Newest papers

CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion

Kai Zhu, Yintianrun Zhang, Shuwei Jiang, Ruolin Zuo, Yixin Chen, Duomin Wang, Miao Liu, Yin Li, Daquan Zhou, Yiwu Zhong · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29915 · cited by 0 works (OpenAlex) · open-access PDF

Korean

디스플레이 기반 비디오 생성 모델 (VGMs)은 시각적으로 믿을 수있는 비디오를 생산할 수 있지만 카메라의 자아-움직임은 종종 긴 지평을 넘어 드라이브합니다. 카메라 자아-움직임은 프레임 사이의 시야점이 변화하는 방법을 결정하며 일관된 기하학 및 경로를 유지하는 데 필수적입니다. 이 문제를 해결하기 위해 우리는 CausalAlign을 제안합니다. 첫째, 우리는 정의 된 레이어에서 3D 모델 기초를 델타 토큰 공간을 통해 나타내는 표현을 조정함으로써 CausalAlign을 제안합니다. 이 공간은 연속 프레임 사이의 작업을 코딩하여 자아-움직임 역학에 집중할 수 있습니다. 둘째, 우리는 자아-움직임

Machine translation (Meta M2M100); the English original follows.

Abstract

Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint changes between frames and is essential for maintaining consistent geometry and trajectories. To address this problem, we propose CausalAlign, a causal alignment framework with two components. First, we diagnose how precise ego motion is represented, used, and retained within VGMs using linear probes and causal interventions, revealing a rise-and-fall pattern during denoising. Second, we strengthen ego-motion state in VGM by aligning the representations at the identified layers to a 3D foundation model through delta-token space. This space encodes the changes between consecutive frames, allowing the alignment to focus on ego-motion dynamics rather than static scene content. With Wan2.2 fine-tuned on DL3DV and RealEstate10K, CausalAlign can largely improve motion accuracy, geometric consistency, and temporal smoothness, while preserving visual quality. For example, it improves geometric consistency by more than 20% relative to the base model. Moreover, with the fine-tuned VGM, CausalAlign improves the success rate of world action models (WAMs) by 10 points on mobile manipulation tasks of RoboCasa365 benchmark. Overall, CausalAlign improves ego-motion consistency in diffusion-based VGMs and yields noticeable gains in embodied models.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer vision, Artificial intelligence, Consistency (knowledge bases), Computer science, Motion (physics), Focus (optics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange