CompilerKV uses offline-compiled retention tables as portable priors to achieve SOTA prefill-only KV compression performance across backbones at low token budgets.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A convex KMM-based valuation method that accounts for both target-task alignment and inter-dataset redundancy in gradient space outperforms standard gradient-alignment baselines for LLM post-training data selection.
citing papers explorer
-
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation
CompilerKV uses offline-compiled retention tables as portable priors to achieve SOTA prefill-only KV compression performance across backbones at low token budgets.
-
Convex Dataset Valuation for Post-Training
A convex KMM-based valuation method that accounts for both target-task alignment and inter-dataset redundancy in gradient space outperforms standard gradient-alignment baselines for LLM post-training data selection.