VideoEditor-MoE: Scaling Complex Video Editing with Mixture of Experts
cs.CV, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-19
Code: https://github.com/massyzs/Video-Editor-MoE
Terminology
Sources
- Scaling Diffusion Transformers to 16 Billion Parameters
- LoRA: Low-Rank Adaptation of Large Language Models
- Mixtral of Experts
- Adam: A Method for Stochastic Optimization
- Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
- Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing
- Decoupled Weight Decay Regularization
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
- DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
- Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
- Wan: Open and Advanced Large-Scale Video Generative Models
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