VN
Vlad Niculae
cs.CLcs.LGstat.MLcs.AIcs.CVcs.SIphysics.soc-phcs.MScs.SDeess.AS
On Valency
published · living versionsW_z6djh46g·v1 · currentpublished
UvA-MT's Participation in the WMT26 General Translation Shared Task
with Di Wu, Sergey Troshin, Wafaa Mohammed, Seth Aycock +2
1 version
W_hthtev2b·v1published
Preprints & journals
48 papers in the corpus · 2013–2026UvA-MT's Participation in the WMT26 General Translation Shared Task2610.27852v1 · Di Wu, Sergey Troshin, Wafaa Mohammed et al.2026 · 0 citationsarXivon Valency
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
How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups2606.16596v1 · Wafaa Mohammed, Kata Naszadi, Vlad Niculae2026 · 0 citationsarXiv
Your Multimodal Speech Model Says I Have a Face for Radio2605.30472v1 · Maya K. Nachesa, Vlad Niculae, Vagrant Gautam2026 · 0 citationsarXiv
AdaSplash-2: Faster Differentiable Sparse Attention2604.15180v1 · Nuno Goncalves, Hugo Pitorro, Vlad Niculae 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
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding2510.06866v1 · Wafaa Mohammed, Vlad Niculae, Chrysoula Zerva2025 · 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
How Well Do Vision-Language Models Understand Movies?2506.06275v2 · Emmanouil Zaranis, Ant'onio Farinhas, Saul Santos et al.2025 · 0 citationsarXiv
Keep your distance: learning dispersed embeddings on 2502.08231v4 · Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae2025 · 0 citationsTMLR (2025)
Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval2411.08590v5 · Saul Santos, Vlad Niculae, Daniel McNamee et al.2024 · 0 citationsarXiv
kNN For Whisper And Its Effect On Bias And Speaker Adaptation2410.18850v2 · Maya K. Nachesa, Vlad Niculae2024 · 0 citationsarXiv
Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation2410.14391v2 · Wafaa Mohammed, Vlad Niculae2024 · 0 citationsarXiv
On the Low-Rank Parametrization of Reward Models for Controlled Language Generation2407.04615v4 · Sergey Troshin, Vlad Niculae, Antske Fokkens2024 · 0 citationsarXiv
Sparse and Structured Hopfield Networks2402.13725v2 · Saul Santos, Vlad Niculae, Daniel McNamee et al.2024 · 1 citationarXiv
On Measuring Context Utilization in Document-Level MT Systems2402.01404v1 · Wafaa Mohammed, Vlad Niculae2024 · 2 citationsarXiv
The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation2310.20620v2 · Evgeniia Tokarchuk, Vlad Niculae2023 · 1 citationarXiv
Joint Dropout: Improving Generalizability in Low-Resource Neural Machine Translation through Phrase Pair Variables2307.12835v1 · Ali Araabi, Vlad Niculae, Christof Monz2023 · 0 citationsarXiv
Two derivations of Principal Component Analysis on datasets of distributions2306.13503v1 · Vlad Niculae2023 · 1 citationarXiv
Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens2305.11550v3 · David Stap, Vlad Niculae, Christof Monz2023 · 4 citationsarXiv
DAG Learning on the Permutahedron2301.11898v2 · Valentina Zantedeschi, Luca Franceschi, Jean Kaddour et al.2023 · 1 citationarXiv
Discrete Latent Structure in Neural Networks2301.07473v3 · Vlad Niculae, Caio F. Corro, Nikita Nangia et al.2023 · 5 citationsarXiv
How Effective is Byte Pair Encoding for Out-Of-Vocabulary Words in Neural Machine Translation?2208.05225v2 · Ali Araabi, Christof Monz, Vlad Niculae2022 · 6 citationsarXiv
Modeling Structure with Undirected Neural Networks2202.03760v2 · Tsvetomila Mihaylova, Vlad Niculae, Andr'e F. T. Martins2022 · 1 citationarXiv
Sparse Communication via Mixed Distributions2108.02658v2 · Ant'onio Farinhas, Wilker Aziz, Vlad Niculae et al.2021 · 1 citationarXiv
Sparse Continuous Distributions and Fenchel-Young Losses2108.01988v2 · Andr'e F. T. Martins, Marcos Treviso, Ant'onio Farinhas et al.2021 · 3 citationsarXiv
Learning Binary Decision Trees by Argmin Differentiation2010.04627v2 · Valentina Zantedeschi, Matt J. Kusner, Vlad Niculae2020 · 7 citationsarXiv
Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning2010.02357v1 · Tsvetomila Mihaylova, Vlad Niculae, Andr'e F. T. Martins2020 · 0 citationsarXiv
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity2007.01919v3 · Goncalo M. Correia, Vlad Niculae, Wilker Aziz et al.2020 · 9 citationsarXiv
Sparse and Continuous Attention Mechanisms2006.07214v3 · Andr'e F. T. Martins, Ant'onio Farinhas, Marcos Treviso et al.2020 · 20 citationsarXiv
Sparse and Structured Visual Attention2002.05556v2 · Pedro Henrique Martins, Vlad Niculae, Zita Marinho et al.2020 · 6 citationsarXiv
LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction2001.04437v3 · Vlad Niculae, Andr'e F. T. Martins2020 · 9 citationsarXiv
Adaptively Sparse Transformers1909.00015v2 · Goncalo M. Correia, Vlad Niculae, Andr'e F.T. Martins2019 · 17 citationsarXiv
Notes on Latent Structure Models and SPIGOT1907.10348v1 · Andr'e F.T. Martins, Vlad Niculae2019 · 0 citationsarXiv
Sparse Sequence-to-Sequence Models1905.05702v2 · Ben Peters, Vlad Niculae, Andr'e F.T. Martins2019 · 203 citationsarXiv
Learning with Fenchel-Young Losses1901.02324v2 · Mathieu Blondel, Andr'e F. T. Martins, Vlad Niculae2019 · 36 citationsarXiv
Towards Dynamic Computation Graphs via Sparse Latent Structure1809.00653v1 · Vlad Niculae, Andr'e F. T. Martins, Claire Cardie2018 · 21 citationsarXiv
Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms1805.09717v4 · Mathieu Blondel, Andr'e F. T. Martins, Vlad Niculae2018 · 25 citationsarXiv
SparseMAP: Differentiable Sparse Structured Inference1802.04223v2 · Vlad Niculae, Andr'e F. T. Martins, Mathieu Blondel et al.2018 · 66 citationsarXiv
Multi-output Polynomial Networks and Factorization Machines1705.07603v2 · Mathieu Blondel, Vlad Niculae, Takuma Otsuka et al.2017 · 7 citationsarXiv
A Regularized Framework for Sparse and Structured Neural Attention1705.07704v3 · Vlad Niculae, Mathieu Blondel2017 · 74 citationsarXiv
Argument Mining with Structured SVMs and RNNs1704.06869v1 · Vlad Niculae, Joonsuk Park, Claire Cardie2017 · 103 citationsarXiv
Conversational Markers of Constructive Discussions1604.07407v1 · Vlad Niculae, Cristian Danescu-Niculescu-Mizil2016 · 51 citationsarXiv
Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions1602.01103v2 · Chenhao Tan, Vlad Niculae, Cristian Danescu-Niculescu-Mizil et al.2016 · 245 citationsarXiv
Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game1506.04744v1 · Vlad Niculae, Srijan Kumar, Jordan Boyd-Graber et al.2015 · 50 citationsarXivon Valency
API design for machine learning software: experiences from the scikit-learn project1309.0238v1 · Lars Buitinck (ILPS), Gilles Louppe, Mathieu Blondel et al.2013 · 2,120 citationsEuropean Conference on Machine Learning and Principles and Practices of Knowledge Discovery in Databases (2013)
Career total: 104 works. 48 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.