基本信息
views: 143
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
I am a research scientist in the Language Team at Google DeepMind. I currently work on data quality for pretraining and fine tuning stages of large language models (Gemini).
Research-wise, I am passionate about training data attribution at scale, i.e. measuring how much each output is influenced by each training example, and using this insight to improve model quality, enable data curation with feedback from the model, and discover causal links between the training data and model behavior. Over the years, I have also worked on interpretability and model understanding for language and vision models, including feature and example-level attribution methods, counterfactual analysis and concepts in embedding spaces.
I also enjoy engineering and have built large scale AI/ML infrastructure for model and dataset debugging and understanding, e.g. Google Cloud XAI and model internals-based retrieval for large transformers on billions of examples.
Research-wise, I am passionate about training data attribution at scale, i.e. measuring how much each output is influenced by each training example, and using this insight to improve model quality, enable data curation with feedback from the model, and discover causal links between the training data and model behavior. Over the years, I have also worked on interpretability and model understanding for language and vision models, including feature and example-level attribution methods, counterfactual analysis and concepts in embedding spaces.
I also enjoy engineering and have built large scale AI/ML infrastructure for model and dataset debugging and understanding, e.g. Google Cloud XAI and model internals-based retrieval for large transformers on billions of examples.
Research Interests
Papers共 32 篇Author StatisticsCo-AuthorSimilar Experts
By YearBy Citation主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Gemini Team, Petko Georgiev, Ving Ian Lei,Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, Soroosh Mariooryad, Yifan Ding,
arxiv(2024)
Cited0Views0Bibtex
0
0
CoRR (2023): 400-414
CoRR (2023): 2033-2045
CoRR (2023)
CoRR (2022)
CoRR (2021)
Cited2Views0EIBibtex
2
0
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021): 5048-5056
FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCYpp.705-705, (2020)
Load More
Author Statistics
Co-Author
Co-Institution
D-Core
- 合作者
- 学生
- 导师
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn