Tag
SpaceDG is a large-scale dataset and benchmark that evaluates multimodal language models' spatial reasoning robustness under visual degradations like motion blur and low light, revealing significant performance gaps and showing that fine-tuning on SpaceDG improves robustness without degrading clean image performance.
This paper introduces ROMA, an RL fine-tuning framework that enhances the robustness of multimodal large language models against visual degradations like blur and compression artifacts. It achieves this through a dual-forward-pass strategy and specialized regularization techniques, improving performance on reasoning benchmarks without sacrificing accuracy on clean inputs.