Clips2Story: Training-Free Video Storyboarding and Editing Using Multimodal Retrieval-Embedded Generation
cs.CV, cs.AI, cs.LG, cs.MM
Submitted: 2026-11-04
Updated: 2026-11-04
Project page: https://junnuo3.github.io/clips2story/3
Terminology
Sources
- Qwen2.5-VL Technical Report
- WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
- VideoPoet: A Large Language Model for Zero-Shot Video Generation
- LLM-grounded Video Diffusion Models
- VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- TeaserGen: Generating Teasers for Long Documentaries
- REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
- Qwen3 Technical Report
- Vidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video
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