Radu Soricut

11.2k total citations · 1 hit paper
42 papers, 2.5k citations indexed

About

Radu Soricut is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Molecular Biology. According to data from OpenAlex, Radu Soricut has authored 42 papers receiving a total of 2.5k indexed citations (citations by other indexed papers that have themselves been cited), including 36 papers in Artificial Intelligence, 18 papers in Computer Vision and Pattern Recognition and 3 papers in Molecular Biology. Recurrent topics in Radu Soricut's work include Natural Language Processing Techniques (27 papers), Topic Modeling (25 papers) and Multimodal Machine Learning Applications (17 papers). Radu Soricut is often cited by papers focused on Natural Language Processing Techniques (27 papers), Topic Modeling (25 papers) and Multimodal Machine Learning Applications (17 papers). Radu Soricut collaborates with scholars based in United States, United Kingdom and Netherlands. Radu Soricut's co-authors include Nan Ding, Piyush Sharma, Sebastian Goodman, Daniel Marcu, Eric Brill, Lucia Specia, Matt Post, Philipp Koehn, Christof Monz and Ondřej Bojar and has published in prestigious journals such as Information Processing & Management, Computer Vision and Image Understanding and Transactions of the Association for Computational Linguistics.

In The Last Decade

Radu Soricut

42 papers receiving 2.3k citations

Hit Papers

Conceptual Captions: A Cleaned, Hypernymed, Image Alt-tex... 2018 2026 2020 2023 2018 250 500 750 1000

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Radu Soricut United States 17 2.0k 1.2k 187 69 45 42 2.5k
Michael Denkowski United States 13 1.4k 0.7× 939 0.8× 128 0.7× 51 0.7× 51 1.1× 17 1.9k
Oscar Täckström United States 13 1.5k 0.8× 364 0.3× 158 0.8× 86 1.2× 27 0.6× 19 1.7k
Kevin Duh United States 24 2.1k 1.1× 490 0.4× 216 1.2× 101 1.5× 62 1.4× 148 2.4k
Mitesh M. Khapra India 19 1.2k 0.6× 442 0.4× 141 0.8× 29 0.4× 37 0.8× 86 1.5k
Loïc Barrault France 11 1.4k 0.7× 405 0.3× 158 0.8× 75 1.1× 24 0.5× 36 1.6k
Marta R. Costa‐jussà Spain 18 1.6k 0.8× 347 0.3× 112 0.6× 80 1.2× 73 1.6× 149 1.7k
Hao Zhou China 19 1.6k 0.8× 540 0.5× 126 0.7× 72 1.0× 19 0.4× 84 1.9k
Jacob Andreas United States 20 1.3k 0.7× 878 0.8× 63 0.3× 50 0.7× 18 0.4× 62 1.7k
Eiichiro Sumita Japan 32 3.8k 1.9× 940 0.8× 184 1.0× 203 2.9× 132 2.9× 333 4.0k

Countries citing papers authored by Radu Soricut

Since Specialization
Citations

This map shows the geographic impact of Radu Soricut's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Radu Soricut with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Radu Soricut more than expected).

Fields of papers citing papers by Radu Soricut

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Radu Soricut. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Radu Soricut. The network helps show where Radu Soricut may publish in the future.

Co-authorship network of co-authors of Radu Soricut

This figure shows the co-authorship network connecting the top 25 collaborators of Radu Soricut. A scholar is included among the top collaborators of Radu Soricut based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Radu Soricut. Radu Soricut is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Wu, Jialin, Hu Xia, Yaqing Wang, Bo Pang, & Radu Soricut. (2024). Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-Rank Experts. 14205–14215. 4 indexed citations
2.
Burns, Andrea, Burcu Karagol Ayan, Yasumasa Onoe, et al.. (2024). ImageInWords: Unlocking Hyper-Detailed Image Descriptions. 93–127. 1 indexed citations
3.
Changpinyo, Soravit, Linting Xue, Ashish V. Thapliyal, et al.. (2023). MaXM: Towards Multilingual Visual Question Answering. 2667–2682. 4 indexed citations
4.
Changpinyo, Soravit, Xi Chen, Hexiang Hu, et al.. (2023). PreSTU: Pre-Training for Scene-Text Understanding. 15224–15234. 8 indexed citations
5.
Wang, Su, Chitwan Saharia, Jordi Pont-Tuset, et al.. (2023). Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting. 18359–18369. 66 indexed citations
6.
Thapliyal, Ashish V., et al.. (2022). Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset. 715–729. 19 indexed citations
7.
Changpinyo, Soravit, et al.. (2022). All You May Need for VQA are Image Captions. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1947–1963. 25 indexed citations
8.
Akula, Arjun, Soravit Changpinyo, Boqing Gong, et al.. (2021). CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2148–2166. 13 indexed citations
9.
Zhu, Zhenhai & Radu Soricut. (2021). H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences. 3801–3815. 9 indexed citations
10.
Chandu, Khyathi Raghavi, Piyush Sharma, Soravit Changpinyo, Ashish Thapliyal, & Radu Soricut. (2020). Weakly Supervised Content Selection for Improved Image Captioning. 1 indexed citations
11.
Sharma, Piyush, Nan Ding, Sebastian Goodman, & Radu Soricut. (2018). Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning. 2556–2565. 1004 indexed citations breakdown →
12.
Ding, Nan & Radu Soricut. (2017). Cold-Start Reinforcement Learning with Softmax Policy Gradients. Neural Information Processing Systems. 30. 2817–2826. 7 indexed citations
13.
Bojar, Ondřej, Christian Buck, Christian Federmann, et al.. (2014). Findings of the 2014 Workshop on Statistical Machine Translation. 12–58. 335 indexed citations
14.
Bojar, Ondřej, Christian Buck, Chris Callison-Burch, et al.. (2013). Findings of the 2013 Workshop on Statistical Machine Translation. UvA-DARE (University of Amsterdam). 1–44. 179 indexed citations
15.
Bojar, Ondřej, Christian Buck, Chris Callison-Burch, et al.. (2013). Proceedings of the Eighth Workshop on Statistical Machine Translation. Workshop on Statistical Machine Translation. 6 indexed citations
16.
Callison-Burch, Chris, Philipp Koehn, Christof Monz, et al.. (2012). Proceedings of the Seventh Workshop on Statistical Machine Translation. Workshop on Statistical Machine Translation. 30 indexed citations
17.
Ravi, Sujith, Kevin Knight, & Radu Soricut. (2008). Automatic prediction of parser accuracy. 887–887. 27 indexed citations
18.
Soricut, Radu. (2005). Natural language generation for text-to-text applications using an information-slim representation. National Conference on Artificial Intelligence. 1662–1663. 2 indexed citations
19.
Soricut, Radu & Eric Brill. (2004). Automatic Question Answering: Beyond the Factoid.. North American Chapter of the Association for Computational Linguistics. 57–64. 68 indexed citations
20.
Echihabi, Abdessamad, et al.. (2002). GLEANS: A Generator of Logical Extracts and Abstracts for Nice Summaries. 5 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026