Learning to Ground VLMs without Forgetting

Aritra Bhowmik, Mohammad Mahdi Derakhshani, Dennis Koelma, Martin R. Oswald, Yuki M Asano, Cees G. M. Snoek

Keywords: vision language models, visual grounding, mixture of experts, synthetic datasets

Abstract:

Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Visual Language Models (VLMs) struggle at this task. In this paper, we introduce LynX, a framework that equips pretrained VLMs with visual grounding ability without forgetting their existing image and language understanding skills.
To this end, we propose a Dual Mixture of Experts module that modifies only the decoder layer of the language model, using one frozen Mixture of Experts (MoE) pre-trained on image and language understanding and another learnable MoE for new grounding capabilities. This allows the VLM to retain previously learned knowledge and skills, while acquiring what is missing.
To train the model effectively, we generate a high-quality synthetic dataset we call SCouT, which mimics human reasoning in visual grounding. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process, thereby simplifying the task of visual grounding. We evaluate LynX on several object detection and visual grounding datasets, demonstrating strong performance in object detection, zero-shot localization and grounded reasoning while maintaining its original image and language understanding capabilities on seven standard benchmark datasets.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10883