Related papers: Qinco2: Vector Compression and Search with Improve…

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather…

The rapid scaling of Large Language Models (LLMs) elevates inference costs and compounds substantial deployment barriers. While quantization to 8 or 4 bits mitigates this, sub-3-bit methods face severe accuracy, scalability, and efficiency…

Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical…

Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They have become essential tools for researchers and practitioners…

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve…

Powerful large language models (LLMs) are increasingly expected to be deployed with lower computational costs, enabling their capabilities on resource-constrained devices. Post-training quantization (PTQ) has emerged as a star approach to…

Neural audio compression has emerged as a promising technology for efficiently representing speech, music, and general audio. However, existing methods suffer from significant performance degradation at limited bitrates, where the available…

Quantum computers show potential for achieving computational advantage over classical computers, with many candidate applications in combinatorial optimisation. We present an application level benchmarking framework for near-term quantum…

Multi-agent collaborative perception (CP) improves scene understanding by sharing information across connected agents such as autonomous vehicles, unmanned aerial vehicles, and robots. Communication bandwidth, however, constrains…

Quantum Computing aims to streamline machine learning, making it more effective with fewer trainable parameters. This reduction of parameters can speed up the learning process and reduce the use of computational resources. However, in the…

The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into discrete representations suitable for language-based processing. Discrete tokenization,…

Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to…

Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is typically based on a cross-attention module between the…

Vector Quantization (VQ) underpins many modern generative frameworks such as VQ-VAE, VQ-GAN, and latent diffusion models. Yet, it suffers from the persistent problem of codebook collapse, where a large fraction of code vectors remains…

Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a codebook. However, issues such as codebook collapse persist in…

We present a new approach for efficient approximate nearest neighbor (ANN) search in high dimensional spaces, extending the idea of Product Quantization. We propose a two-level product and vector quantization tree that reduces the number of…

This paper shows how to reduce the computational cost for a variety of common machine vision tasks by operating directly in the compressed domain, particularly in the context of hardware acceleration. Pyramid Vector Quantization (PVQ) is…

Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to…

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…