{"ID":2857301,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08964","arxiv_id":"2510.08964","title":"Unleashing Perception-Time Scaling to Multimodal Reasoning Models","abstract":"Recent advances in inference-time scaling, particularly those leveraging reinforcement learning with verifiable rewards, have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs). Inspired by this success, similar strategies have been applied to multimodal reasoning, yet their impact on visual perception remains unclear. To investigate this gap, we introduce DisTANCE, a perception-centric benchmark for visual estimation tasks. Evaluation results show that LVLMs exhibit limited estimation precision, and inference-time scaling offers only marginal gains. We attribute this to the fast perception paradigm of current LVLMs, where visual understanding is treated as a one-shot output without modeling the underlying perceptual process. To address this, we propose Perception-Time Scaling (PTS), a novel paradigm that encourages token-rich perception and decomposes complex perception problems into intermediate tractable sub-problems, thereby enabling perception to align with and benefit from inference-time scaling. Combined with reinforcement learning techniques, PTS significantly improves perception accuracy, raising high-precision performance on DisTANCE from 8.0% to 64.7%, and generalizes well to out-of-domain tasks. Surprisingly, even though PTS data are purely synthetic, combining them with math reasoning data yields consistent gains in both reasoning and real-world perception benchmarks. Further analysis reveals that PTS introduces more perception-related tokens and increases the model's attention to image tokens. Our code and data will be publicly released.","short_abstract":"Recent advances in inference-time scaling, particularly those leveraging reinforcement learning with verifiable rewards, have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs). Inspired by this success, similar strategies have been applied to multimodal reasoning, yet their impac...","url_abs":"https://arxiv.org/abs/2510.08964","url_pdf":"https://arxiv.org/pdf/2510.08964v1","authors":"[\"Yifan Li\",\"Zhenghao Chen\",\"Ziheng Wu\",\"Kun Zhou\",\"Ruipu Luo\",\"Can Zhang\",\"Zhentao He\",\"Yufei Zhan\",\"Wayne Xin Zhao\",\"Minghui Qiu\"]","published":"2025-10-10T03:17:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Language Model\"]","has_code":false}