Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document

Abstract

Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Character Recognition. Despite their effectiveness, these models are too costly for real-time or resource-constrained applications. We investigate model compression through knowledge distillation, training compact student models from a larger teacher. We leverage mechanistic interpretability to drive student architecture design within this framework. By analyzing internal computations, we identify essential subcomponents to retain, while having a clear view of which subcomponents should be approximated, skipped, or reparametrized based on their function. This approach yields Donut-MINT (Mechanistic Interpretability-based Network Trimming), a pruned Donut variant that reduces inference time and memory usage while maintaining strong performance on DocVQA, a standard benchmark for document Visual Question Answering. Our method reframes compression as circuit discovery, bridging interpretability research and practical Vision-Language Model deployment.