Thursday, June 13, 2024

Artificial Intelligence news

Apple is promising personalized...

At its Worldwide Developer Conference on Monday, Apple for the first time...

What using artificial intelligence...

This story originally appeared in The Algorithm, our weekly newsletter on AI....

The data practitioner for...

The rise of generative AI, coupled with the rapid adoption and democratization...

Five ways criminals are...

Artificial intelligence has brought a big boost in productivity—to the criminal underworld.  Generative...
HomeMachine LearningApplication-Agnostic Language Modeling...

Application-Agnostic Language Modeling for On-Device ASR



On-device automatic speech recognition systems face several challenges compared to server-based systems. They have to meet stricter constraints in terms of speed, disk size and memory while maintaining the same accuracy. Often they have to serve several applications with different distributions at once, such as communicating with a virtual assistant and speech-to-text. The simplest solution to serve multiple applications is to build application-specific (language) models, but this leads to an increase in memory. Therefore, we explore different data- and architecture-driven language modeling…



Article Source link and Credit

Continue reading

Swallowing the Bitter Pill: Simplified Scalable Conformer Generation

We present a novel way to predict molecular conformers through a simple formulation that sidesteps many of the heuristics of prior works and achieves state of the art results by using the advantages of scale. By training a...

KPConvX: Modernizing Kernel Point Convolution with Kernel Attention

In the field of deep point cloud understanding, KPConv is a unique architecture that uses kernel points to locate convolutional weights in space, instead of relying on Multi-Layer Perceptron (MLP) encodings. While it initially achieved success, it has...

Efficient Diffusion Models without Attention

Transformers have demonstrated impressive performance on class-conditional ImageNet benchmarks, achieving state-of-the-art FID scores. However, their computational complexity increases with transformer depth/width or the number of input tokens and requires patchy approximation to operate on even latent input sequences....