no code implementations • 1 Feb 2024 • Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
The query, key, and value are often intertwined and generated within those blocks via a single, shared linear transformation.
no code implementations • 17 May 2023 • Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
The manifold hypothesis posits that high-dimensional data often lies on a lower-dimensional manifold and that utilizing this manifold as the target space yields more efficient representations.
1 code implementation • 13 Mar 2023 • Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
Contrastive methods have performed better than generative models in previous state representation learning research.
1 code implementation • 30 Jun 2022 • Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks.
no code implementations • 2 Mar 2022 • Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
In this article, we further explore the possibility of replacing priors with noise and sample the noise from a Gaussian distribution to introduce more diversity into this algorithm.
no code implementations • 28 Sep 2021 • Shilun Lin, Wenchao Su, Li Meng, Fenglong Xie, Xinhui Li, Li Lu
Thirdly, a duration predictor instead of an attention model that connects the above hybrid encoder and decoder.
no code implementations • 28 Jun 2021 • Li Meng, Anis Yazidi, Morten Goodwin, Paal Engelstad
Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a combination of Double Q-learning and Dueling Q-learning.
no code implementations • 30 Jan 2021 • Shilun Lin, Fenglong Xie, Li Meng, Xinhui Li, Li Lu
In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application.
2 code implementations • 31 Oct 2018 • Daniel Sáez Trigueros, Li Meng, Margaret Hartnett
Starting in the seventies, face recognition has become one of the most researched topics in computer vision and biometrics.
no code implementations • 31 Oct 2018 • Daniel Sáez Trigueros, Li Meng, Margaret Hartnett
In this paper we investigate the feasibility of using synthetic data to augment face datasets.
no code implementations • 27 Jun 2018 • Lin Yibo, Li Meng, Watanabe Yuki, Kimura Taiki, Matsunawa Tetsuaki, Nojima Shigeki, Pan David Z.
Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models.
no code implementations • 25 Jul 2017 • Daniel Sáez Trigueros, Li Meng, Margaret Hartnett
Despite the recent success of convolutional neural networks for computer vision applications, unconstrained face recognition remains a challenge.