Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
- 类型:arxiv
- 标识:2608.18484
- 链接:https://arxiv.org/abs/2608.18484
- 主分类:multimodal
- 形态:method
- 被引:1
- 被引来源:Semantic Scholar
- S2被引:1
- OpenAlex被引:0
- 影响力被引:0
- TLDR:This work introduces SparsePR, a training-free method combining Response-Coupled Partitioning with Probe-Fitted Residual Reconstruction, and finds that partition choice affects both the overlap among grouped queries' preferred supports and how well an affine function of the sparse output can represent the difference between dense and sparse outputs.
- OpenAlex ID:W7203939448
- OpenAlex DOI:10.48550/arxiv.2608.18484
- DOI:10.48550/arxiv.2608.18484
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://arxiv.org/pdf/2608.18484
- OpenAlex更新:2026-08-31
- 副分类:engineering
- 待LLM分类:否
- 标题中文:划分支撑集、重构残差:面向视频生成与世界模型的免训练稀疏注意力
- TLDR中文:本文提出 SparsePR,一种无需训练的方法,将响应耦合划分(Response-Coupled Partitioning)与探针拟合残差重建(Probe-Fitted Residual Reconstruction)相结合,并发现划分方式既影响同一分组内查询偏好支持集之间的重叠程度,也影响稀疏输出的仿射函数对稠密与稀疏输出差异的拟合能力。
- 来源文件:
- /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]