# VALA: Learning Latent Anchors for Training-Free and Temporally Consistent

arXiv: https://arxiv.org/abs/2510.22970 · HTML: https://mlsanity.com/paper/2510.22970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models](https://mlsanity.com/paper/2312.04524/) (2023)
- [VidToMe: Video Token Merging for Zero-Shot Video Editing](https://mlsanity.com/paper/2312.10656/) (2023)
- [COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing](https://mlsanity.com/paper/2406.08850/) (2024)
- [SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer](https://mlsanity.com/paper/2412.10958/) (2024)
- [VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing](https://mlsanity.com/paper/2502.17258/) (2025)
- [Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices](https://mlsanity.com/paper/2405.12211/) (2024)
- [Object-Centric Diffusion for Efficient Video Editing](https://mlsanity.com/paper/2401.05735/) (2024)
- [Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion](https://mlsanity.com/paper/2403.14617/) (2024)
- [A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing](https://mlsanity.com/paper/2312.05856/) (2023)
- [DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency](https://mlsanity.com/paper/2408.07481/) (2024)

## Abstract (arXiv)

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~VALA (Variational Alignment for Latent Anchors), 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.