The recent emergence of Large Language Models based on the Transformer architecture has enabled dramatic advancements in the field of Natural Language Processing. However, these models have long infer

Previous works on the Recurrent Neural Network-Transducer (RNN-T) models have shown that, under some conditions, it is possible to simplify its prediction network with little or no loss in recognition

State-of-the-art encoder-decoder models (e.g. for machine translation (MT) or speech recognition (ASR)) are constructed and trained end-to-end as an atomic unit. No component of the model can be (re-)

Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decod

We propose a strategic formulation for the joint source-channel coding problem in which the encoder and the decoder are endowed with distinct distortion functions. We provide the solutions in four dif

The fully-convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture mul

We investigate the use of the evolutionary NEAT algorithm for the optimization of a policy network that performs quantum error decoding on the toric code, with bitflip and depolarizing noise, one qubi

Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the encoder of a segmen

Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by thi

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-deco

Continuous monitoring of foot ulcer healing is needed to ensure the efficacy of a given treatment and to avoid any possibility of deterioration. Foot ulcer segmentation is an essential step in wound d

In this work we develop a general tensor network decoder for 2D codes. Specifically, we propose a decoder which approximates maximally likelihood decoding for 2D stabiliser and subsystem codes subject

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by

We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike

Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine. However, there are often external fac

Inspired by holographic codes and tensor-network decoders, we introduce tensor-network stabilizer codes which come with a natural tensor-network decoder. These codes can correspond to any geometry, bu