Preacher: Paper-to-Video Agentic System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jingwei, Yang, Ling, Luo, Hao, Wang, Fan, Li, Hongyan, Wang, Mengdi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912575365578752
author Liu, Jingwei
Yang, Ling
Luo, Hao
Wang, Fan
Li, Hongyan
Wang, Mengdi
author_facet Liu, Jingwei
Yang, Ling
Luo, Hao
Wang, Fan
Li, Hongyan
Wang, Mengdi
contents The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. While state-of-the-art video generation models demonstrate potential, they are constrained by limited context windows, rigid video duration constraints, limited stylistic diversity, and an inability to represent domain-specific knowledge. To address these limitations, we introduce Preacher, the first paper-to-video agentic system. Preacher employs a topdown approach to decompose, summarize, and reformulate the paper, followed by bottom-up video generation, synthesizing diverse video segments into a coherent abstract. To align cross-modal representations, we define key scenes and introduce a Progressive Chain of Thought (P-CoT) for granular, iterative planning. Preacher successfully generates high-quality video abstracts across five research fields, demonstrating expertise beyond current video generation models. Code will be released at: https://github.com/Gen-Verse/Paper2Video
format Preprint
id arxiv_https___arxiv_org_abs_2508_09632
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Preacher: Paper-to-Video Agentic System
Liu, Jingwei
Yang, Ling
Luo, Hao
Wang, Fan
Li, Hongyan
Wang, Mengdi
Computer Vision and Pattern Recognition
Artificial Intelligence
The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. While state-of-the-art video generation models demonstrate potential, they are constrained by limited context windows, rigid video duration constraints, limited stylistic diversity, and an inability to represent domain-specific knowledge. To address these limitations, we introduce Preacher, the first paper-to-video agentic system. Preacher employs a topdown approach to decompose, summarize, and reformulate the paper, followed by bottom-up video generation, synthesizing diverse video segments into a coherent abstract. To align cross-modal representations, we define key scenes and introduce a Progressive Chain of Thought (P-CoT) for granular, iterative planning. Preacher successfully generates high-quality video abstracts across five research fields, demonstrating expertise beyond current video generation models. Code will be released at: https://github.com/Gen-Verse/Paper2Video
title Preacher: Paper-to-Video Agentic System
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.09632