视频推理模型已准备好走出实验室了吗？

摘要

在现实世界部署中，视觉语言模型常面临天气变化、遮挡和相机运动等干扰。此类条件下，模型的理解与推理能力会显著下降，暴露出洁净受控（即无干扰）评估环境与实际鲁棒性之间的差距。为突破此局限，我们提出ROVA训练框架，通过时空扰动下的鲁棒感知一致性奖励建模来提升模型稳健性。ROVA采用难度感知的在线训练策略，根据模型动态能力优先选择信息量丰富的样本。具体而言，该框架通过自反式评估持续重估样本难度，实现基于鲁棒感知一致性奖励的自适应训练。我们还推出PVRBench新基准测试，通过向具身视频数据集注入真实扰动，评估模型在现实干扰下的准确性与推理质量。我们在PVRBench、UrbanVideo和VisBench上评估ROVA与基线模型，发现开源与专有模型在真实扰动下的准确率与推理能力最大降幅分别达35%和28%。相比基线模型（QWen2.5/3-VL、InternVL2.5、Embodied-R），ROVA有效缓解性能衰退，相对准确率提升至少24%，推理能力提高超9%。这些增益可迁移至洁净标准基准测试，带来持续改进。

English

In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean, controlled (i.e., unperturbed) evaluation settings and real-world robustness. To address this limitation, we propose ROVA, a novel training framework that improves robustness by modeling a robustness-aware consistency reward under spatio-temporal corruptions. ROVA introduces a difficulty-aware online training strategy that prioritizes informative samples based on the model's evolving capability. Specifically, it continuously re-estimates sample difficulty via self-reflective evaluation, enabling adaptive training with a robustness-aware consistency reward. We also introduce PVRBench, a new benchmark that injects real-world perturbations into embodied video datasets to assess both accuracy and reasoning quality under realistic disturbances. We evaluate ROVA and baselines on PVRBench, UrbanVideo, and VisBench, where open-source and proprietary models suffer up to 35% and 28% drops in accuracy and reasoning under realistic perturbations. ROVA effectively mitigates performance degradation, boosting relative accuracy by at least 24% and reasoning by over 9% compared with baseline models (QWen2.5/3-VL, InternVL2.5, Embodied-R). These gains transfer to clean standard benchmarks, yielding consistent improvements.

视频推理模型已准备好走出实验室了吗？

Are Video Reasoning Models Ready to Go Outside?

摘要

Support