Related papers: VEQ: Modality-Adaptive Quantization for MoE Vision…

Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing compute and memory demands, especially as models scale to…

Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…

This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth $\leq2$ bits) we can use for higher efficiency. Our work is motivated by the substantial…

Mixture-of-Experts (MoE) based large language models (LLMs) offer strong performance but suffer from high memory and computation costs. Weight binarization provides extreme efficiency, yet existing binary methods designed for dense LLMs…

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each…

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…

Quantization is a key method for deploying deep neural networks on edge devices with limited memory and computation resources. Recent improvements in Post-Training Quantization (PTQ) methods were achieved by an additional local optimization…

As large language models (LLMs) become more prevalent, there is a growing need for new and improved quantization methods that can meet the computationalast layer demands of these modern architectures while maintaining the accuracy. In this…

Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL…

Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on…

Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or…

Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…

Vector-Quantized Variational Autoencoders (VQ-VAE)[1] provide an unsupervised model for learning discrete representations by combining vector quantization and autoencoders. In this paper, we study the use of VQ-VAE for representation…

Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning. In contrast, visual modality is inherently continuous and high-dimensional, which…

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across multi-modal tasks by scaling model size and training data. However, these dense LVLMs incur significant computational costs and motivate the exploration of…

Quantization is one of the most effective methods to compress neural networks, which has achieved great success on convolutional neural networks (CNNs). Recently, vision transformers have demonstrated great potential in computer vision.…