# BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation

arXiv: https://arxiv.org/abs/2605.27067 · HTML: https://mlsanity.com/paper/2605.27067/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 27 of 27)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [TransNet V2: An effective deep network architecture for fast shot transition detection](https://mlsanity.com/paper/2008.04838/) (2020)
- [CLIP-It! Language-Guided Video Summarization](https://mlsanity.com/paper/2107.00650/) (2021)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Summarizing Videos with Attention](https://mlsanity.com/paper/1812.01969/) (2018)
- [LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing](https://mlsanity.com/paper/2402.10294/) (2024)
- [VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling](https://mlsanity.com/paper/2406.04321/) (2024)
- [All-In-One Metrical And Functional Structure Analysis With Neighborhood Attentions on Demixed Audio](https://mlsanity.com/paper/2307.16425/) (2023)
- [FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces](https://mlsanity.com/paper/2501.12909/) (2025)
- [Movie Summarization via Sparse Graph Construction](https://mlsanity.com/paper/2012.07536/) (2020)
- [EditDuet: A Multi-Agent System for Video Non-Linear Editing](https://mlsanity.com/paper/2509.10761/) (2025)
- [Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition](https://mlsanity.com/paper/2111.08774/) (2021)
- [Towards Automated Movie Trailer Generation](https://mlsanity.com/paper/2404.03477/) (2024)
- [DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing](https://mlsanity.com/paper/2604.04875/) (2026)
- [From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations](https://mlsanity.com/paper/2505.12237/) (2025)
- [Prompt-Driven Agentic Video Editing System: Autonomous Comprehension of Long-Form, Story-Driven Media](https://mlsanity.com/paper/2509.16811/) (2025)
- [CutClaw: Agentic Hours-Long Video Editing via Music Synchronization](https://mlsanity.com/paper/2603.29664/) (2026)
- [A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation](https://mlsanity.com/paper/2604.10456/) (2026)
- [An Inverse Partial Optimal Transport Framework for Music-guided Movie Trailer Generation](https://mlsanity.com/paper/2407.19456/) (2024)
- [Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation](https://mlsanity.com/paper/2512.04426/) (2025)
- [Trailer Reimagined: An Innovative, Llm-DRiven, Expressive Automated Movie Summary framework (TRAILDREAMS)](https://mlsanity.com/paper/2602.02630/) (2026)

## Built on by (most cited first, 1 of 1)

- [Unified Agentic Video Editing Across Levels of Complexity and Creativity](https://mlsanity.com/paper/2609.12769/) (2026)

## Abstract (arXiv)

Automatic movie trailer generation must select shots from a full-length film and synchronize them with background music. Existing methods either relegate music alignment to post-processing or enforce rigid one-to-one shot-music mappings, overlooking that professional editing rhythm is elastic: rapid cuts accompany high-energy passages while sustained shots span quieter bars. We introduce BEAT, a framework that addresses this gap with two core components: MuVA, a compact music-visual alignment encoder trained with Sinkhorn-regularized two-stage learning, and Bar-DP, an energy-adaptive dynamic programming algorithm that produces elastic many-to-one alignments following musical dynamics. These components are integrated into a five-phase agentic pipeline that grounds the core alignment in learned cross-modal features while coordinating higher-level creative decisions through structured text signals. To support comprehensive evaluation, we also introduce TrailerArena, a benchmark with 20+ metrics across four complementary dimensions. On TrailerArena, BEAT achieves state-of-the-art performance across shot selection, ordering, and perceptual quality, while producing fully composed trailers end-to-end.