# Learning to Trim: End-to-End Causal Graph Pruning with Dynamic Anatomical Feature Banks for Medical VQA

arXiv: https://arxiv.org/abs/2603.26028 · HTML: https://mlsanity.com/paper/2603.26028/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training](https://mlsanity.com/paper/2209.07098/) (2022)
- [Overcoming Data Limitation in Medical Visual Question Answering](https://mlsanity.com/paper/1909.11867/) (2019)
- [Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models](https://mlsanity.com/paper/2303.05977/) (2023)
- [Self-supervised vision-language pretraining for Medical visual question answering](https://mlsanity.com/paper/2211.13594/) (2022)
- [Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering](https://mlsanity.com/paper/2307.05314/) (2023)
- [MISS: A Generative Pretraining and Finetuning Approach for Med-VQA](https://mlsanity.com/paper/2401.05163/) (2024)
- [Chest X-ray Image Classification: A Causal Perspective](https://mlsanity.com/paper/2305.12072/) (2023)
- [Structure Causal Models and LLMs Integration in Medical Visual Question Answering](https://mlsanity.com/paper/2505.02703/) (2025)
- [Test-Time Adaptation by Causal Trimming](https://mlsanity.com/paper/2510.11133/) (2025)

## Abstract (arXiv)

Medical Visual Question Answering (MedVQA) models often exhibit limited generalization due to reliance on dataset-specific correlations, such as recurring anatomical patterns or question-type regularities, rather than genuine diagnostic evidence. Existing causal approaches are typically implemented as static adjustments or post-hoc corrections. To address this issue, we propose a Learnable Causal Trimming (LCT) framework that integrates causal pruning into end-to-end optimization. We introduce a Dynamic Anatomical Feature Bank (DAFB), updated via a momentum mechanism, to capture global prototypes of frequent anatomical and linguistic patterns, serving as an approximation of dataset-level regularities. We further design a differentiable trimming module that estimates the dependency between instance-level representations and the global feature bank. Features highly correlated with global prototypes are softly suppressed, while instance-specific evidence is emphasized. This learnable mechanism encourages the model to prioritize causal signals over spurious correlations adaptively. Experiments on VQA-RAD, SLAKE, SLAKE-CP and PathVQA demonstrate that LCT consistently improves robustness and generalization over existing debiasing strategies.