Related papers: FlowCut: Rethinking Redundancy via Information Flo…

This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic…

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime…

Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existing vision token reduction methods alleviate this burden, but they unintentionally…

Vision-language models (VLMs) rely on long visual token sequences for visual understanding, making the prefill stage expensive in both computation and memory. Most existing pruning methods follow an absolute-ranking paradigm, assigning…

Large language models (LLMs) have proven to be highly effective across various natural language processing tasks. However, their large number of parameters poses significant challenges for practical deployment. Pruning, a technique aimed at…

Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning…

While significant advancements have been made in compressed representations for text embeddings in large language models (LLMs), the compression of visual tokens in multi-modal LLMs (MLLMs) has remained a largely overlooked area. In this…

Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial…

Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos. Due to the rich visual information, a single image can generate thousands of vision tokens, leading…

Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis…

We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lead to significant performance drop when applied to VLMs.…

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to…

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…

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…

This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less…

Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune…

Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by…

Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities. However, their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic…

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…