Lei Hsiung
Lei Hsiung has 2 papers in our library, in 2026, most of them on Language models & pretraining, Bias, fairness & safety; often with Tianyu Pang, Yaoqing Yang, Pin-Yu Chen.
OpenAlex · ORCID · h-index 3 · 15 works · 57 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 6 times in our library · ⭐ Paper Stars ranking: #10408
Affiliations
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workSocial Sciences · 1 work
🧭 Topics 2Research subjects and languages the work is about.Bias, fairness & safety · 1 workLanguage models & pretraining · 1 work
Works by year
2020s
Papers
- Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets (2026 · 4 citations)
Open-weight chat models are released with safety alignment, but further fine-tuning, even on harmless data, often erodes these guardrails. - HTMuon: Improving Muon via Heavy-Tailed Spectral Correction (2026 · 2 citations)
Muon is a matrix-based optimizer now used in large-scale LLM training. It orthogonalizes the momentum matrix, which forces every singular value to one. The authors argue this has two costs. It gives as much weight to noisy, small-singular-value directions as to informative ones. It also keeps the weight spectra…
Co-authors here
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/lei-hsiung/