arXiv (All)
open access
Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
Block-sparse attention accelerates video transformers by grouping queries and keys and computing attention only between selected groups. However, it faces two challenges: (1) queries sharing a block route may attend to different keys; and (2) retaining most attention mass does not necessarily preser
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
- VLM4Cluster: Benchmarking Deep Clustering In the Era of Vision-Language Pre-training#1131849
- Efficient generative adversarial networks using linear additive-attention Transformers#1013372
- Attention re-alignment in multimodal large language models via intermediate-layer guidance.#165723
- CoWindow Attention: Full Causal Coverage Is a Collective Property#1117035
- Recency Forcing: Bridging the Long-Horizon Gap in Autoregressive Video Generation#1014317
Record · ID 1117551
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