shadow-mask-distillation

Tag

Cards List
#shadow-mask-distillation

How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment

arXiv cs.LG · 2026-05-11 Cached

This paper proposes Shadow Mask Distillation (SMD) to solve the off-policy bias caused by KV cache compression during reinforcement learning post-training for large language models. It introduces a mechanism that ensures on-policy alignment and improves memory efficiency for long-context reasoning tasks.

0 favorites 0 likes
← Back to home

Submit Feedback