MoCoDiff：面向富有表现力动作生成的可控自回归扩散模型
MoCoDiff: A Controllable Autoregressive Diffusion Model for Expressive Motion Generation
把语义、风格、历史三类条件拆成独立的轻量线性调制通路（IMC/TIMC），避免融合条件互相干扰，这一思路可直接迁移到视频生成、人体动作/手势动画等需要长时序一致性与多条件可控的扩散生成任务。
原文依据 IMC is a lightweight, modality-specific linear modulation modules that inject text, style, and history signals through separate conditioning paths.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于扩散的动作生成已取得快速进展，但现有方法在长时程一致性、风格控制与多条件引导方面仍存在困难。一个主要原因是融合式条件设计：语义、风格与时序信号共享同一条通路，导致相互干扰并限制了可控性。我们提出 MoCoDiff，一个引入注入调制控制器（Injection Modulation Controllers，IMC）的可控自回归扩散框架。IMC 是轻量、按模态区分的线性调制模块，通过各自独立的条件通路注入文本、风格与历史信号。IMC 在保持冻结骨干网络简洁性的同时，避免了融合式条件固有的纠缠，从而实现更稳定、更可解释的多条件控制。为进一步增强长程合成能力，我们构建了一个配备时序 IMC（TIMC）的可控自回归扩散模型，将历史作为依赖时间步的校正信号。该可控形式能够主动抑制漂移、强制动作片段之间的平滑过渡，并显著提升长序列上的时序连贯性。实验表明，MoCoDiff 在风格保真度、过渡质量与效率上均达到最优，同时无需重新训练即可支持灵活且可解释的多条件动作合成。
英文原文摘要 1371 字符
Diffusion-based motion generation has advanced rapidly, but current methods still struggle with long-horizon consistency, style control, and multi-condition guidance. A major reason is the fused-conditioning design, where semantic, stylistic, and temporal signals share a single pathway, causing interference and limiting controllability.We propose MoCoDiff, a controlable autoregressive diffusion framework that introduces Injection Modulation Controllers (IMC). IMC is a lightweight, modality-specific linear modulation modules that inject text, style, and history signals through separate conditioning paths. IMC preserves the simplicity of a frozen backbone while avoiding the entanglement inherent to fused conditioning, enabling more stable and interpretable multi-condition control.To further enhance long-range synthesis, we develop a controllable autoregressive diffusion model equipped with Temporal IMC (TIMC), which applies history as a timestep-dependent corrective signal. This controllable formulation actively suppresses drift, enforces smooth transitions across motion segments, and significantly improves temporal coherence over extended sequences.Experiments show that MoCoDiff achieves state-of-the-art style fidelity, transition quality, and efficiency, while supporting flexible and interpretable multi-condition motion synthesis without retraining.