2025
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
ICML 2025poster
Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning---even compared to LLMs on the same tasks presented in text form---giving rise to perceptions of *modality imbalance* or *brittleness*. Towards a syste…