Related papers: METEOR: Multi-Encoder Collaborative Token Pruning …

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token…

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to…

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

Recent advancements in Vision-Language Models (VLMs) enable large language models (LLMs) to process high-resolution images, significantly improving real-world multimodal understanding. However, this capability introduces a large number of…

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Vision Transformers (ViTs) have emerged as powerful backbones in computer vision, outperforming many traditional CNNs. However, their computational overhead, largely attributed to the self-attention mechanism, makes deployment on…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

Multimodal Large Language Models (MLLMs) typically process a large number of visual tokens, leading to considerable computational overhead, even though many of these tokens are redundant. Existing visual token pruning methods primarily…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Multimodal Large Language Models (MLLMs) deliver strong vision-language performance but at high computational cost, driven by numerous visual tokens processed by the Vision Transformer (ViT) encoder. Existing token pruning strategies are…

While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies.…

Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained…

We present MMCORE, a unified framework designed for multimodal image generation and editing. MMCORE leverages a pre-trained Vision-Language Model (VLM) to predict semantic visual embeddings via learnable query tokens, which subsequently…

Current VLM-based VQA methods often process entire images, leading to excessive visual tokens that include redundant information irrelevant to the posed question. This abundance of unnecessary image details creates numerous visual tokens,…

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token pruning method applied before the vision-language…

Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted…