04:00
2026-08-04
arxiv.org
artificial-intelligence
Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference
A new arXiv study (2608.00077v1) audits visual-token pruning in OCR-critical multimodal large language models (MLLMs), finding that accuracy alone misses failures where correct answers lack local toke…