TimeLens2：基於多模態大語言模型的通用影片時間定位

摘要

视频多模态大语言模型（MLLMs）能够描述视频中发生的内容，但很少能识别出支撑证据出现的时间位置。我们研究通用型视频时间定位任务，即单一模型需预测跨不同视频长度、领域、查询形式和视角的可变基数证据区间集合。现有训练策略与此集合值任务存在错位：长视频的标注常依赖于脆弱的单次标注，而强化学习奖励要么无法区分不相交预测，要么需要脆弱的片段匹配。TimeLens2将时间证据视为区间集合进行全程监督与优化。TimeLens2-93K通过基于描述的提议生成、独立定位、跨模型共识、语义验证及边界精修构建了可靠的多跨度监督。我们的时间Wasserstein奖励在合并区间支撑集上的均匀分布间计算精确的一维W₁距离，提供稠密且无需匹配的反馈，适用于不等基数与等效碎片化场景；时间IoU则以精确重叠反馈作为补充。在七个基准测试中，TimeLens2-2B在每个基准上的表现均优于所有同规模基线，而4B和8B变体则达到最先进水平，超越了参数量高达397B的开源模型。2B、4B和8B变体相较于其Qwen3-VL骨干网络，分别提升了14.2、13.0和18.1 mIoU个点。

English

Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal grounding, in which one model predicts a variable-cardinality set of evidence intervals across video lengths, domains, query forms, and viewpoints. Existing training strategies are misaligned with this set-valued task: long-video labels often rely on brittle one-pass annotation, while reinforcement-learning rewards either fail to distinguish non-overlapping predictions or require fragile segment matching. TimeLens2 treats temporal evidence as an interval set throughout supervision and optimization. TimeLens2-93K constructs reliable multi-span supervision through caption-derived proposals, independent localization, cross-agent consensus, semantic verification, and boundary refinement. Our temporal Wasserstein reward computes exact one-dimensional \(W_1\) between uniform distributions over merged interval supports, providing dense, matching-free feedback under unequal cardinalities and equivalent fragmentation; temporal IoU complements it with precise-overlap feedback. Across seven benchmarks, TimeLens2-2B outperforms all size-matched baselines on every benchmark, while the 4B and 8B variants achieve state-of-the-art performance, surpassing open-source models with up to 397B parameters. The 2B, 4B, and 8B variants improve over their Qwen3-VL backbones by 14.2, 13.0, and 18.1 mIoU points, respectively.