Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).

翻译：当前最强大的视频语言模型（VLM）仍为闭源。最强的开源权重模型要么依赖从闭源VLM生成的合成数据进行蒸馏训练，要么未公开其训练数据或方法。因此，开源社区缺乏改进现有最先进视频（及图像）语言模型的基础。关键在于，许多下游应用不仅需要高级视频理解能力，还需要定位能力——无论是通过指向还是像素级追踪。即使是闭源模型也缺乏此功能。我们提出了Molmo2，这是一个新的VLM系列，在开源模型中达到最先进水平，并在单图像、多图像及视频任务中的指向驱动定位方面展现出卓越的新能力。我们的核心贡献是收集了7个新的视频数据集和2个多图像数据集，包括用于预训练的高细节视频描述数据集、用于微调的自由形式视频问答数据集、包含复杂查询的新目标追踪数据集，以及创新的视频指向数据集，所有数据均未使用闭源VLM进行收集。我们还提出了利用高效打包和消息树编码方案的数据训练方法，并证明视觉令牌的双向注意力机制与新颖的令牌权重策略能提升性能。我们最先进的80亿参数模型在短视频、计数和描述任务上优于同类开源权重与数据模型，并在长视频任务上具有竞争力。在视频定位任务中，Molmo2显著优于Qwen3-VL等现有开源模型（视频计数准确率35.5对29.6），并在部分任务上超越Gemini 3 Pro等闭源模型（视频指向F1分数38.4对20.0，视频追踪J&F分数56.2对41.1）。