Paper Detail

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

huggingface Score 7.5

Published 2026-10-21 · First seen 2026-10-27

General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{zhu2026causalalign,
  title = {CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion},
  author = {Kai Zhu and Yintianrun Zhang and Shuwei Jiang and Ruolin Zuo and Yixin Chen and Duomin Wang and Miao Liu and Yin Li and Daquan Zhou and Yiwu Zhong},
  year = {2026},
  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 },
  url = {https://huggingface.co/papers/2610.29915},
  keywords = {diffusion-based video generation models, camera ego-motion, linear probes, causal interventions, denoising, delta-token space, 3D foundation model, geometric consistency, world action models, code available, huggingface daily},
  eprint = {2610.29915},
  archiveprefix = {arXiv},
}

Metadata

{}