1 citations · 1 across the 18 of their papers we have counts for
18 papers
Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
Di Wu, Sergey Troshin, Christof Monz +2
Two forms of test-time scaling for Large Language Models (LLMs) have emerged as effective and widely adopted paradigms: sequential, in which later answer attempts depend on earlier…
How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups
Wafaa Mohammed, Kata Naszadi, Vlad Niculae
Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of tra…
Your Multimodal Speech Model Says I Have a Face for Radio
Maya K. Nachesa, Vlad Niculae, Vagrant Gautam
As large neural models have become better at language tasks, researchers are increasingly building multi- and omnimodal models that handle more modalities of data. One example is t…
AdaSplash-2: Faster Differentiable Sparse Attention
Nuno Gonçalves, Hugo Pitorro, Vlad Niculae +4
Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is -entmax a…
Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
Evgeniia Tokarchuk, Maya K. Nachesa, Sergey Troshin +1
Modern neural translation models based on the Transformer architecture are known for their high performance, particularly when trained on high-resource datasets. A standard next-to…
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
Wafaa Mohammed, Vlad Niculae, Chrysoula Zerva
Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution…
Asking a Language Model for Diverse Responses
Sergey Troshin, Irina Saparina, Antske Fokkens +1
Large language models increasingly rely on explicit reasoning chains and can produce multiple plausible responses for a given context. We study the candidate sampler that produces…
Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
Sergey Troshin, Wafaa Mohammed, Yan Meng +3
Diversity is an essential metric for evaluating the creativity of outputs generated by language models. Temperature-based sampling is a common strategy to increase diversity. Howev…
Angular Dispersion Accelerates -Nearest Neighbors Machine Translation
Evgeniia Tokarchuk, Sergey Troshin, Vlad Niculae
Augmenting neural machine translation with external memory at decoding time, in the form of k-nearest neighbors machine translation (-NN MT), is a well-established strategy for…
How Well Do Vision-Language Models Understand Movies?
Emmanouil Zaranis, António Farinhas, Saul Santos +28
Vision-language models (VLMs) can increasingly handle extended contexts and answer questions about long videos--but can they understand the narrative structure of movies as humans…
Keep your distance: learning dispersed embeddings on
Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae
Learning well-separated features in high-dimensional spaces, such as text or image embeddings, is crucial for many machine learning applications. Achieving such separation can be e…
Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval
Saul Santos, Vlad Niculae, Daniel McNamee +1
Associative memory models, such as Hopfield networks and their modern variants, have garnered renewed interest due to advancements in memory capacity and connections with self-atte…
kNN For Whisper And Its Effect On Bias And Speaker Adaptation
Maya K. Nachesa, Vlad Niculae
Speech recognition performance varies by language, domain, and speaker characteristics such as accent, but fine-tuning a model on any of these categories may lead to catastrophic f…
Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation
Wafaa Mohammed, Vlad Niculae
Large language models (LLMs) are increasingly strong contenders in machine translation. In this work, we focus on document-level translation, where some words cannot be translated…
On the Low-Rank Parametrization of Reward Models for Controlled Language Generation
Sergey Troshin, Vlad Niculae, Antske Fokkens
Language models trained on large amounts of data are known to produce inappropriate content in some cases and require careful tuning to be used in the real world. We revisit an eff…
On Measuring Context Utilization in Document-Level MT Systems
Wafaa Mohammed, Vlad Niculae
Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware e…
Sparse and Structured Hopfield Networks
Saul Santos, Vlad Niculae, Daniel McNamee +1
Modern Hopfield networks have enjoyed recent interest due to their connection to attention in transformers. Our paper provides a unified framework for sparse Hopfield networks by e…
The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation
Evgeniia Tokarchuk, Vlad Niculae
Continuous-output neural machine translation (CoNMT) replaces the discrete next-word prediction problem with an embedding prediction. The semantic structure of the target embedding…