Results 31 to 40 of about 500,674 (362)
DistillSpec: Improving Speculative Decoding via Knowledge Distillation [PDF]
International Conference on Learning Representations, 2023 Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according to the target
Yongchao Zhou +7 more
semanticscholar +1 more source
Learning high-accuracy error decoding for quantum processors [PDF]
Nature, 2023 Building a large-scale quantum computer requires effective strategies to correct errors that inevitably arise in physical quantum systems1. Quantum error-correction codes2 present a way to reach this goal by encoding logical information redundantly into ...
Johannes Bausch +17 more
semanticscholar +1 more source
Reduced complexity hard‐ and soft‐input BCH decoding with applications in concatenated codes
IET Circuits, Devices and Systems, 2021 Error correction coding for optical communication and storage requires high rate codes that enable high data throughput and low residual errors. Recently, different concatenated coding schemes were proposed that are based on binary BCH codes with low ...
Jürgen Freudenberger +2 more
doaj +1 more source
A high-performance neuroprosthesis for speech decoding and avatar control
Nature, 2023 A study using high-density surface recordings of the speech cortex in a person with limb and vocal paralysis demonstrates real-time decoding of brain activity into text, speech sounds and orofacial movements.
Sean L. Metzger +14 more
semanticscholar +1 more source
Accelerating Transformer Inference for Translation via Parallel Decoding [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model ...
Andrea Santilli +6 more
semanticscholar +1 more source
Hacia una caracterización de los traductores e intérpretes en Colombia
Ikala: Revista de Lenguaje y Cultura, 2020 El objetivo principal de este estudio, de carácter exploratorio, metodología cuantitativa y enfoque descriptivo, fue realizar una caracterización de los traductores e intérpretes en Colombia.
John Jairo Giraldo-Ortiz +4 more
doaj +1 more source
Frontiers in Human Neuroscience, 2018 Recent research has demonstrated how brain-computer interfaces (BCI) based on auditory stimuli can be used for communication and rehabilitation. In these applications, users are commonly instructed to avoid eye movements while keeping their eyes open ...
David Hübner +5 more
doaj +1 more source
A Robust Screen-Free Brain-Computer Interface for Robotic Object Selection
Frontiers in Robotics and AI, 2020 Brain signals represent a communication modality that can allow users of assistive robots to specify high-level goals, such as the object to fetch and deliver.
Henrich Kolkhorst +9 more
doaj +1 more source
The decoding Library for list decoding [PDF]
ACM Communications in Computer Algebra, 2013 The decoding library is a C library whose main goal is to implement as effi- ciently as possible the Guruswami-Sudan algorithm. It is written in C89 and is stand-alone.
openaire +2 more sources
Statistical Decoding 2.0: Reducing Decoding to LPN
, 2022 The security of code-based cryptography relies primarily on the hardness of generic decoding with linear codes. The best generic decoding algorithms are all improvements of an old algorithm due to Prange: they are known under the name of information set decoders (ISD).
Carrier, Kévin +3 more
openaire +4 more sources