arXiv (All)
open access
Transform Trained Transformer for Accelerating Native 4K Video Generation
Native 4K (2176$\times$3840) video generation remains a critical challenge due to the quadratic computational explosion of full-attention as spatiotemporal resolution increases, making it difficult for models to strike a balance between efficiency and quality. This paper proposes a novel Transformer
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
- iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity#1248582
- Decoupling Logical Masks from GPU Execution for Dynamic Block-Sparse Attention#1061497
- Vista4D: Video Reshooting with 4D Point Clouds#131356
- STELLA: A 16nm Spatio-Temporal Elastic Low-Latency CGRA for Multi-Stage Pipelined Applications#1144670
- Scalable FPGA Framework for Real-Time Denoising in High-Throughput Imaging: A DRAM-Optimized Pipeline using High-Level Synthesis#821403
Record · ID 1201952
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