15 papers
CAREF: Calibration-Aware Regularization for Explanation Faithfulness Without Rationale Supervision
Naphat Nithisopa, Teerapong Panboonyuen
We introduce CAREF, a parameter-efficient fine-tuning framework that jointly optimizes predictive accuracy and explanation faithfulness via calibration-aware regularization. At its…
GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning
Kasidit Sermsri, Teerapong Panboonyuen
Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and s…
Foundations and Architectures of Artificial Intelligence for Motor Insurance
Teerapong Panboonyuen
This handbook presents a systematic treatment of the foundations and architectures of artificial intelligence for motor insurance, grounded in large-scale real-world deployment. It…
HOMEY: Heuristic Object Masking with Enhanced YOLO for Property Insurance Risk Detection
Teerapong Panboonyuen
Automated property risk detection is a high-impact yet underexplored frontier in computer vision with direct implications for real estate, underwriting, and insurance operations. W…
HERS: Hidden-Pattern Expert Learning for Risk-Specific Vehicle Damage Adaptation in Diffusion Models
Teerapong Panboonyuen
Recent advances in text-to-image (T2I) diffusion models have enabled increasingly realistic synthesis of vehicle damage, raising concerns about their reliability in automated insur…
Seeing Isn't Always Believing: Analysis of Grad-CAM Faithfulness and Localization Reliability in Lung Cancer CT Classification
Teerapong Panboonyuen
Explainable Artificial Intelligence (XAI) techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM), have become indispensable for visualizing the reasoning process…
KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image
Teerapong Panboonyuen
Satellite image inpainting is a crucial task in remote sensing, where accurately restoring missing or occluded regions is essential for robust image analysis. In this paper, we pro…
Debiasing Large Language Models in Thai Political Stance Detection via Counterfactual Calibration
Kasidit Sermsri, Teerapong Panboonyuen
Political stance detection in low-resource and culturally complex settings poses a critical challenge for large language models (LLMs). In the Thai political landscape - marked by…
CU-ICU: Customizing Unsupervised Instruction-Finetuned Language Models for ICU Datasets via Text-to-Text Transfer Transformer
Teerapong Panboonyuen
Integrating large language models into specialized domains like healthcare presents unique challenges, including domain adaptation and limited labeled data. We introduce CU-ICU, a…
SLICK: Selective Localization and Instance Calibration for Knowledge-Enhanced Car Damage Segmentation in Automotive Insurance
Teerapong Panboonyuen
We present SLICK, a novel framework for precise and robust car damage segmentation that leverages structural priors and domain knowledge to tackle real-world automotive inspection…
ALBERT: Advanced Localization and Bidirectional Encoder Representations from Transformers for Automotive Damage Evaluation
Teerapong Panboonyuen
This paper introduces ALBERT, an instance segmentation model specifically designed for comprehensive car damage and part segmentation. Leveraging the power of Bidirectional Encoder…
DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation
Naphat Nithisopa, Teerapong Panboonyuen
Text recognition in natural images remains a challenging yet essential task, with broad applications spanning computer vision and natural language processing. This paper introduces…
SEA-ViT: Sea Surface Currents Forecasting Using Vision Transformer and GRU-Based Spatio-Temporal Covariance Modeling
Teerapong Panboonyuen
Forecasting sea surface currents is essential for applications such as maritime navigation, environmental monitoring, and climate analysis, particularly in regions like the Gulf of…
REG: Refined Generalized Focal Loss for Road Asset Detection on Thai Highways Using Vision-Based Detection and Segmentation Models
Teerapong Panboonyuen
This paper introduces a novel framework for detecting and segmenting critical road assets on Thai highways using an advanced Refined Generalized Focal Loss (REG) formulation. Integ…
MARS: Mask Attention Refinement with Sequential Quadtree Nodes for Car Damage Instance Segmentation
Teerapong Panboonyuen, Naphat Nithisopa, Panin Pienroj +3
Evaluating car damages from misfortune is critical to the car insurance industry. However, the accuracy is still insufficient for real-world applications since the deep learning ne…