PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs

by [unverified] · free · Last verified 2026-06-20T07:58:01.931Z

Despite remarkable progress in Multimodal Large Language Models (MLLMs), these models still struggle with fine-grained understanding tasks. In this work, we propose Procedurally Generated Tasks (PGT), a simple data-driven framework that serves a dual purpose: inducing fine-grained visual understa...