NSA is a hardware-aligned sparse attention mechanism that enables end-to-end trainable long-context modeling by combining coarse token compression with fine-grained selection.
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation , booktitle =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
STORM manages agent states in shared workspaces to ensure consistent views and resolve conflicting edits at write time, outperforming git-worktree baselines by +18.7 on Commit0-Lite and +1.4 on PaperBench while reaching combined scores of 87.6 and 78.2.
citing papers explorer
-
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
NSA is a hardware-aligned sparse attention mechanism that enables end-to-end trainable long-context modeling by combining coarse token compression with fine-grained selection.
-
Multi-agent Collaboration with State Management
STORM manages agent states in shared workspaces to ensure consistent views and resolve conflicting edits at write time, outperforming git-worktree baselines by +18.7 on Commit0-Lite and +1.4 on PaperBench while reaching combined scores of 87.6 and 78.2.