CV

Education

• Ph.D. in Communication Engineering, National Taiwan University, 2021 - Present
  • Network Database Laboratory
  • Supervisor: Ming-Syan Chen
• M.S. in Manufacturing Technology, National Taipei University of Technology, 2018 - 2021
  • Advanced Microsystems and Device Laboratory
  • Supervisor: Chih-Cheng Lu
• B.S. in Mechanical Engineering, National Taipei University of Technology, 2014 - 2018

Research Interests

• Efficient Deep Learning for Transformers (2024–Present)
  • Dynamic LLM inference (BiLEE, ECAI 2024)
  • Pruning Vision Transformers with LoRA-guided importance consensus (LoGIC, AAAI 2026)
  • KV-cache compression for long-context inference
• Few-Shot Learning under Distribution Shifts (2023–2024)
  • Dual alignment and optimal transport-based feature calibration for robust few-shot adaptation (DuAL, NeurIPS 2025)
• Interpretable ECG Diagnosis (2019–2021)
  • Interpretable 3-D ECG deep models for myocardial infarction detection (CMPB 2022)

Skills

• Deep Learning & Neural Networks
  • Vision Transformers (ViT)
  • Large Language Models (LLMs)
  • Graph Neural Networks
  • Convolutional Neural Networks (CNNs)
• Model Optimization
  • Network Pruning
  • Knowledge Distillation
  • Quantization
  • LoRA and Parameter Efficient Fine-tuning
• Signal Processing
  • ECG Analysis
  • Biomedical Signal Processing
• Programming Languages
  • Python, C++, CUDA
  • PyTorch, TensorFlow, JAX

Publications

LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers

Chou, Yu-Hong*, Fang, Rui*, Chen, Hsi-Wen, and Chen, Ming-Syan. (2026). "LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers." Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-26).

Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts

Jiang, Siyang, Fang, Rui, Chen, Hsi-Wen, Ding, Wei, Xing, Guoliang, and Chen, Ming-Syan. (2025). "Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts." NeurIPS 2025.

Bi-Level Early Exiting for Generative Document Retrieval

Fang, Rui, Yeh, Chin-Yuan, Chen, Hsi-Wen, and Chen, Ming-Syan. (2024). "Bi-Level Early Exiting for Generative Document Retrieval." Frontiers in Artificial Intelligence and Applications, Volume 392: ECAI 2024, 4035–4042.

Dual-Triangular QR Decomposition with Global Acceleration and Partially Q-Rotation Skipping

Fang, Rui, Jiang, Siyang, Chen, Hsi-Wen, Ding, Wei, and Chen, Ming-Syan. (2022). "Dual-Triangular QR Decomposition with Global Acceleration and Partially Q-Rotation Skipping." 2022 International Conference on Field-Programmable Technology (ICFPT), 1–4.

A visually interpretable detection method combines 3-D ECG with a multi-VGG neural network for myocardial infarction identification

Professional Activity

• Conference Reviewer: CVPR, ICML, IJCAI, ECAI, ECCV, etc.