SOURCE-LINKED INTELLIGENCE

FlexComp: One Model for Every Ratio in Context Compression

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Soft context compression condenses a context into a few memory tokens that a frozen LLM consumes in place of the raw text, but existing compressors fix the compression ratio at training and inference: each deployed ratio requires a separately trained model, and the chosen ratio is applied uniformly to all inputs, whose actual needs vary drastically. We propose FlexComp, a method-agnostic framework that decouples the ratio from both training and deployment: Matryoshka-style training samples the memory budget $K$ per instance, turning one model into an any-ratio compressor, and the budget is the

Read original source ↗ Open in workspace

recordType

paper

region

Global