Shadow Mask Distillation enables KV cache compression in RL post-training of LLMs by mitigating amplified off-policy bias that defeats standard importance reweighting.
Sparse-RL: Breaking the memory wall in LLM reinforcement learning via stable sparse rollouts.arXiv preprint arXiv:2401.10079
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
Shadow Mask Distillation enables KV cache compression in RL post-training of LLMs by mitigating amplified off-policy bias that defeats standard importance reweighting.