{"ID":2849437,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22970","arxiv_id":"2510.22970","title":"VALA: Learning Latent Anchors for Training-Free and Temporally Consistent","abstract":"Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to maintain temporal consistency during DDIM inversion, which introduces manual bias and reduces the scalability of end-to-end inference. In this paper, we propose~\\textbf{VALA} (\\textbf{V}ariational \\textbf{A}lignment for \\textbf{L}atent \\textbf{A}nchors), a variational alignment module that adaptively selects key frames and compresses their latent features into semantic anchors for consistent video editing. To learn meaningful assignments, VALA propose a variational framework with a contrastive learning objective. Therefore, it can transform cross-frame latent representations into compressed latent anchors that preserve both content and temporal coherence. Our method can be fully integrated into training-free text-to-image based video editing models. Extensive experiments on real-world video editing benchmarks show that VALA achieves state-of-the-art performance in inversion fidelity, editing quality, and temporal consistency, while offering improved efficiency over prior methods.","short_abstract":"Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to maintain temporal consistency during DDIM inversion, which introduces manual bias and...","url_abs":"https://arxiv.org/abs/2510.22970","url_pdf":"https://arxiv.org/pdf/2510.22970v1","authors":"[\"Zhangkai Wu\",\"Xuhui Fan\",\"Zhongyuan Xie\",\"Kaize Shi\",\"Longbing Cao\"]","published":"2025-10-27T03:44:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}