Related papers: A Novel Reconfigurable Vector-Processed Interleavi…

Diffusion Language Models (DLMs) have recently emerged as a strong alternative to autoregressive language models (LMs). DLMs offer comparable accuracy with faster inference speed via parallel decoding. However, standard DLM decoding…

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and…

We present a novel algorithm that solves the turbo code LP decoding problem in a fininte number of steps by Euclidean distance minimizations, which in turn rely on repeated shortest path computations in the trellis graph representing the…

In this paper a discussion of the detailed operation of the interleavers used by the turbo codes defined on the telecommunications standards cdma2000 (3GPP2 C.S0024-B V2.0) and W-CDMA (3GPP TS 25.212 V7.4.0) is presented. Differences in the…

Tensor decomposition (TD) is an important method for extracting latent information from high-dimensional (multi-modal) sparse data. This study presents a novel framework for accelerating fundamental TD operations on massively parallel GPU…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

The error-pattern correcting code (EPCC) is incorporated in the design of a turbo equalizer (TE) with aim to correct dominant error events of the inter-symbol interference (ISI) channel at the output of its matching Viterbi detector. By…

In this paper, a dual learning-based method in intra coding is introduced for PCS Grand Challenge. This method is mainly composed of two parts: intra prediction and reconstruction filtering. They use different network structures, the neural…

Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature…

By concatenating a polar transform with a convolutional transform, polarization-adjusted convolutional (PAC) codes can reach the dispersion approximation bound in certain rate cases. However, the sequential decoding nature of traditional…

A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding…

This paper investigates low-latency streaming codes for a three-node relay network. The source transmits a sequence of messages (streaming messages) to the destination through the relay between them, where the first-hop channel from the…

This paper studies the complicated interplay of the completion time (as a measure of throughput) and the decoding delay performance in instantly decodable network coded (IDNC) systems over wireless broadcast erasure channels with memory,…

In this paper, we propose to enhance the performance of the sum-product algorithm (SPA) by interleaving SPA iterations with a random local graph update rule. This rule is known as edge local complementation (ELC), and has the effect of…

Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce…

The demand for efficient multi-rate encoding techniques has surged with the increasing prevalence of ultra-high-definition (UHD) video content, particularly in adaptive streaming scenarios where a single video must be encoded at multiple…

We consider streaming data transmission over a discrete memoryless channel. A new message is given to the encoder at the beginning of each block and the decoder decodes each message sequentially, after a delay of $T$ blocks. In this…

A novel adaptive binary decoding algorithm for LDPC codes is proposed, which reduces the decoding complexity while having a comparable or even better performance than corresponding non-adaptive alternatives. In each iteration the variable…

Random linear network coding (RLNC) in theory achieves the max-flow capacity of multicast networks, at the cost of high decoding complexity. To improve the performance-complexity tradeoff, we consider the design of sparse network codes. A…

Tucker decomposition is one of the SOTA CNN model compression techniques. However, unlike the FLOPs reduction, we observe very limited inference time reduction with Tucker-compressed models using existing GPU software such as cuDNN. To this…