Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with three key contributions. First, we establish the first comprehensive OMTG benchmark, introducing Count Accuracy (C-Acc) and Effective Temporal F1 (EtF1) as evaluation metrics. Second, we curate a high-quality OMTG dataset comprising 56k samples through a sophisticated construction pipeline. Third, we develop novel temporal and caption reward functions specifically designed for OMTG. In particular, the caption reward leverages Chain-of-Thought reasoning over dense video captions to explicitly guide policy optimization toward both preciseness and completeness. Extensive experiments show our model achieves a new state-of-the-art EtF1 of 43.65\% on OMTG Bench, outperforming Gemini 2.5 Pro and Seed-1.8 by 15.85\% and 15.61\%, respectively.

翻译：时间定位旨在定位与文本查询相对应的视频片段。以往研究主要集中在单片段检索上。然而，现实场景中常需为单个查询定位多个不连续的片段——我们将其称为一对多时间定位。针对一对一设置优化的现有先进多模态大语言模型在此背景下表现不佳，由于缺乏事件基数感知，往往产生接近零的分数。为弥补这一差距，我们提出系统解决方案，包含三项关键贡献。首先，我们建立了首个全面的OMTG基准，引入计数准确率（C-Acc）和有效时间F1值（EtF1）作为评估指标。其次，我们通过精细构建流程，整理出包含5.6万样本的高质量OMTG数据集。第三，我们开发了专门针对OMTG设计的新型时间与字幕奖励函数。具体而言，字幕奖励利用密集视频字幕上的思维链推理，明确引导策略优化走向精确性与完整性。大量实验表明，我们的模型在OMTG基准上取得了43.65%的最优EtF1值，分别超越Gemini 2.5 Pro和Seed-1.8达15.85%和15.61%。