


最近变动
Anthropic → Mirendil · Founding member
经历
现任
Mirendil新Founding member
曾任
Anthropic– 2026Co-Leading AI Scientist, Discovery Team- Meta2025Student Researcher
Google2022 – 2025Student Researcher
Microsoft Research2019Undergraduate researcher
University of Texas at AustinPhD (fifth year),导师 Inderjit Dhillon- BIBITS Pilani, GoaBachelor's
,导师 Ravishankar Krishnaswamy (undergraduate thesis)
论文
- The Art of Scaling Reinforcement Learning Compute for LLMsarXiv 2025研究语言模型强化学习的表现如何随训练算力增加而变化,并提出一套训练方案(ScaleRL)。
- MatFormer: Nested Transformer for Elastic InferencearXiv 2023训练一个内含多个嵌套小模型的 Transformer,可按不同算力预算取出使用。
- Dual-Encoders for Extreme Multi-Label ClassificationarXiv 2023研究如何训练双编码器模型,用于标签数量极大的分类任务。