AI Paper Atlas

Research map / Video / Video generation

AR-Edit: Training-Free Streaming Video Editing without Inversion

Hovhannes Margaryan, Vicky Kalogeiton, Quentin Bammey, Christian Sandor

NeurIPS 2026 · Video › Video generation · approach: Trajectory-guided motion control

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy