BERT Traditional/Simplified Chinese Classifier
2025-11

BERT Traditional/Simplified Chinese Classifier

BERT-based classifier for Traditional Chinese variants (Taiwan vs Mainland). Achieves 87.71% accuracy with long-text support, Focal Loss, and MC Dropout voting.

PythonBERTNLPText Classification
🎯 87.71%
Formosa Vision: Open-Source Taiwanese Image Dataset
2025-09

Formosa Vision: Open-Source Taiwanese Image Dataset

Established the 'Formosa Vision Dialogue Corpus' using images from National Cultural Memory Bank 2.0 to enhance VLM's understanding of Taiwan's landmarks, history, and culture.

VLMDatasetTaiwanCultural AI
Fair Resume Matching System with XAI
2025-11

Fair Resume Matching System with XAI

A resume matching system balancing performance and fairness, combining LoRA fine-tuning, adversarial debiasing, and XAI for transparent decision-making.

PythonLoRAFairnessXAI
Chinese SMS Contrastive Clustering
2025-08

Chinese SMS Contrastive Clustering

A Chinese SMS classification system based on multi-stage clustering and contrastive learning, using SimCSE-style methods to fine-tune Sentence Encoder.

PythonContrastive LearningClusteringNLP
⭐ 2
OllaForge: LLM Dataset Generator
2025-10

OllaForge: LLM Dataset Generator

High-performance CLI tool leveraging local Ollama models to generate and augment training datasets for LLM fine-tuning with structured JSON output and concurrent batch processing.

PythonCLILLMData Generation
⭐ 1
GenTrip: AI Trip Planner
2024-09

GenTrip: AI Trip Planner

Smart travel planning system combining Pandas AI and GPT-4o RAG retrieval, supporting multimodal input and customizable requirements.

PythonRAGGPT-4GenAI
⭐ 2