Related papers: Unified Spatio-Temporal Token Scoring for Efficien…

Large Vision-Language Models (LVLMs) have recently demonstrated strong multimodal understanding, yet their fine-grained visual perception is often constrained by low input resolutions. A common remedy is to partition high-resolution images…

Long-form video understanding remains challenging for Video Large Language Models (VideoLLMs), as the dense frame sampling introduces massive visual tokens while sparse sampling risks missing critical temporal evidence and leading to LLM…

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rely on Gumbel-Softmax to approximate discrete selection during training. However, the…

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Video Large Language Models have demonstrated strong video understanding capabilities, yet their practical deployment is hindered by substantial inference costs caused by redundant video tokens. Existing pruning techniques fail to…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and discarding low-scoring patches to accelerate LVLM…

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight and token pruning are…

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…

Large Vision Language Models (LVLMs) have achieved significant success across multi-modal tasks. However, the computational cost of processing long visual tokens can be prohibitively expensive on resource-limited devices. Previous methods…

Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs and the high dimensionality of input…

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training…

Recently, multimodal large language models (MM-LLMs) have achieved significant success in various tasks, but their high computational costs limit widespread application. The main computational burden arises from processing concatenated text…

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting…

The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging agentic applications that require processing multi-million…

Recent progress in Multimodal Large Language Models(MLLMs) often use large image tokens to compensate the visual shortcoming of MLLMs, which not only exhibits obvious redundancy but also greatly exacerbates the already high computation.…

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively…

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most existing work estimates visual redundancy using a single…