Wei Huang
108 Arbeiten1.338 Zitationen
Relevante Arbeiten
Meistzitierte Publikationen im Bereich Gesundheit & MedTech
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
2023 · 17 Zit. · arXiv (Cornell University)
MetaPoison: Practical General-purpose Clean-label Data Poisoning
2020 · 14 Zit. · arXiv (Cornell University)
Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
2025 · 0 Zit. · ArXiv.org