Existing visual attribution methods often fail to identify the visual evidence used by LVLMs in chest X-ray reasoning, while MedFocus using unbalanced optimal transport and targeted interventions substantially outperforms them across multiple models and settings.
Unbalanced optimal transport: Dynamic and kantorovich formulations.Journal of Functional Analysis, 274 (11):3090–3123
2 Pith papers cite this work, alongside 207 external citations. Polarity classification is still indexing.
2
Pith papers citing it
207
external citations · OpenAlex
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Order is distinct from control, where control is defined as a local receiver-gated response law demonstrated across biological circuits and LLM response panels with reported prediction accuracies of 72-84%.
citing papers explorer
-
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
Existing visual attribution methods often fail to identify the visual evidence used by LVLMs in chest X-ray reasoning, while MedFocus using unbalanced optimal transport and targeted interventions substantially outperforms them across multiple models and settings.
-
Order Is Not Control
Order is distinct from control, where control is defined as a local receiver-gated response law demonstrated across biological circuits and LLM response panels with reported prediction accuracies of 72-84%.