Mordal: Automated Pretrained Model Selection for Vision Language Models
This addresses the problem of manual, inefficient model selection for VLMs in domains like healthcare and robotics, offering an incremental improvement through automation.
The authors tackled the lack of automated frameworks for creating task-specific vision language models (VLMs) by introducing Mordal, an automated model search framework that efficiently finds the best VLM for user-defined tasks, reducing GPU hours by up to 8.9×–11.6× compared to grid search and discovering new VLMs that outperform state-of-the-art counterparts.
Incorporating multiple modalities into large language models (LLMs) is a powerful way to enhance their understanding of non-textual data, enabling them to perform multimodal tasks. Vision language models (VLMs) form the fastest growing category of multimodal models because of their many practical use cases, including in healthcare, robotics, and accessibility. Unfortunately, even though different VLMs in the literature demonstrate impressive visual capabilities in different benchmarks, they are handcrafted by human experts; there is no automated framework to create task-specific multimodal models. We introduce Mordal, an automated multimodal model search framework that efficiently finds the best VLM for a user-defined task without manual intervention. Mordal achieves this both by reducing the number of candidates to consider during the search process and by minimizing the time required to evaluate each remaining candidate. Our evaluation shows that Mordal can find the best VLM for a given problem using up to $8.9\times$--$11.6\times$ lower GPU hours than grid search. In the process of our evaluation, we have also discovered new VLMs that outperform their state-of-the-art counterparts.