Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether noun and verb tokens capture instances and their relations; and semantic propagation, via video-to-video attention, which assesses whether instance bindings persist across frames. We find both effects concentrate in a small subset of interaction-dominant layers. Motivated by this, we introduce MATRIX, a simple and effective regularization that aligns attention in specific layers of video DiTs with multi-instance mask tracks from the MATRIX-11K dataset, enhancing both grounding and propagation. We further propose InterGenEval, an evaluation protocol for interaction-aware video generation. In experiments, MATRIX improves both interaction fidelity and semantic alignment while reducing drift and hallucination. Extensive ablations validate our design choices. Codes and weights will be released.

翻译：视频DiT模型在视频生成领域取得了显著进展，但在建模多实例或主体-物体交互方面仍存在困难。这引出一个关键问题：这些模型如何在内部表征交互？为回答此问题，我们构建了MATRIX-11K数据集——包含交互感知描述与多实例掩码轨迹的视频数据集。基于该数据集，我们开展系统性分析，形式化视频DiT模型的两个视角：语义定位（通过视频-文本注意力，评估名词与动词词元能否捕获实例及其关系）与语义传播（通过视频-视频注意力，评估实例绑定关系能否跨帧持续）。研究发现，这两种效应集中于少量交互主导层。据此，我们提出MATRIX方法——一种简洁有效的正则化策略，将视频DiT特定层中的注意力与MATRIX-11K数据集的多实例掩码轨迹对齐，从而增强定位与传播能力。此外，我们提出交互感知视频生成评估协议InterGenEval。实验表明，MATRIX在提升交互保真度与语义对齐的同时，减少了漂移与幻觉。大量消融实验验证了设计选择的合理性。代码与权重将开源。