LongVPO:从锚定线索到自我推理的长视频偏好优化
LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
AI总结:
LongVPO通过两阶段直接偏好优化框架,利用合成数据和递归标注流程,在无需长视频标注的情况下实现高效长视频理解,优于现有开源模型并保持短视频性能。
摘要:
我们提出了LongVPO,一种新颖的两阶段直接偏好优化框架,使短上下文的视觉-语言模型能够鲁棒地理解超长视频,而无需任何长视频标注。在第一阶段,我们通过将问题锚定到单个短片段、将干扰项交错插入,并应用视觉相似性和问题特定性过滤来缓解位置偏差,确保监督的明确性。我们还通过仅评估锚定片段来近似参考模型在长上下文中的评分,从而减少计算开销。在第二阶段,我们采用递归标注流程对长视频生成场景级元数据,然后使用大型语言模型生成多段推理查询和不受欢迎的响应,通过多段推理任务对模型的偏好进行对齐。仅使用16K合成示例和没有昂贵的人工标签,LongVPO在多个长视频基准上优于当前最先进的开源模型,同时保持强大的短视频性能(例如在MVBench上),提供了一种可扩展的高效长视频理解范式。
英文摘要:
We present LongVPO, a novel two-stage Direct Preference Optimization framework that enables short-context vision-language models to robustly understand ultra-long videos without any long-video annotations. In Stage 1, we synthesize preference triples by anchoring questions to individual short clips, interleaving them with distractors, and applying visual-similarity and question-specificity filtering to mitigate positional bias and ensure unambiguous supervision. We also approximate the reference model's scoring over long contexts by evaluating only the anchor clip, reducing computational overhead. In Stage 2, we employ a recursive captioning pipeline on long videos to generate scene-level metadata, then use a large language model to craft multi-segment reasoning queries and dispreferred responses, aligning the model's preferences through multi-segment reasoning tasks. With only 16K synthetic examples and no costly human labels, LongVPO outperforms the state-of-the-art open-source models on multiple long-video benchmarks, while maintaining strong short-video performance (e.g., on MVBench), offering a scalable paradigm for efficient long-form video understanding.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。