SOURCE-LINKED INTELLIGENCE

Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increases proportionally to input length. Although model optimization and lossy prompt compression are widely used, these methods still fail to solve the long-context recall problem beyond pretrained and size-constrained context windows. This paper proposes a long-context recall method that maintains near-constant GPU memory usage as context length increases, without additional training. The main idea is to reconstruct facts using parameter activations

Read original source ↗ Open in workspace

recordType

paper

region

Global