Related papers: Beyond Attention Scores: SVD-Based Vision Token Pr…
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…
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities, yet they encounter significant computational bottlenecks due to the massive volume of visual tokens. Consequently, visual token pruning, which substantially…
The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…
This is a further development of Vision Transformer Pruning via matrix decomposition. The purpose of the Vision Transformer Pruning is to prune the dimension of the linear projection of the dataset by learning their associated importance…
Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such as image captioning and visual question answering. Although…
Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deployment. Existing token pruning methods suffer from a fundamental trade-off: aggressive…
Large models achieve strong performance on Vision-and-Language Navigation (VLN) tasks, but are costly to run in resource-limited environments. Token pruning offers appealing tradeoffs for efficiency with minimal performance loss by reducing…
Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning offers a practical remedy, existing methods still struggle to balance local…
Vision-Language Models (VLMs) have achieved notable success in multimodal tasks but face practical limitations due to the quadratic complexity of decoder attention mechanisms and autoregressive generation. Existing methods like FASTV and…
Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…
Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…
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…
Vision-language models (VLMs) have been widely adopted for 3D question answering (3D QA). In typical pipelines, visual tokens extracted from multiple viewpoints are concatenated with language tokens and jointly processed by a large language…
Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders inference efficiency, and prior studies have shown that many…
Current Video Large Language Models (VideoLLMs) suffer from quadratic computational complexity and key-value cache scaling, due to their reliance on processing excessive redundant visual tokens. To address this problem, we propose SharpV, a…
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…
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…
Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have…
Real-time inference of vision-language-action (VLA) models is essential for robotic control. While visual token pruning has shown strong potential for accelerating inference, most existing methods mainly base pruning decisions on…
Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…