Author

G. Thai

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Repair Before You Fuse: Frozen-Host Adaptation for Corrupted-but-Present Sensors

Camera-LiDAR detectors can continue to consume unreliable features even when both sensors remain present, synchronized, and calibrated. We introduce \emph{Boundary Feature Repair} (BFR), a frozen-host adaptation framework that learns task-supervised residual corrections at modality interfaces the detector already consu...

G. Thai, Quang-Thinh Ly, A. Phan et al. · 0 citations

#machine learning Preprint Sep 2026

How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds

Few-shot anomaly detectors are judged by ranking metrics, yet deployment requires an alarm threshold with a controlled false-alarm rate (FAR). We ask how much normal evidence, in images or category units, is needed to certify such a threshold for an unseen category. Using a frozen DINOv2 principal component analysis (P...

G. Thai, A. T. Nguyen · 0 citations

#artificial intelligence Conference Nov 2025

SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks, establishes a scalable foundation for dynamic expert routing in visual networks, thereby facilitating flexible visual reasoning.

G. Thai, Hoang-Nguyen Vu, A. Phan et al. · 2026 IEEE/CVF Conference on... · 1 citation