Lyn
CtrlK
  • LYN DOCS
    • Introducing Lyn
    • Our Vision for Video AI and Human-Centric Agential Video
    • Decentralized Video AI Layer
    • Video Agent Generation: Diffusion Based Model
      • Text-to-Speech Synthesis Using Diffusion Bridge Model
      • Real-time Conversational Generation: A Framework for Voice-driven Facial Animation
    • Decentralized Video Agent Applications and Capabilities
  • AI Modeling Research
    • Autoregressive Modeling with Vector Quantization
      • Hierarchical Spatial-Temporal Video Generation Architecture
      • Efficient Autoregressive Video Generation via Token Masking
      • Autoregressive Text-to-Visual Generation via Hybrid Architecture
    • From Video to Movie: Composite Video Editing and RHF for Quality
      • VideoGen-of-Thought
    • Supercharging MLLMs and LVLMs
  • Technical Designs
    • Everlyn's Data Pre-processing Pipeline
      • Towards Intelligent Video Captioning and Annotation
    • $LYN Overview
    • Supplementary Information
      • Definitions
      • References
  • LINKS
    • Lyn Official Site
    • Everlyn Github
    • Lyn Twitter
    • Lyn Discord
Powered by GitBook
On this page
  1. Technical Designs

Supplementary Information

Additional info referenced throughout the Lyn Gitbook.

This section covers diagrams, definitions, references and other supplementary information relevant to the technical research shared throughout the Lyn Gitbook.

Previous$LYN OverviewNextDefinitions

Last updated 10 months ago