arXiv (All)
open access
SLA2: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training
Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or linear branch based on attention-weight magnitude, which can
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
- RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion Transformers#987872
- Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation#1218564
- WaveAlign: Cache-Aware Query-Row Scheduling for Sparse Attention in Long-Video Generation#1129430
- WaveAlign: Cache-Aware Query-Row Scheduling for Sparse Attention in Long-Video Generation#1108706
- Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers#1387264
Record · ID 1389197
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