Related papers: Enlarging Context with Low Cost: Efficient Arithme…

Spatially coupled, parallel concatenated codes (SC-PCCs) have been shown to approach channel capacity when decoded using optimal iterative methods. However, under complexity constraints such decoding strategies can result in unacceptable…

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compactly supported stencils and point-wise nonlinearities. Commonly, the convolution operators couple features from all…

Decoding algorithms based on approximate tensor network contraction have proven tremendously successful in decoding 2D local quantum codes such as surface/toric codes and color codes, effectively achieving optimal decoding accuracy. In this…

Semantic segmentation of remotely sensed images plays a crucial role in precision agriculture, environmental protection, and economic assessment. In recent years, substantial fine-resolution remote sensing images are available for semantic…

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs…

Real-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory costs skyrocketing,…

This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model…

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density…

Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence. The context encoding is…

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing…

A transcoding scheme for the High Efficiency Video Coding (HEVC) is proposed that allows any partial frame modification to be followed by a partial re-compression of only the modified areas, while guaranteeing identical reconstruction of…

Data-driven flow-field reconstruction typically relies on autoencoder architectures that compress high-dimensional states into low-dimensional latent representations. However, classical approaches such as variational autoencoders (VAEs)…

Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some…

As the availability of imagery data continues to swell, so do the demands on transmission, storage and processing power. Processing requirements to handle this plethora of data is quickly outpacing the utility of conventional processing…

Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We…

Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy documentation every time the model needs to use the tool,…

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks…

Deep convolutional neural networks (CNNs) are broadly considered to be state-of-the-art generic end-to-end image classification systems. However, they are known to underperform when training data are limited and thus require data…