跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 21 天前AI 評分36

Disen-Forcing:解耦自回歸影片擴散中的語義錨定與動態

Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion

AI 導讀

Disen-Forcing 是一種用於自回歸影片擴散模型的蒸餾方法,透過解耦注意力頭的專門分工,改善長時段影片生成的長程一致性與動態表現。研究指出,只有一部分注意力頭負責長程一致性,沿用 frame sink 讓所有注意力頭接觸固定的初始影格,可能令模型在蒸餾時偏向低動態模式。長時段影片生成基準測試顯示,Disen-Forcing 能同時改善一致性與動態表現。

正文

Published on Nov 2

Authors:

,

,

,

,

,

,

Abstract

Disen-Forcing is a distillation-time method for autoregressive video diffusion models that disentangles attention-head specialization to improve long-range consistency and motion dynamics in long-horizon video generation.

Autoregressive video diffusion models (AR-VDMs) enable real-time, long-horizon video generation but degrade rapidly once the inference horizon outruns the training horizon, due to compounding exposure bias. To stabilize long rollouts, recent methods heuristically adopt frame sink, keeping initial frames as a persistent model context, inspired by attention sinks in LLMs. We revisit this design and find that the mechanism by which initial frames stabilize long-range consistency in AR-VDMs is not an LLM-style attention sink; instead, long-range consistency is anchored through a sparse subset of attention heads, while the majority of heads predominantly capture local temporal dynamics. This observation reveals an over-conditioning pathology in existing frame-sink strategies: by universally exposing every head to the pinned initial-frame context, the model becomes prone to collapsing motion toward the low-dynamic modes of the teacher during model distillation. We propose Disen-Forcing, a distillation-time plug-in for AR-VDMs that disentangles and reinforces this head specialization through disentangled context routing and motion-disentangling regularization. On long-horizon video generation benchmarks, Disen-Forcing simultaneously improves long-range consistency and motion dynamics of base AR-VDMs, a trade-off that sink-based methods fail to balance.

View arXiv page View PDF Project page Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.02822 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.02822 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.02822 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co