2025/10/21 by Yanhong Li, Y. Li, Zixuan Lan +4 · 2 voices · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Multimodal Machine Learning Applications #Natural Language Processing Techniques #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2510.18279
openalex publication_date 2025/10/21 · arxiv published 2025/10/21 · arxiv updated 2025/10/22 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/28
Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while preserving performance? In this paper, we show that visual text representations are a practical and surprisingly effective form of input compression for decoder LLMs. We exploit the idea of rendering long text inputs as a single image and provide it directly to the model. This leads to dramatically reduced number of decoder tokens required, offering a new form of input compression. Through experiments on two distinct benchmarks RULER (long-context retrieval) and CNN/DailyMail (document summarization) we demonstrate that this text-as-image method yields substantial token savings (often nearly half) without degrading task performance.