AdaV: Adaptive Text-visual Redirection for Vision-Language Models

ACL ARR 2025 February Submission821 Authors

Abstract: The success of Vision-Language Models (VLMs) often relies on high-resolution schemes that preserve image details, while these approaches also generate an excess of visual tokens, leading to a substantial decrease in model efficiency. A typical VLM includes a visual encoder, a text encoder, and an LLM. Recent studies suggest pruning visual tokens based on visual and textual priors to accelerate VLMs without additional training costs. However, these methods often overlook prompt semantics or suffer from biased self-attention in the LLM. Inspired by the efficient mechanisms of the human brain for multimodal understanding, we introduce AdaV, a novel training-free visual token pruning method. By emulating the neural pathways that preprocess visual and auditory information before the reasoning stage, we shift text-guided visual attention redirection to the pre-LLM stage, which reduces biased token pruning and enhances model robustness with a limited visual token budget. A Self-adaptive Cross-modality Attention Redirection (SCAR) module is further proposed that effectively merges and redirects visual attention with text-to-image attention. Extensive experiments on seven challenging benchmarks demonstrate that our AdaV achieves SOTA performance in training-free VLM acceleration and can be plug-and-play on various VLMs. We plan to open-source the code upon publication.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: Multimodality and Language Grounding to Vision, Robotics and Beyond,Efficient/Low-Resource Methods for NLP,Generation

Contribution Types: Model analysis & interpretability, Approaches to low-resource settings, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 821