MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration 事件

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration arXiv:2604.14889v2 Announce Type: replace Abstract: While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial memory and inference overhead. Existing approaches such as context compression and multi-token prediction (MTP) improve efficiency from two complementary directions by compressing historical tokens and genera