arXiv (All)
open access
Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training
Natively training joint video-audio generation models at higher resolutions empowers them to learn richer visual details and sharper motion dynamics. However, full attention incurs quadratic cost and, as resolution increases, spreads attention over increasingly redundant tokens, diluting learning si
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training#1221431
- DriftAudio: Marginal Drifting for Distributional Post-Training of One-Step Text-to-Audio Generators#1064142
- vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes#1011778
- vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes#965389
- Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong Baseline#1129983
Record · ID 1201429
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive