🧑‍🔬 Vlad Niculae

🏛️ Affiliations

🎓University of AmsterdamAmsterdam · Netherlands2016–2026 · 40 paperscurrent🎓Cornell UniversityIthaca · United States2015–2018 · 13 papers🔬Instituto de TelecomunicaçõesLisbon · Portugal2018–2024 · 11 papers🎓University of BucharestBucharest · Romania2011–2013 · 9 papers🎓Saarland UniversitySaarbrücken · Germany2014–2019 · 3 papers🎓University of WolverhamptonWolverhampton · United Kingdom2013 · 3 papers🎓New York UniversityNew York · United States2019 · 2 papers🎓Williams CollegeWilliamstown · United States2017 · 2 papers🔬Max Planck Institute for Software SystemsSaarbrücken · Germany2014 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Adaptively Sparse Transformers (2019 · 271 citations)
   Standard Transformers normalize every attention head with softmax, so each head spreads at least some weight over all context tokens.
2. Argument Mining with Structured SVMs and RNNs (2017 · 160 citations)
   The paper addresses argument mining when support relations between argumentative units do not have to form trees.

All works

6 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Adaptively Sparse TransformersGonçalo M. Correia, Vlad Niculae, André F. T. MartinsConference on Empirical Methods in Natural Language Processing (EMNLP) · 271 citations
2. Argument Mining with Structured SVMs and RNNsVlad Niculae, Joonsuk Park, Claire CardieAnnual Meeting of the Association for Computational Linguistics (ACL) · 160 citations
3. Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation · original ↗ · no summary yet · Proceedings of Machine Translation Summit XX: Volume 1Wafaa Mohammed, Vlad Niculae2025 · 4 citations
4. Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding · original ↗ · no summary yet · Proceedings of the 19th Conference of the European Chapter of the Association…Wafaa Mohammed, Vlad Niculae, Chrysoula Zerva2026 · 1 citation
5. How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups · original ↗ · no summary yet · arXiv:2606.16596Wafaa Mohammed, Kata Naszadi, Vlad Niculae2026
6. Representation Collapse in Machine Translation Through the Lens of Angular Dispersion · original ↗ · no summary yet · Findings of the Association for Computational Linguistics: EACL 2026Evgeniia Tokarchuk et al.2026

🤝 Co-authors here

3 co-authors with a page, the most papers together first.

• André F. T. Martins
• Claire Cardie
• Joonsuk Park

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2017
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2019
• Findings of the Association for Computational Linguistics…
• Proceedings of Machine Translation Summit XX: Volume 1
• Proceedings of the 19th Conference of the European Chapter…

🔗 Cited by

Papers of our library cite their works 140 times (of the 141,840 papers whose bibliographies we read); 10 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/vlad-niculae/