Lei Hsiung

According to our database, Lei Hsiung authored at least 13 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction.

Tianyu Pang, Yujie Fang, Zihang Liu, Shenyang Deng, Lei Hsiung, Shuhua Yu, Yaoqing Yang

CoRR, March, 2026

The Pitfalls of Text Degeneration when Aligning LLMs through Model Merge.

Peijun Qing, Lei Hsiung, Hefan Zhang, Haiquan Lu, Xingjian Diao, Chiyu Ma, Saeed Hassanpour, Soroush Vosoughi

Trans. Mach. Learn. Res., 2026

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets.

Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, Yaoqing Yang

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

When Does Visual Prompting Outperform Linear Probing for Vision-Language Models? A Likelihood Perspective.

Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Tsung-Yi Ho

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Spectral Insights into Data-Oblivious Critical Layers in Large Language Models.

Xuyuan Liu, Lei Hsiung, Yaoqing Yang, Yujun Yan

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes.

Hao-Lun Sun, Lei Hsiung, Nandhini Chandramoorthy, Pin-Yu Chen, Tsung-Yi Ho

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

AutoVP: An Automated Visual Prompting Framework and Benchmark.

Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Si Liu, Tsung-Yi Ho

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

AutoVP: An Automated Visual Prompting Framework and Benchmark.

Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Sijia Liu, Tsung-Yi Ho

CoRR, 2023

NeuralFuse: Learning to Improve the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes.

Hao-Lun Sun, Lei Hsiung, Nandhini Chandramoorthy, Pin-Yu Chen, Tsung-Yi Ho

CoRR, 2023

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations.

Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration.

Lei Hsiung, Yung-Chen Tang, Pin-Yu Chen, Tsung-Yi Ho

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

CARBEN: Composite Adversarial Robustness Benchmark.

Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

A Lab-Based Investigation of Reaction Time and Reading Performance using Different In-Vehicle Reading Interfaces during Self-Driving.

Lei Hsiung, Yung-Ju Chang, Wei-Ko Li, Tsung-Yi Ho, Shan-Hung Wu

Proceedings of the AutomotiveUI '22: 14th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, Seoul, Republic of Korea, September 17, 2022