AR-Edit: Training-Free Autoregressive Video Editing without Inversion
cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Project page: https://marghovo.github.io/AR-Edit/Abstract
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Qwen2.5-VL Technical Report
- DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
- Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices
- FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers
- FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
- TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion
- StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
- TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space
- TokenFlow: Consistent Diffusion Features for Consistent Video Editing
- Classifier-Free Diffusion Guidance
- SneakPeek: Future-Guided Instructional Streaming Video Generation
- AutoVFX: Physically Realistic Video Editing from Natural Language Instructions
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
- StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
- FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
- StreamDiT: Real-Time Streaming Text-to-Video Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs