Zobrazeno 1 - 10
of 215
pro vyhledávání: '"Huang, Yixiao"'
The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performance gap. Motivated by this, we examine the benefits of Convolution-Aug
Externí odkaz:
http://arxiv.org/abs/2407.05591
This work studies sparse adversarial perturbations bounded by $l_0$ norm. We propose a white-box PGD-like attack method named sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine sparse-PGD with a black-box a
Externí odkaz:
http://arxiv.org/abs/2405.05075
Transformer-based language models are trained on large datasets to predict the next token given an input sequence. Despite this simple training objective, they have led to revolutionary advances in natural language processing. Underlying this success
Externí odkaz:
http://arxiv.org/abs/2403.08081
Modern language models rely on the transformer architecture and attention mechanism to perform language understanding and text generation. In this work, we study learning a 1-layer self-attention model from a set of prompts and associated output data
Externí odkaz:
http://arxiv.org/abs/2402.13512
Publikováno v:
In International Journal of Rock Mechanics and Mining Sciences September 2024 181
Publikováno v:
In Food Research International September 2024 191
Publikováno v:
In Journal of Food Composition and Analysis August 2024 132
Publikováno v:
In Cleaner Logistics and Supply Chain June 2024 11
Publikováno v:
Phys. Rev. A 102, 043307 (2020)
We study the quantum critical effect enhanced spin-nematic squeezing and quantum Fisher information (QFI) in the spin-1 dipolar atomic Bose-Einstein condensate. We show that the quantum phase transitions can improve the squeezing and QFI in the nearb
Externí odkaz:
http://arxiv.org/abs/2009.09728
Publikováno v:
In Transport Policy July 2023 138:25-44