基本信息
views: 23
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
I mainly work on deep-learning-based reasoning and its applications. I am interested in the following subjects:
Generative models, in particular, induction of compositional structure in generative models and modeling of posteriors over high-dimensional explanatory variables. Much of my recent work is on generative flow networks, or GFlowNets, which are a path towards inference machines that build structured, uncertainty-aware explanations for observed data.
Applications to natural language processing: what large language models can do, what they cannot do, and how to overcome their limitations with inference procedures that induce behaviours more akin to human reasoning.
Generative models, in particular, induction of compositional structure in generative models and modeling of posteriors over high-dimensional explanatory variables. Much of my recent work is on generative flow networks, or GFlowNets, which are a path towards inference machines that build structured, uncertainty-aware explanations for observed data.
Applications to natural language processing: what large language models can do, what they cannot do, and how to overcome their limitations with inference procedures that induce behaviours more akin to human reasoning.
Research Interests
Papers共 12 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
International Conference on Artificial Intelligence and Statistics (2024): 1279-1287
Cited0Views0EIBibtex
0
0
Siddarth Venkatraman,Moksh Jain,Luca Scimeca,Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe,Sarthak Mittal,Pablo Lemos,Emmanuel Bengio,Alexandre Adam,Jarrid Rector-Brooks,
CoRR (2024)
Cited0Views0EIBibtex
0
0
CoRR (2024)
Cited0Views0Bibtex
0
0
arxiv(2024)
Cited0Views0Bibtex
0
0
CoRR (2024)
Cited0Views0EIBibtex
0
0
ICLR 2023 (2023)
NeurIPS 2022 (2022)
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