ST
Sergey Troshin
cs.CLcs.LGcs.AIcs.SE
On Valency
published · living versionsW_z6djh46g·v1 · currentpublished
UvA-MT's Participation in the WMT26 General Translation Shared Task
with Di Wu, Wafaa Mohammed, Seth Aycock, Evgeniia Tokarchuk +2
1 version
Preprints & journals
9 papers in the corpus · 2020–2026UvA-MT's Participation in the WMT26 General Translation Shared Task2610.27852v1 · Di Wu, Sergey Troshin, Wafaa Mohammed et al.2026 · 0 citationsarXivon Valency
Last Translation Benchmark2609.04173v2 · Vil'em Zouhar, Niyati Bafna, Mukund Choudhary et al.2026 · 0 citationsarXiv
Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation2608.28496v2 · Di Wu, Sergey Troshin, Christof Monz et al.2026 · 0 citationsarXiv
Representation Collapse in Machine Translation Through the Lens of Angular Dispersion2602.17287v1 · Evgeniia Tokarchuk, Maya K. Nachesa, Sergey Troshin et al.2026 · 0 citationsarXiv
Asking a Language Model for Diverse Responses2509.17570v1 · Sergey Troshin, Irina Saparina, Antske Fokkens et al.2025 · 0 citationsarXiv
Angular Dispersion Accelerates -Nearest Neighbors Machine Translation2509.16729v1 · Evgeniia Tokarchuk, Sergey Troshin, Vlad Niculae2025 · 0 citationsarXiv
Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs2510.01218v1 · Sergey Troshin, Wafaa Mohammed, Yan Meng et al.2025 · 0 citationsarXiv
On the Low-Rank Parametrization of Reward Models for Controlled Language Generation2407.04615v4 · Sergey Troshin, Vlad Niculae, Antske Fokkens2024 · 0 citationsarXiv
A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code2010.12663v2 · Nadezhda Chirkova, Sergey Troshin2020 · 6 citationsarXiv
Career total: 11 works. 9 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.