Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning

arXiv:2507.00748v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning (RL) based post-training strategy for MLLMs in multi-image grounding tasks. We first synthesize high-quality chain-of-thought (CoT) data for cold-start initialization, followed by supervised fine-tuning (SFT) using low-rank adaptation (LoRA). Subsequently, we apply rejection sampling with the merged SFT model to curate reliable RL data and use rule-based RL to guide the model toward optimal reasoning paths. Extensive experiments demonstrate the effectiveness of our approach, achieving +9.04% on MIG-Bench and +4.41% on average across seven out-of-domain benchmarks.

Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?
Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs
POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs

Source: arXiv cs.CV | 2026-04-14

Related