通过多次采样与答案一致性判断，提升视频关系推理准确率。
Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge
- 多轮随机推理后基于答案一致性聚合结果，提升推理鲁棒性。
- 对置信度低的题目重新筛选候选答案并重看视频，但测试集效果略降。
- 适合需要高精度视频关系理解的场景，尤其关注答案可靠性。
本文介绍我们针对CVPR 2026 VidLLMs挑战赛第二赛道的解决方案。该赛道评估视频中隐含关系的推理能力，要求模型推断未明确呈现的关系。我们提出答案自一致性与边缘触发问题重仲裁框架（ASC-MQRA），一种无需训练的测试时推理方法，基于多模态推理模型构建。核心的ASC组件通过多次随机视频问答运行，并以答案级自一致性聚合结果，显著优于单次推理，构成最终提交方案。进一步研究了MQRA模块，针对第一阶段投票分布显示不确定性的低置信度样本进行条件重仲裁。投票边缘分析表明，低置信度样本中常包含真实答案，因此MQRA通过缩小候选集并仅在保留候选上重看视频来优化。验证集上MQRA进一步提升性能，说明低置信度可作为有效不确定性信号。但在测试集上，MQRA表现略低于ASC，表明重仲裁对触发子集的大小与类别分布敏感。因此，最终提交采用无重仲裁的ASC方案，在验证集上获得72.73%平均准确率和78.34%类别宏平均准确率，在测试集上达81.16%平均准确率和80.91%类别宏平均准确率。本报告详述提示策略、实现设置、消融实验与诊断分析，代码公开于https://github.com/data-analytics-labo/ASC-MQRA。
原文摘要 · Abstract (English)
In this report, we present our solution for Track 2 of the CVPR 2026 VidLLMs Challenge. This track evaluates visual relational reasoning in videos, where models must infer relations that are not always explicitly visible. We propose Answer Self-Consistency with Margin-Triggered Question Re-Arbitration (ASC-MQRA), a training-free test-time reasoning framework built on a multimodal reasoning model. The core ASC component performs multiple stochastic video question-answering runs and aggregates their answer choices through answer-level self-consistency. This substantially improves over single-pass inference and forms our final test submission. We further study MQRA, a conditional re-arbitration module for low-margin examples where the first-stage vote distribution indicates uncertainty. Our vote-margin analysis shows that low-margin examples often retain the ground-truth answer among the top candidates, motivating MQRA to narrow the candidate set and re-watch the video only over the retained candidates. On validation, MQRA further improves over ASC, indicating that low-margin vote distributions can provide a useful uncertainty signal. On test, however, MQRA slightly degrades performance relative to ASC, suggesting that re-arbitration is sensitive to the size and category distribution of the triggered subset. Our final test submission therefore uses ASC without re-arbitration, achieving 72.73 average accuracy and 78.34 category-wise macro average accuracy on validation, and 81.16 average accuracy and 80.91 category-wise macro average accuracy on test. This report details our prompting strategy, implementation setup, ablation studies, and diagnostic analyses. The code is available at https://github.com/data-analytics-labo/ASC-MQRA
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。