


最近变动
Virtue AI → Meta
经历
现任
- Meta新
加入
曾任
Virtue AI– 2026Co-founder
Stanford University (stai_research group)Leads the lab
论文
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT ModelsarXiv 2023提出一套基准,从毒性、偏见、鲁棒性、隐私、公平等方面测试 GPT 模型的可信度。
- Are Emergent Abilities of Large Language Models a Mirage?arXiv 2023认为语言模型能力看似突然跃升,可能来自评估指标的选择。
访谈与演讲
- 2026-08-20Sanmi Koyejo: Stanford Professor '50% of AI Is Data — 10% Is the Algorithm We Actually Teach' |
Ep 9 · Practice Ground · 播客 ↗ - 2025-11-28Ep. 31: Sanmi Koyejo, Stanford CS Professor and Virtue
AI Co-Founder · Delta Podcast · 播客 ↗ - 2024-02-12Are Emergent Behaviors in LLMs an Illusion? with
Sanmi Koyejo · The TWIMLAI Podcast · 播客 ↗ - 2020-02-27Metric Elicitation and Robust Distributed Learning with
Sanmi Koyejo · The TWIMLAI Podcast · 播客 ↗
时间线上提到
这一页有错误或遗漏?告诉我,会更正或撤下。 联系 →