yzhang2016/video-generation-survey

A reading list of video generation

What it solves

Researchers and developers struggle to keep up with the fast-moving fields of generative AI — new papers, new techniques, and new subfields appear constantly. This project provides a structured, human-curated reading list so you can quickly find relevant publications without endlessly searching.

How it works

The repository is essentially an organized collection of Markdown files, each dedicated to a specific area: video generation, editing in diffusion models, multi-modality understanding and generation, and virtual humans. The main README links to those separate lists. It also includes a link to an external web-based paper visualization tool that lets you explore the collected literature in a graphical way (a screenshot is shown in the README).

Who it’s for

Anyone working in or entering the fields of computer vision, generative models, multimodal AI, or virtual-human research — especially students, academics, and developers who want a curated starting point for literature review.

Highlights

  • Covers several related subfields in one place: video generation, diffusion-editing, multimodal understanding/generation, and virtual humans.
  • Each area has its own dedicated reading list file, making navigation straightforward.
  • Includes a link to an interactive paper visualization tool for exploring the literature.
  • Actively maintained with a news section, suggesting regular updates.

Related

  • Project
    GuanYixuan/pyCapCut

    A Python library for programmatically generating and editing CapCut project drafts, enabling automation of video editing tasks like media placement, text styling, and effect application.

  • Project
    vincentsch/explainroo

    An open-source engine that allows AI agents to generate narrated, animated explainer videos locally by orchestrating text-to-speech, graphics rendering, and automated camera work.

  • Project
    Songssx/ComfyUI-MiniMaxH3-TimelineDirector

    A ComfyUI plugin that provides a visual timeline and orchestration tools for the MiniMax H3 video model, enabling seamless long-form video generation, character replacement, and audio-driven lip sync.

  • Project
    bkingfilm/lapian-notes

    A local-first tool for film analysis that extracts frames and subtitles to create AI-assisted narrative structure trees, plot swimlanes, and emotion curves.