Zobrazeno 1 - 10
of 2 680
pro vyhledávání: '"Niculae AȘ"'
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-attention in transformers. In this work, we introduce a unified framework-
Externí odkaz:
http://arxiv.org/abs/2411.08590
Autor:
Nachesa, Maya K., Niculae, Vlad
Speech recognition performance varies by language, domain, and speaker characteristics such as accent, and fine-tuning a model on any of these categories may lead to catastrophic forgetting. $k$ nearest neighbor search ($k$NN), first proposed for neu
Externí odkaz:
http://arxiv.org/abs/2410.18850
Autor:
Mohammed, Wafaa, Niculae, Vlad
Large language models (LLM) are increasingly strong contenders in machine translation. We study document-level translation, where some words cannot be translated without context from outside the sentence. We investigate the ability of prominent LLMs
Externí odkaz:
http://arxiv.org/abs/2410.14391
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 the reward augmented decoding (RAD) approach to control the generation from
Externí odkaz:
http://arxiv.org/abs/2407.04615
Surveillance footage represents a valuable resource and opportunities for conducting gait analysis. However, the typical low quality and high noise levels in such footage can severely impact the accuracy of pose estimation algorithms, which are found
Externí odkaz:
http://arxiv.org/abs/2404.12183
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 establishing a link with Fenchel-Young losses. The result is a new fami
Externí odkaz:
http://arxiv.org/abs/2402.13725
Autor:
Mohammed, Wafaa, Niculae, Vlad
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 evaluation, such as contrastive methods, only measure translation accur
Externí odkaz:
http://arxiv.org/abs/2402.01404
Autor:
Tokarchuk, Evgeniia, Niculae, Vlad
Continuous-output neural machine translation (CoNMT) replaces the discrete next-word prediction problem with an embedding prediction. The semantic structure of the target embedding space (i.e., closeness of related words) is intuitively believed to b
Externí odkaz:
http://arxiv.org/abs/2310.20620
Despite the tremendous success of Neural Machine Translation (NMT), its performance on low-resource language pairs still remains subpar, partly due to the limited ability to handle previously unseen inputs, i.e., generalization. In this paper, we pro
Externí odkaz:
http://arxiv.org/abs/2307.12835
Autor:
Niculae, Vlad
In this brief note, we formulate Principal Component Analysis (PCA) over datasets consisting not of points but of distributions, characterized by their location and covariance. Just like the usual PCA on points can be equivalently derived via a varia
Externí odkaz:
http://arxiv.org/abs/2306.13503