iGVLM: Dynamic Instruction-Guided Vision Encoding for Question-Aware Multimodal Understanding

TL;DR

iGVLM introduces a flexible, instruction-guided visual encoding framework that enhances multimodal understanding by dynamically modulating visual features based on textual instructions, improving reasoning capabilities.

Contribution

The paper presents a novel dual-branch architecture with dynamic feature modulation for instruction-aware visual reasoning in LVLMs.

Findings

Improves instruction sensitivity across diverse language models.

Enhances logical consistency in multi-query, multi-instruction scenarios.

Maintains pre-trained visual priors while enabling task-specific adaptation.

Abstract

Despite the success of Large Vision--Language Models (LVLMs), most existing architectures suffer from a representation bottleneck: they rely on static, instruction-agnostic vision encoders whose visual representations are utilized in an invariant manner across different textual tasks. This rigidity hinders fine-grained reasoning where task-specific visual cues are critical. To address this issue, we propose iGVLM, a general framework for instruction-guided visual modulation. iGVLM introduces a decoupled dual-branch architecture: a frozen representation branch that preserves task-agnostic visual representations learned during pre-training, and a dynamic conditioning branch that performs affine feature modulation via Adaptive Layer Normalization (AdaLN). This design enables a smooth transition from general-purpose perception to instruction-aware reasoning while maintaining the structural integrity and stability of pre-trained visual priors. Beyond standard benchmarks, we introduce MM4, a controlled diagnostic probe for quantifying logical consistency under multi-query, multi-instruction settings. Extensive results show that iGVLM consistently enhances instruction sensitivity across diverse language backbones, offering a plug-and-play paradigm for bridging passive perception and active reasoning.