KV cache eviction must decide which entries carry information that the rest of the cache can no longer supply. A natural way to estimate this is a learnable gate: give each cached entry a gate on its attention weight and train the gate on the model's own objective. The gate belongs inside the normalizing softmax, where...
Hao Gu, Xin-Tong Yang, Zhi-Wei Li et al.· 0 citations
Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word. This view can confuse what RL discovers with what a model inherits from its training data. We trace the word through open models'training histories, re...
Zhi-Zhuo Kou, Si-Zai Hou, Long Chen et al.· 0 citations
Test-time training is formulated as read-write TTT serving and present RW-TTT, which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner.
