Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
This addresses the practical robustness issue for multimodal AI systems in real-world applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of multimodal large language models struggling with extreme real-world visual degradations by proposing Robust-R1, a framework that explicitly models degradations through structured reasoning chains, achieving state-of-the-art robustness on benchmarks like R-Bench and maintaining superior performance under adversarial degradations.
Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.