{"ID":2847174,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00396","arxiv_id":"2511.00396","title":"Saliency-R1: Incentivizing Unified Saliency Reasoning Capability in MLLM with Confidence-Guided Reinforcement Learning","abstract":"Although multimodal large language models (MLLMs) excel in high-level vision-language reasoning, they lack inherent awareness of visual saliency, making it difficult to identify key visual elements. To bridge this gap, we propose Saliency-R1, the first unified MLLM framework that jointly tackles three representative and heterogeneous saliency tasks: Salient Object Detection (SOD), Salient Instance Segmentation (SIS), and Co-salient Object Detection (CoSOD), enhancing the model's capacity for saliency reasoning. We introduce a textual interface with structured tags (\u003crg\u003e, \u003cins\u003e) to encode region- and instance-level referring expressions, enabling a single referring segmenter to produce task-appropriate masks. To train the MLLM efficiently, we propose Confidence-Guided Policy Optimization (CGPO), a novel single-sample reinforcement learning algorithm. CGPO improves on GRPO by replacing group-normalized advantages with a per-sample signal based on reward-confidence discrepancy, thereby reducing computational waste, mitigating signal dilution, and lowering training overhead. Our model exceeds or matches the performance of robust open/closed-source MLLMs and specialized state-of-the-art methods across all three tasks, demonstrating the efficacy of our framework in saliency reasoning.","short_abstract":"Although multimodal large language models (MLLMs) excel in high-level vision-language reasoning, they lack inherent awareness of visual saliency, making it difficult to identify key visual elements. To bridge this gap, we propose Saliency-R1, the first unified MLLM framework that jointly tackles three representative an...","url_abs":"https://arxiv.org/abs/2511.00396","url_pdf":"https://arxiv.org/pdf/2511.00396v3","authors":"[\"Long Li\",\"Shuichen Ji\",\"Ziyang Luo\",\"Zhihui Li\",\"Dingwen Zhang\",\"Junwei Han\",\"Nian Liu\"]","published":"2025-11-01T04:37:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}