CVJul 29

Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference

arXiv:2608.0007720.3h-index: 4
Predicted impact top 5% in CV · last 90 daysOriginality Highly original
AI Analysis

This work addresses a critical blind spot in evaluating visual token pruning for MLLMs, specifically for OCR-critical applications, by introducing a spatial provenance audit that reveals quality-risk-traceability frontiers not captured by accuracy alone, which is important for developers and users relying on the interpretability and reliability of MLLM outputs.

This paper introduces an evidence-risk audit for visual token pruning in text-rich MLLMs, focusing on whether retained tokens are traceable to OCR regions supporting correct answers, rather than just answer accuracy. They found that while Qwen Target at 30% retention had similar accuracy to Full (0.786 vs 0.783), its positive-support coverage was significantly higher (0.620) compared to Random (0.270) and Grid (0.318) at the same budget, and achieved up to 4.32x batch-prefill speedup and 76.4% lower incremental peak memory.

Visual-token pruning is usually judged by answer quality at a fixed retention budget. For text-rich multimodal large language models (MLLMs), this protocol can miss a distinct failure: an answer remains correct even when no retained token is locally traceable to the small OCR region that supports it. We turn this blind spot into an evidence-risk audit that couples answer behavior with geometric token-origin provenance, interventions, and realized cost; transparent training-free selectors isolate controlled operating points. On locked image-disjoint confirmation, Qwen Target at 30% retention has observed accuracy 0.786 versus 0.783 for Full (paired image-cluster difference +0.003, 95% CI [-0.014, +0.020]), yet same-budget Target, Random, and Grid retain sharply different positive-support coverage: 0.620, 0.270, and 0.318. Across Qwen3-VL-8B, LLaVA-1.5-7B, and InternVL3.5-8B, matched controls, interventions, detector tests, and external methods reveal model-specific quality-risk-traceability frontiers that accuracy alone does not expose. Materialized prefixes yield up to 4.32x batch-prefill speedup and 76.4% lower incremental peak memory; full-validation TextVQA and DocVQA further show that favorable target-verification points do not imply task-general compression. Visual-token pruning should therefore report surviving spatial provenance and realized cost alongside quality and compression.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes