用合成数据让小模型读懂超长视频，无需人工标注。
LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
- 分两阶段：先锚定短片段生成偏好三元组，再递归生成多段推理问题
- 仅用16K合成数据，长视频性能超越现有开源模型
- 适合研究长视频理解与低成本训练的学者
我们提出LongVPO，一种新型两阶段直接偏好优化框架，使短上下文视觉语言模型能够在无长视频标注的情况下稳健理解超长视频。第一阶段通过将问题锚定在短片段上，插入干扰项，并应用视觉相似性和问题特异性过滤，缓解位置偏差并确保监督清晰；同时仅评估锚点片段来近似参考模型对长上下文的评分，降低计算开销。第二阶段在长视频上采用递归字幕生成流程，获取场景级元数据，再利用大语言模型构建多段推理问题及劣质回答，通过多段推理任务对齐模型偏好。仅使用16,000个合成样本且无需昂贵的人工标注，LongVPO在多个长视频基准上超越当前最优开源模型，同时保持优秀的短视频表现（如MVBench），提供了一种高效的长视频理解可扩展范式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。