CV
Education
National Taiwan University, Graduate Institute of Communication Engineering
Ph.D. at Network Database Laboratory. Supervisor: Prof. Ming-Syan Chen
National Taipei University of Technology, Graduate Institute of Manufacturing Technology
M.S. at Advanced Microsystems and Device Laboratory. Supervisor: Prof. Chih-Cheng Lu
National Taipei University of Technology, College of Mechanical and Electrical Engineering
B.S. in Mechanical Engineering
Awards
- 2025 National Taiwan University Wen-Tzu Hsiang Memorial Scholarship
Research Interests
- Efficient Transformer inference: early exiting, KV admission, long-context inference, and adaptive computation for generative retrieval and language models.
- Model compression and quantization: quantization for recursive Transformers and early-exit Vision Transformers, LoRA-guided pruning, and multi-task compression.
- Trustworthy deployment: multi-task unlearning, secure on-device language models with trusted execution environments, and interpretable medical AI.
Skills
Deep Learning
Vision Transformers, Large Language Models, Graph Neural Networks, Convolutional Neural Networks
Model Optimization
Network pruning, quantization, early exiting, LoRA, parameter-efficient fine-tuning
Systems and Deployment
On-device inference, trusted execution environments, CUDA and GPU programming
Programming
Python, C++, CUDA, PyTorch, TensorFlow, JAX
Publications
LoopQ: Quantization for Recursive Transformers
arXiv preprint arXiv:2605.16343, 2026
Interference-Aware Multi-Task Unlearning
arXiv preprint arXiv:2605.19042, 2026
Amortized-Precision Quantization for Early-Exit Vision Transformers
arXiv preprint arXiv:2605.07317, 2026
LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers
Proceedings of the AAAI Conference on Artificial Intelligence 40(25), 20588-20596, 2026
Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
Advances in Neural Information Processing Systems 38, 64804-64830, 2026
KV Admission: Learning What to Write for Efficient Long-Context Inference
arXiv preprint arXiv:2512.17452, 2025
SEAL: Secure and Efficient Adaptive Layering for On-Device Language Models with TEE
2025 IEEE 11th International Conference on Edge Computing and Scalable Cloud, 2025
BiLEE: Bi-Level Early Exiting for Generative Document Retrieval
ECAI 2024: 27th European Conference on Artificial Intelligence, 4035-4042, 2024
Dual-Triangular QR Decomposition with Global Acceleration and Partially Q-Rotation Skipping
2022 International Conference on Field-Programmable Technology (ICFPT), 1-4, 2022
A visually interpretable detection method combines 3-D ECG with a multi-VGG neural network for myocardial infarction identification
Computer Methods and Programs in Biomedicine 219, 106762, 2022
Professional Activity
- Conference Reviewer: CVPR, ICML, IJCAI, ECAI, ECCV, ICLR, NeurIPS, etc.