Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference

Paper recorded by Signals 4 on 2026-10-29 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-29 on arXiv · recorded by Signals 4 on 2026-10-30

Category: cs.CL · 自然语言处理 · first seen 2026-10-30

Abstract

Multi-turn conversations with multimodal large language models (MLLMs) reuse input context, but long multimodal inputs increase time to first token (TTFT). Query-aware hard pruning reduces prefill tokens but permanently excludes information that later questions may require. We propose Raincheck, a framework for deferred multimodal prefill that decouples initial token selection from later informati

Read on arXiv →