重新思考位置嵌入：作为多参考与多镜头视频生成的上下文控制器
Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation
将位置编码作为额外的上下文控制信号，在语义检索之外实现 token 级精确匹配，可缓解多参考图像外观高度相似时的参考混淆问题，为多参考、多镜头视频生成中的角色一致性控制提供可复用思路。
原文依据 when reference images exhibit highly similar appearances, the model often suffers from reference confusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期 Sora2 等商业模型在基于多参考角色生成多镜头视频方面展现出可喜进展，然而学术界对该问题的研究仍然有限。本文研究该任务并识别出一个核心挑战：当参考图像外观高度相似时，模型常出现参考混淆，语义相似的 token 会削弱模型检索正确上下文的能力。为此，本文提出 PoCo（位置嵌入作为上下文控制器），在语义检索之外引入位置编码作为额外的上下文控制。通过利用 token 的辅助信息，PoCo 能够在保持隐式语义一致性建模的同时实现精确的 token 级匹配。基于 PoCo，本文构建了一个多参考、多镜头视频生成模型，能够可靠地控制具有极其相似视觉特征的角色。大量实验表明，与多种基线相比，PoCo 提升了跨镜头一致性和参考保真度。
英文原文摘要 1074 字符
Recent proprietary models such as Sora2 demonstrate promising progress in generating multi-shot videos conditioned on multiple reference characters. However, academic research on this problem remains limited. We study this task and identify a core challenge: when reference images exhibit highly similar appearances, the model often suffers from reference confusion, where semantically similar tokens degrade the model's ability to retrieve the correct context. To address this, we introduce PoCo (Position Embedding as a Context Controller), which incorporates position encoding as additional context control beyond semantic retrieval. By employing side information of tokens, PoCo enables precise token-level matching while preserving implicit semantic consistency modeling. Building on PoCo, we develop a multi-reference and multi-shot video generation model capable of reliably controlling characters with extremely similar visual traits. Extensive experiments demonstrate that PoCo improves cross-shot consistency and reference fidelity compared with various baselines.