Inference Optimal VLMs Need Only One Visual Token but Larger Models
- URL: http://arxiv.org/abs/2411.03312v1
- Date: Tue, 05 Nov 2024 18:54:21 GMT
- Title: Inference Optimal VLMs Need Only One Visual Token but Larger Models
- Authors: Kevin Y. Li, Sachin Goyal, Joao D. Semedo, J. Zico Kolter,
- Abstract summary: Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks.
VLMs are often constrained by high latency during inference due to substantial compute required to process the large number of input tokens.
We take some initial steps towards building approaches tailored for high token compression settings.
- Score: 54.01228554126122
- License:
- Abstract: Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks. However, their real-world deployment is often constrained by high latency during inference due to substantial compute required to process the large number of input tokens (predominantly from the image) by the LLM. To reduce inference costs, one can either downsize the LLM or reduce the number of input image-tokens, the latter of which has been the focus of many recent works around token compression. However, it is unclear what the optimal trade-off is, as both the factors directly affect the VLM performance. We first characterize this optimal trade-off between the number of visual tokens and LLM parameters by establishing scaling laws that capture variations in performance with these two factors. Our results reveal a surprising trend: for visual reasoning tasks, the inference-optimal behavior in VLMs, i.e., minimum downstream error at any given fixed inference compute, is achieved when using the largest LLM that fits within the inference budget while minimizing visual token count - often to a single token. While the token reduction literature has mainly focused on maintaining base model performance by modestly reducing the token count (e.g., $5-10\times$), our results indicate that the compute-optimal inference regime requires operating under even higher token compression ratios. Based on these insights, we take some initial steps towards building approaches tailored for high token compression settings. Code is available at https://github.com/locuslab/llava-token-compression.
Related papers
- A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs [65.00970402080351]
A promising approach to accelerating large vision-language models (VLMs) is using partial information, such as attention maps from specific layers, to assess token importance and prune less essential tokens.
Our study reveals three key insights: (i) Partial attention information is insufficient for accurately identifying critical visual tokens, resulting in suboptimal performance, especially at low token retention ratios; (ii) Global attention information, such as the attention map aggregated across all layers, more effectively preserves essential tokens and maintains comparable performance under aggressive pruning; and (iii) The global attention map aggregated from a small VLM closely resembles that of a large VLM,
arXiv Detail & Related papers (2024-12-04T13:56:44Z) - [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster [26.025260449905577]
Existing methods assess the importance of visual tokens based on the text-visual cross-attentions in large language models (LLMs)
We introduce FasterVLM, a training-free visual token pruning method that evaluates the importance of visual tokens more accurately.
FasterVLM can prune 95% of visual tokens while maintaining 90% of the performance of LLaVA-1.5-7B.
arXiv Detail & Related papers (2024-12-02T18:57:40Z) - Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction [62.8375542401319]
Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone.
The number of vision tokens increases quadratically as the image resolutions, leading to huge computational costs.
We propose a greedy search algorithm (G-Search) to find the least number of vision tokens to keep at each layer from the shallow to the deep.
arXiv Detail & Related papers (2024-11-30T18:54:32Z) - ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models [32.6661928486072]
ATP-LLaVA is a novel approach that adaptively determines instance-specific token pruning ratios for each Large Language Model layer.
Our approach reduces the average token count by 75% while maintaining performance, with only a minimal 1.9% degradation across seven widely used benchmarks.
arXiv Detail & Related papers (2024-11-30T11:42:35Z) - Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
High-resolution images and videos pose a barrier to their broader adoption.
compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.
We introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments.
arXiv Detail & Related papers (2024-11-26T09:36:02Z) - Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models [6.467840081978855]
multimodal large language models (MM-LLMs) have achieved significant success in various tasks.
Main computational burden arises from processingd text and visual tokens.
We propose a dynamic pruning algorithm that identifies the inflection point in the visual CLS token similarity curve.
arXiv Detail & Related papers (2024-09-02T10:49:10Z) - VoCo-LLaMA: Towards Vision Compression with Large Language Models [56.20788367278211]
Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window.
We propose VoCo-LLaMA, the first approach to compress vision tokens using LLMs.
Our method achieves minimal performance loss with a compression ratio of 576$times$, resulting in up to 94.8$%$ fewer FLOPs and 69.6$%$ acceleration in inference time.
arXiv Detail & Related papers (2024-06-18T05:05:12Z) - LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models [35.88374542519597]
Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model.
Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which further increases the number of visual tokens significantly.
We propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs.
arXiv Detail & Related papers (2024-03-22T17:59:52Z) - An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs.
We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
arXiv Detail & Related papers (2024-03-11T14:35:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.