Research map / Video / Video generation
AR-Edit: Training-Free Streaming Video Editing without Inversion
Hovhannes Margaryan, Vicky Kalogeiton, Quentin Bammey, Christian Sandor
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes AR-Edit, a training-free method for streaming video editing without inversion, built on analysis of self-attention dynamics in DMD-distilled autoregressive video diffusion models.
Problem
Real-time video editing of a stream without access to future frames; existing training-free video editing methods assume full offline access, while streaming methods require extra training or support only specific editing techniques.
Approach
Analyzes the self-attention dynamics of DMD-distilled autoregressive video diffusion models to enable streaming editing without inversion and without additional training, removing the limitation of prior streaming approaches to specific editing techniques.
Experimental setup
Builds on: DMD (distribution matching distillation)
Closest papers by meaning
- AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion (CVPR 2025 · similarity 0.88)
- FADE: Frequency-Aware Diffusion Model Factorization for Video Editing (CVPR 2025 · similarity 0.87)
- AdaState: Self-Evolving Anchors for Streaming Video Generation (NeurIPS 2026 · similarity 0.87)
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models (CVPR 2025 · similarity 0.87)
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion (NeurIPS 2025 · similarity 0.86)
- Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
