SOURCE-LINKED INTELLIGENCE

UniCAR-RL: Seeing Better before Thinking Deeper in Visual Mathematics

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

Multimodal Large Language Models (MLLMs) often struggle with complex mathematical visual reasoning primarily due to a lack of fine-grained perception, causing initial visual hallucinations to directly trigger cascading reasoning failures. In traditional end-to-end reinforcement learning (RL), sparse rewards fail to decouple perceptual hallucinations from logical missteps, hindering targeted perception optimization. Alternatively, fine-tuning with perception-enhanced CoT data incurs high costs and hallucinations. In this paper, we address these challenges by proposing UniCAR-RL, an annotation-f

Read original source ↗ Open in workspace

recordType

paper

region

Global