Related papers: Masked Vector Quantization

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping…

Building on our recent research on neural heuristic quantization systems, results on learning quantized motions and resilience to channel dropouts are reported. We propose a general emulation problem consistent with the neuromimetic…

Quantization is an effective method for reducing memory footprint and inference time of Neural Networks, e.g., for efficient inference in the cloud, especially at the edge. However, ultra low precision quantization could lead to significant…

Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remarkable advancements. Improvements in architecture,…

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the…

We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation. This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent space is modeled by a conditional variant of the recently…

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Multi-source user representation learning plays a critical role in enabling personalized services on web platforms (e.g., Alipay). While prior works have adopted late-fusion strategies to combine heterogeneous data sources, they suffer from…

The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent…

Retrieving the most similar vector embeddings to a given query among a massive collection of vectors has long been a key component of countless real-world applications. The recently introduced Retrieval-Augmented Generation is one of the…

Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge…

Foundation models in language and vision benefit from a unified discrete token interface that converts raw inputs into sequences for scalable pre-training and inference. For graphs, an effective tokenizer should yield reusable discrete…

In this paper, we reveal that artificial neural network (ANN) assisted multiple-input multiple-output (MIMO) signal detection can be modeled as ANN-assisted lossy vector quantization (VQ), named MIMO-VQ, which is basically a joint…

In this paper, we propose a generalizable mixed-precision quantization (GMPQ) method for efficient inference. Conventional methods require the consistency of datasets for bitwidth search and model deployment to guarantee the policy…

Post-training quantization (PTQ) has emerged as an effective technique for compressing large models and accelerating inference without retraining. While PTQ has been extensively studied in large language models (LLMs), its application to…

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements. Recent Vector-Quantized image…

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain…

Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs,…

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…