arXiv (All)
open access
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study three key questions: (1) when do the two common masking rule
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
- Accelerating Masked Image Generation by Learning Controlled Latent Dynamics#925937
- Denoising Diffusion Generative Models Secretly Calculate Attentions#820887
- Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning#1049738
- ClusterAttention: A training-free speedup of bidirectional attention#1141634
- CoWindow Attention: Full Causal Coverage Is a Collective Property#1117035
Record · ID 1389199
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