arXiv (All)
open access
Efficiently Approximating Attention Is Hard
Softmax attention is ubiquitous in modern machine learning, but its quadratic scaling with sequence length makes it costly. To reduce this cost, attention is often approximated with fast algorithms, which incur error but can still perform well in practice and on some inputs. At the same time, the gr
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
- FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention#1050275
- Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusion#1105608
- PARK: Accurate Block Retrieval for Sparse Attention in Video Diffusion Transformers#1143945
- EnhanceGraph: A Continuously Enhanced Graph-based Index for High-dimensional Approximate Nearest Neighbor Search#1122930
- Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks#1071474
Record · ID 1141305
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