C
Colin B. Clement
Researcher at Microsoft
Publications - 24
Citations - 578
Colin B. Clement is an academic researcher from Microsoft. The author has contributed to research in topics: Image registration & Computer science. The author has an hindex of 6, co-authored 24 publications receiving 156 citations. Previous affiliations of Colin B. Clement include Cornell University.
Papers
More filters
Posted Content
GraphCodeBERT: Pre-training Code Representations with Data Flow
Daya Guo,Shuo Ren,Shuai Lu,Zhangyin Feng,Duyu Tang,Shujie Liu,Long Zhou,Nan Duan,Alexey Svyatkovskiy,Fu Shengyu,Michele Tufano,Shao Kun Deng,Colin B. Clement,Dawn Drain,Neel Sundaresan,Jian Yin,Daxin Jiang,Ming Zhou +17 more
TL;DR: Results show that code structure and newly introduced pre-training tasks can improve GraphCodeBERT and achieves state-of-the-art performance on the four downstream tasks and it is shown that the model prefers structure-level attentions over token- level attentions in the task of code search.
Posted Content
On the Use of ArXiv as a Dataset
TL;DR: This work provides a pipeline which standardizes and simplifies access to the arXiv's publicly available data, and uses this pipeline to extract and analyze a 6.7 million edge citation graph, with an 11 billion word corpus of full-text research articles.
Journal ArticleDOI
Image registration of low signal-to-noise cryo-STEM data.
Benjamin H. Savitzky,Ismail El Baggari,Colin B. Clement,Emily Waite,Berit H. Goodge,David J. Baek,John P. Sheckelton,Christopher Pasco,Hari P. Nair,Nathaniel J. Schreiber,Jason Hoffman,Jason Hoffman,Alemayehu S. Admasu,Jaewook Kim,Sang-Wook Cheong,Anand Bhattacharya,Darrell G. Schlom,Tyrel M. McQueen,Robert Hovden,Robert Hovden,Lena F. Kourkoutis +20 more
TL;DR: This work presents an approach which effectively registers and averages image stacks which are challenging due to their low-SNR and propensity for unit cell misalignments, and demonstrates the effectiveness of this approach on experimental, cryogenic STEM datasets.
Proceedings Article
GraphCodeBERT: Pre-training Code Representations with Data Flow
Daya Guo,Shuo Ren,Shuai Lu,Zhangyin Feng,Duyu Tang,Shujie Liu,Long Zhou,Nan Duan,Alexey Svyatkovskiy,Fu Shengyu,Michele Tufano,Shao Kun Deng,Colin B. Clement,Dawn Drain,Neel Sundaresan,Jian Yin,Daxin Jiang,Ming Zhou +17 more
TL;DR: GraphCodeBERT as mentioned in this paper uses data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables.
Journal ArticleDOI
Normal Form for Renormalization Groups
Archishman Raju,Colin B. Clement,Lorien X. Hayden,Jaron Kent-Dobias,Danilo B. Liarte,D. Zeb Rocklin,James P. Sethna +6 more
TL;DR: In this paper, normal form theory is used to classify nonlinearities near critical points into families, which could help researchers better understand fractal systems and improve the understanding of fractal structures.