SOURCE-LINKED INTELLIGENCE
A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
Answering questions over real-world documents requires processing long inputs that interleave text with tables. Optical context compression, which represents context as images, promises to reduce token cost, but its effect on table understanding remains unclear. We study pixel-level table compression for question answering over documents with multiple tables, evaluating five VLMs across two benchmarks and five visual-token budgets. Representing tables as images at native resolution matches text in both performance and efficiency, but downscaling them makes models compensate the loss in readabi
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-08-27T10:50:13.000Z
First collected: 2026-09-21T08:51:59.673Z. This is not the publication date.