Jul 2026
SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning
SIVA-RL is proposed, a Sensitivity-Invariance Visual Alignment framework that replaces operator-conditioned regularization with sample-wise, outcome-conditioned supervision and yields an 8.79 percentage-point gain on vision-dependent reasoning and up to 14.9% relative overall improvement across all four GRPO- and DAPO-based configurations.
Cheng Tang, Junzhi Ning, Min Cen et al.
· arXiv.org · 0 citations