baseline methods.

0 citationsRead paper

NeuroEdge: Real-Time Hand Gesture Recognition with High-Density EMG Using Deep Learning at the Edge

May 28, 2026

This work addresses the computational and memory bottlenecks inherent in deploying real-time, high-density electromyography (HD-EMG)–based gesture recognition on resource-constrained embedded devices. The authors propose an edge-based neuromuscular interface system that, for the first time, enables end-to-end real-time gesture recognition using 192-channel HD-EMG signals directly on microcontrollers (ESP32 and Sony Spresense). The system integrates a custom HD-EMG StreamBridge wireless interface, a lightweight EdgeDL inference framework, and a one-dimensional convolutional neural network, with co-optimized DMA and SPI burst communication to establish an efficient data streaming and inference pipeline. Evaluated on seven distinct gestures, the system achieves a classification accuracy of 90% with an average end-to-end latency of only 83 milliseconds.

0 citationsRead paper

Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts

May 08, 2026

This study addresses the substantial overestimation of the “unsolvability ceiling” in multi-LLM routing observed in prior work, which stems from evaluation artifacts such as judge bias, generation truncation, and format mismatches, thereby misleading router design. The authors propose the first systematic decomposition framework that leverages dual-judge verification, exact-match anchoring, and randomized shuffling controls. Applying this framework to 206,000 query–model pairs across six benchmarks using Gemma 4 and Llama 3.1 series models, they rigorously quantify how these artifacts inflate perceived unsolvability and distort training signals for routers. Their analysis markedly reduces the measured unsolvable fractions across tasks and reveals that standard routers often degenerate into majority-class predictors, incurring opportunity cost losses of 13–17 percentage points.

0 citationsRead paper
Recent publications

Latest Papers

GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation

Sep 24, 2026

This study addresses the failure of side information in imputing continuous block missingness in air quality sensor data by proposing a geometry-aware conditional diffusion model. Through joint conditioning on masks and observed values alongside variable identity encoding, the model preserves temporal characteristics while mitigating interference from absolute positional embeddings. Furthermore, a block-missing-specific configuration is designed to effectively isolate the geometry-aware conditioning effects, thereby enhancing robustness. Evaluated on the ItalyAir dataset, the proposed method achieves an RMSE of 0.340, significantly outperforming both full-context and CSDI baselines. This work establishes an efficient imputation paradigm for scenarios involving long continuous missing segments.

0 citationsRead paper

UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim Verification

Sep 24, 2026

This study addresses the challenge that existing methods struggle to capture critical local mismatches in the forensic verification of images paired with misleading claims. To this end, we propose a directional multi-scale coverage representation framework. This approach innovatively introduces a compact directional multi-scale local affinity representation to effectively preserve decisive local mismatch information. Furthermore, by integrating a threshold-supported ratio with a lightweight global-local classifier, it achieves precise image-text correspondence detection. Experimental results demonstrate that the proposed model attains a Macro-F1 score of 69.82% and a balanced accuracy of 71.05% on the Fauxtography benchmark, significantly outperforming existing baseline methods.

0 citationsRead paper

NeuroEdge: Real-Time Hand Gesture Recognition with High-Density EMG Using Deep Learning at the Edge

May 28, 2026

This work addresses the computational and memory bottlenecks inherent in deploying real-time, high-density electromyography (HD-EMG)–based gesture recognition on resource-constrained embedded devices. The authors propose an edge-based neuromuscular interface system that, for the first time, enables end-to-end real-time gesture recognition using 192-channel HD-EMG signals directly on microcontrollers (ESP32 and Sony Spresense). The system integrates a custom HD-EMG StreamBridge wireless interface, a lightweight EdgeDL inference framework, and a one-dimensional convolutional neural network, with co-optimized DMA and SPI burst communication to establish an efficient data streaming and inference pipeline. Evaluated on seven distinct gestures, the system achieves a classification accuracy of 90% with an average end-to-end latency of only 83 milliseconds.

0 citationsRead paper

Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts

May 08, 2026

This study addresses the substantial overestimation of the “unsolvability ceiling” in multi-LLM routing observed in prior work, which stems from evaluation artifacts such as judge bias, generation truncation, and format mismatches, thereby misleading router design. The authors propose the first systematic decomposition framework that leverages dual-judge verification, exact-match anchoring, and randomized shuffling controls. Applying this framework to 206,000 query–model pairs across six benchmarks using Gemma 4 and Llama 3.1 series models, they rigorously quantify how these artifacts inflate perceived unsolvability and distort training signals for routers. Their analysis markedly reduces the measured unsolvable fractions across tasks and reveals that standard routers often degenerate into majority-class predictors, incurring opportunity cost losses of 13–17 percentage points.

0 citationsRead paper