cs.CVNov 15, 2026

Fine-Grained RLAIF for Visual Safety: Learning to Zoom into Hazards for Multimodal Safety Alignment

Authors: Chunxue Xu, Yiwei Wang, Yujun Cai, Songze Li

Organizations: Southeast University, China

Abstract

Recent multimodal safety alignment heavily relies on a text-centric paradigm, assuming risks are explicit in language or globally prominent in images. However, real-world hazards are often visually subtle or peripheral, causing existing models to fail due to their reliance on coarse, global visual representations. In this work, we study fine-grained visual safety alignment and introduce a challenging 1,200-sample benchmark across four domains, where hazards necessitate localized inspection. To address this, we propose Fine-Grained RLAIF (FGR), a reinforcement learning framework that casts image zoom-in as a learnable perception policy. FGR employs a decomposed reward design to jointly align three core safety behaviors: (i) where to look via a visual evidence reward, (ii) when to act via a tool-formatting constraint, and (iii) how to reason via visually grounded safety explanations. FGR achieves accuracy ranging from 86.71% to 93.00%, consistently outperforming strong multimodal and agent-based baselines.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

    Oct 15, 2025Jonghyun Park, Minhyuk Seo, Chaewon Yeo +1Multimodal RobustnessLLM Safety Alignment

  2. ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

    Sep 2, 2026Manan Tayal, Akshay NambiVision-Language-Action ModelsSafe RL

  3. Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images

    Mar 9, 2026Qishun Yang, Shu Yang, Lijie Hu +1VLM Safety AlignmentVLM Safety